[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6AE94G59FJD0Q0J7SN2RNYQ":3,"skill-same:01M6AE94G59FJD0Q0J7SN2RNYQ":83},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":59,"commitSha":60,"skillDirectory":61,"forksCount":62,"repositoryHtmlUrl":63,"repositoryHomepageUrl":64,"ownerHtmlUrl":65,"ownerBlogUrl":66,"ownerDescription":67,"updatedAt":68,"install":69,"resources":82},"01M6AE94G59FJD0Q0J7SN2RNYQ","curviate-inbox",null,"Read and send LinkedIn messages with the Curviate CLI. Covers `inbox` (list, get, messages, search, mark-read), `inboxes` (personal and company-page discovery), `message` (new, send, get, edit, delete, react, attachment, InMail), replying as a company page, retrieval mode (`--mode`\u002F`--max-age`) on the two inbox reads, and `webhook` for delivery of message events. Use when triaging conversations, reading a thread, sending or replying to a DM or InMail, or wiring event delivery.","davila7\u002Fclaude-code-templates","davila7","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6216945?v=4","01M6ADEWWFPS191NFM0Y1EX1JH","Daniel Avila","01M6ADJHGM78PHQRD3XZTFDVKK",33481,"MIT","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fcurviate\u002Fcurviate-inbox\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"inbox","curviate inbox","curviate","new","personal","when","company","send","wiring","mode","conversations","webhook","get","delivery","message","read","Recruiting","messages","https","search","delete","plugin","react","github","cli","2026-11-10 10:12:30",false,"---\nname: curviate-inbox\ndescription: \"Read and send LinkedIn messages with the Curviate CLI. Covers `inbox` (list, get, messages, search, mark-read), `inboxes` (personal and company-page discovery), `message` (new, send, get, edit, delete, react, attachment, InMail), replying as a company page, retrieval mode (`--mode`\u002F`--max-age`) on the two inbox reads, and `webhook` for delivery of message events. Use when triaging conversations, reading a thread, sending or replying to a DM or InMail, or wiring event delivery.\"\nlicense: MIT\nmetadata:\n  version: 0.1.0\n  author: Curviate\n  tags: [LinkedIn, CLI, Agents, Sales, Recruiting, Outreach]\n  repository: https:\u002F\u002Fgithub.com\u002FCurviate\u002Fcurviate-plugin\n---\n\n# Curviate: inbox and messaging\n\nMessaging is the highest-consequence surface here: every send lands in a real person's inbox and\ncannot be unsent. Preview first, always.\n\nCommand surface established against CLI `0.33.0`.\n\n## Before any command\n\n```bash\nnpm install -g @curviate\u002Fcli && curviate --version    # needs Node 18 or newer\ncurviate login --api-key \u003Ckey>                        # or export CURVIATE_API_KEY\ncurviate account list --json                          # the acc_id for --account\n```\n\n- **Credentials resolve flag > environment > stored profile** (`CURVIATE_API_KEY`,\n  `CURVIATE_BASE_URL`, `CURVIATE_ACCOUNT`).\n- **`--profile \u003Cname>` picks the stored credential set; `--account \u003Cacc_id>` picks which connected\n  LinkedIn account sends this message.** On a multi-account tenant, getting this wrong sends from the\n  wrong person. Name the account explicitly on every write.\n- **`--preview` before every send.** It renders the resolved request (recipient, text, acting\n  account) without sending. On a read command it is refused with exit `2`.\n- **`--json` on anything you parse**; **`--fields a,b,c`** to project (a message carries 22 fields);\n  **`--verbose`** when a slim response looks suspiciously empty.\n- **Put global flags at the end of the command.**\n- **Branch on the exit code, never on prose.** See the table at the end.\n\n### Text input\n\nMessage text is a positional argument, and `-` reads stdin. **Use a quoted heredoc**: the quoted\ndelimiter disables every shell expansion, so apostrophes, accents, `$` and backticks survive intact.\nAn unquoted heredoc has produced an empty message that went out blank.\n\n```bash\ncat \u003C\u003C'EOF' | curviate message send \"\u003Cchat_id>\" - --preview\nHi Thomas,\n\nthanks for connecting. I saw the work you shared last week.\nEOF\n```\n\n## Retrieval mode: `--mode` and `--max-age`\n\nExactly four reads decide between a stored copy and a live LinkedIn call: `profile me`,\n`profile \u003Cid>`, `inbox get` and `inbox messages`. Two of them are here.\n\n| `--mode` | Behaviour |\n|---|---|\n| `auto` (default) | A stored copy while it is fresh, otherwise fetch. |\n| `live` | Always fetch from LinkedIn. |\n| `refill` | A stored copy at any age; fetch only when nothing is stored. |\n| `cache_only` | Never fetch. A store miss is refused, not fetched. |\n\n`--max-age \u003Cseconds>` (0 to 31536000) overrides those presets in both directions; `--max-age 0` is\nthe same as `--mode live`. Every response carries `source: store | live` plus `observed_at` under\n`--json`, and a `provenance:` line on stderr in human mode. Read `source` rather than assuming.\n\n- **`cache_only` with `--max-age` is a usage error, exit `2`**, raised before any network call.\n  `cache_only` never reaches LinkedIn at any age, so a freshness threshold cannot change its answer.\n  Drop `--max-age`, or use `--mode refill`.\n- **`cache_only` on a store miss is exit `14` (`NOT_STORED`)**: the chat may exist perfectly well on\n  LinkedIn, this API just holds no copy. It is not \"not found\" (`4`), so re-checking the chat id is\n  the wrong move, and it is not retryable as sent. Re-read with `refill`, `auto` or `live`.\n- **`inbox messages`: one bare `--mode live` page restarts the chat walk and leaves it unservable by\n  `cache_only` afterwards.** A listing is served from the store only over a *closed* walk.\n  `inbox messages --all` walks to `cursor: null` and closes it. When you need a chat to be\n  `cache_only`-servable later, reach for `--all` rather than a single live page.\n- **Every other command refuses the flags outright rather than ignoring them**: `unknown flag\n  --mode`, exit `2`.\n\n## Reading: `inbox`\n\n| Command | What it does | Confidence |\n|---|---|---|\n| `curviate inbox list` | Conversations, newest activity first, 20 by default. `--unread` \u002F `--no-unread` filter by read state; `--inbox \u003Cfolder>` selects `primary` (default), `inmail`, `archived`, `spam`, `jobs` or `starred`. | proven |\n| `curviate inbox get \u003Cchat_id>` | One chat's detail including `last_message` (full text and sender), the cheap triage read. Accepts `--mode`\u002F`--max-age`. | proven |\n| `curviate inbox messages \u003Cchat_id>` | The messages in one chat. Full `text` per message; `is_sender` (0 or 1) says who sent each. `--before`\u002F`--after` take ISO-8601 UTC with a `Z` suffix. Accepts `--mode`\u002F`--max-age`. | proven |\n| `curviate inbox search \"\u003Cquery>\"` | Free-text search of the account's own inbox: participant names and message content. | proven |\n| `curviate inbox mark-read \u003Cchat_id>` | Mark a chat read. | proven |\n\n**Listing chats does not mark anything read**, so triage freely.\n\nA chat item already carries the counterpart's identity: `user_id` (the `ACoAA…` member id), an\nembedded `user{}` (`id`, `type`, `display_name`, `profile_url`, `public_picture_url`), and `name`,\nthe chat's own display name, which is populated on direct messages. Escalate to `curviate profile\n\u003Cuser_id>` only for what `user{}` does not carry: headline, network distance, the full profile.\n\n### Traps\n\n- **`--limit` on `inbox list` and `inbox messages` is validated client-side to 1-25** (default 20).\n  Outside that range the command exits `2`.\n- **Neither `inbox list` nor `inbox search` reliably answers \"does a chat with X exist\".** A single\n  `inbox list --limit 25` call has repeatedly omitted a chat created seconds earlier, across\n  candidates, not a one-off race. `inbox search` has a different defect: its result set is ranked\n  and capped rather than exhaustive, so a common first name can omit an exact match that a rarer name\n  finds immediately. When the answer matters, walk `inbox list` by `--cursor` to exhaustion (or a\n  generous `--max-pages`) rather than trusting one page or the search.\n- **Inbox threads carry no vanity slug.** `user.profile_url` is built from the member id and\n  `public_identifier` is absent even under `--verbose`. Join inbox-driven flows on the member id.\n- **`inbox list` has no date-range flags.** `--before`\u002F`--after` exist on `inbox messages` only, and\n  filter messages within one chat. Filter a chat list client-side on `last_message_timestamp`.\n- **A very recent send or delete can take minutes to appear in `inbox messages`** (LinkedIn-side\n  indexing). `message get \u003Cchat_id> \u003Cmessage_id>` reflects it immediately, use that to confirm a\n  send, not a re-list.\n\n## Discovering inboxes: `inboxes`\n\n| Command | What it does | Confidence |\n|---|---|---|\n| `curviate inboxes list` | Every inbox the account can act in: its own, plus the company pages it administers. `--kind personal\\|company` and `--company-id \u003Cid>` narrow it. Beta. | proven |\n| `curviate inboxes chats \u003Cinbox_id>` | One inbox's conversations. Each chat id is send-ready. Beta. | proven |\n\n**A `COMPANY_…` chat id sends as that page, with no extra flag.** Pass it to `message send` and the\nmessage goes out from the page rather than from you; the output confirms with\n`Sent as \u003Cname> (company page)`. Company inboxes are reply-only: they cannot start a conversation.\nThe page's own admin inbox has a second, richer surface under `company` (see `curviate-profile`).\n\n## Sending: `message`\n\n| Command | What it does | Confidence |\n|---|---|---|\n| `curviate message new --to \u003Crecipient> \"\u003Ctext>\"` | Start a new chat. `--to` takes a profile URL, a bare slug or a member id, and resolves it for you. `--attach \u003Cfile>` is repeatable. | proven |\n| `curviate message send \u003Cchat_id> \"\u003Ctext>\"` | Reply in an existing chat. A `COMPANY_` chat id sends as that page. | proven |\n| `curviate message get \u003Cchat_id> \u003Cmessage_id>` | One message. Reflects a very recent send immediately, unlike the thread listing. | proven |\n| `curviate message edit \u003Cchat_id> \u003Cmessage_id> \"\u003Ctext>\"` | Edit a message within LinkedIn's allowed window. | proven |\n| `curviate message delete \u003Cchat_id> \u003Cmessage_id>` | Delete a message. | proven |\n| `curviate message react \u003Cchat_id> \u003Cmessage_id> \u003Cemoji>` | Add an emoji reaction to a message. | proven |\n| `curviate message attachment \u003Cchat_id> \u003Cmessage_id> \u003Cattachment_id>` | Download an attachment. | proven |\n| `curviate message inmail --to \u003Crecipient> --subject \"\u003Csubject>\" \"\u003Ctext>\"` | Send an InMail. Both `--to` and `--subject` are required. Consumes an InMail credit. | proven |\n| `curviate message inmail-balance` | Remaining InMail credits. Check before a run that depends on them. | proven |\n\n**Chat ids** look like `CLASSIC_2-MzJmZTg1…` for a personal chat and `COMPANY_\u003Cid>_2-…` for a page.\n\n**There is no idempotency key and no server-side de-duplication.** A send that times out may already\nhave landed. Re-read the thread (`inbox messages`, or `message get` for the id you just wrote)\nbefore re-issuing anything.\n\n## Event delivery: `webhook`\n\nMessage and account events arrive by webhook rather than by polling.\n\n| Command | What it does | Confidence |\n|---|---|---|\n| `curviate webhook create --source \u003Cs> --request-url \u003Chttps url> --account-ids \u003Cids>` | Register an endpoint. `--source` is `messaging`, `user` or `account_status`. Also `--name`, `--events`, `--data`, `--no-enabled`. | proven |\n| `curviate webhook list` | Registered webhooks. | proven |\n| `curviate webhook events` | The canonical event catalogue, read it before subscribing to a name. | proven |\n| `curviate webhook get \u003Cid>` | One webhook. | proven |\n| `curviate webhook update \u003Cid>` | Update in place. `--request-url`, `--name`, `--enabled`, `--events`, `--data`, `--account-ids`. The source is immutable. | proven |\n| `curviate webhook delete \u003Cid>` | Remove a subscription permanently. | proven |\n| `curviate webhook verify --secret \u003Cs> --header \u003Csig> --body \u003Cjson\\|file\\|->` | Verify a delivery signature offline, no network call. `--max-age-secs` rejects a replay older than the given age (default 300). | proven |\n\nVerify the signature on every delivery before acting on its body.\n\n## Full command surface\n\n\u003C!-- generated: command surface, CLI 0.33.0 -->\n\nRead from the CLI's own `--help` at version 0.33.0. Descriptions, traps and confidence\ntags elsewhere in this skill are hand-written and carry the version they were established against.\n\nEvery command below that takes flags at all also accepts `--json`.\n\n| Command | Arguments | Flags |\n|---|---|---|\n| `curviate inbox list` | *(none)* | `--api-key`, `--profile`, `--account`, `--base-url`, `--timeout`, `--fields`, `--limit`, `--cursor`, `--all`, `--max-pages`, `--page-delay`, `--preview`, `--verbose`, `--beta`, `--unread`, `--inbox` |\n| `curviate inbox get` | `CHATID` | `--api-key`, `--profile`, `--account`, `--base-url`, `--timeout`, `--fields`, `--preview`, `--verbose`, `--beta`, `--mode`, `--max-age` |\n| `curviate inbox mark-read` | `CHATID` | `--api-key`, `--profile`, `--account`, `--base-url`, `--timeout`, `--fields`, `--preview`, `--verbose`, `--beta` |\n| `curviate inbox messages` | `CHATID` | `--api-key`, `--profile`, `--account`, `--base-url`, `--timeout`, `--fields`, `--limit`, `--cursor`, `--all`, `--max-pages`, `--page-delay`, `--preview`, `--verbose`, `--beta`, `--mode`, `--max-age`, `--before`, `--after` |\n| `curviate inbox search` | `QUERY` | `--api-key`, `--profile`, `--account`, `--base-url`, `--timeout`, `--fields`, `--limit`, `--cursor`, `--all`, `--max-pages`, `--page-delay`, `--preview`, `--verbose`, `--beta` |\n| `curviate inboxes list` | *(none)* | `--api-key`, `--profile`, `--account`, `--base-url`, `--timeout`, `--fields`, `--preview`, `--verbose`, `--beta`, `--kind`, `--company-id` |\n| `curviate inboxes chats` | `INBOXID` | `--api-key`, `--profile`, `--account`, `--base-url`, `--timeout`, `--fields`, `--limit`, `--cursor`, `--all`, `--max-pages`, `--page-delay`, `--preview`, `--verbose`, `--beta` |\n| `curviate message` | `CHATID` `TEXT` | `--api-key`, `--profile`, `--account`, `--base-url`, `--timeout`, `--preview`, `--verbose`, `--beta`, `--attach` |\n| `curviate message new` | `TEXT` | `--api-key`, `--profile`, `--account`, `--base-url`, `--timeout`, `--preview`, `--verbose`, `--beta`, `--to` *(required)*, `--attach` |\n| `curviate message send` | `CHATID` `TEXT` | `--api-key`, `--profile`, `--account`, `--base-url`, `--timeout`, `--preview`, `--verbose`, `--beta`, `--attach` |\n| `curviate message get` | `CHATID` `MESSAGEID` | `--api-key`, `--profile`, `--account`, `--base-url`, `--timeout`, `--fields`, `--preview`, `--verbose`, `--beta` |\n| `curviate message edit` | `CHATID` `MESSAGEID` `TEXT` | `--api-key`, `--profile`, `--account`, `--base-url`, `--timeout`, `--preview`, `--verbose`, `--beta` |\n| `curviate message delete` | `CHATID` `MESSAGEID` | `--api-key`, `--profile`, `--account`, `--base-url`, `--timeout`, `--preview`, `--verbose`, `--beta` |\n| `curviate message react` | `CHATID` `MESSAGEID` `EMOJI` | `--api-key`, `--profile`, `--account`, `--base-url`, `--timeout`, `--preview`, `--verbose`, `--beta`, `-emoji, --emojiAlias` |\n| `curviate message attachment` | `CHATID` `MESSAGEID` `ATTACHMENTID` | `--api-key`, `--profile`, `--account`, `--base-url`, `--timeout`, `--fields`, `--preview`, `--verbose`, `--beta`, `-o, --output` |\n| `curviate message inmail` | `TEXT` | `--api-key`, `--profile`, `--account`, `--base-url`, `--timeout`, `--preview`, `--verbose`, `--beta`, `--to` *(required)*, `--subject` *(required)* |\n| `curviate message inmail-balance` | *(none)* | `--api-key`, `--profile`, `--account`, `--base-url`, `--timeout`, `--fields`, `--preview`, `--verbose`, `--beta` |\n| `curviate webhook create` | *(none)* | `--api-key`, `--profile`, `--account`, `--base-url`, `--timeout`, `--fields`, `--limit`, `--cursor`, `--preview`, `--verbose`, `--beta`, `--source` *(required)*, `--request-url` *(required)*, `--account-ids` *(required)*, `--name`, `--no-enabled`, `--events`, `--data` |\n| `curviate webhook list` | *(none)* | `--api-key`, `--profile`, `--account`, `--base-url`, `--timeout`, `--fields`, `--limit`, `--cursor`, `--all`, `--max-pages`, `--page-delay`, `--preview`, `--verbose`, `--beta` |\n| `curviate webhook events` | *(none)* | `--api-key`, `--profile`, `--account`, `--base-url`, `--timeout`, `--fields`, `--limit`, `--cursor`, `--preview`, `--verbose`, `--beta` |\n| `curviate webhook get` | `ID` | `--api-key`, `--profile`, `--account`, `--base-url`, `--timeout`, `--fields`, `--limit`, `--cursor`, `--preview`, `--verbose`, `--beta` |\n| `curviate webhook update` | `ID` | `--api-key`, `--profile`, `--account`, `--base-url`, `--timeout`, `--fields`, `--limit`, `--cursor`, `--preview`, `--verbose`, `--beta`, `--request-url`, `--name`, `--enabled`, `--events`, `--data`, `--account-ids` |\n| `curviate webhook delete` | `ID` | `--api-key`, `--profile`, `--account`, `--base-url`, `--timeout`, `--fields`, `--limit`, `--cursor`, `--preview`, `--verbose`, `--beta` |\n| `curviate webhook verify` | *(none)* | `--secret` *(required)*, `--header` *(required)*, `--body` *(required)*, `--max-age-secs` |\n\n\u003C!-- \u002Fgenerated -->\n\n## Exit codes to branch on here\n\n| Code | Meaning | What to do |\n|---|---|---|\n| `1` | `INTERNAL` from the server itself: a genuine bug on the platform side. | Worth one retry; if it repeats it is a bug to report, not a state to work around. |\n| `2` | Usage or invalid input, often raised before any network call: a `--limit` outside 1-25, `cache_only` with `--max-age`, a missing `--subject` on an InMail. | Fix the invocation. Never retry unchanged. |\n| `4` | Not found: a wrong chat, message or member identifier. | Re-resolve the id; do not retry as sent. |\n| `5` | Three causes, one code: read `error.code`. `NO_ACTIVE_SEAT`: the account is on no active seat. `LINKEDIN_FEATURE_NOT_SUBSCRIBED`: LinkedIn itself lacks the feature. `BETA_NOT_ENABLED`: the operation is beta-gated and this workspace has not opted in (pass `--beta` for one call, or a human enables it in Settings). | Branch on `error.code`: the three fixes have nothing in common, and none is fixed by retrying unchanged. |\n| `6` | `PLATFORM_RATE_LIMIT` and its siblings. Carries `retry_after` in whole seconds. A response naming `budgetRow` means only that row is paused; every other row on the account keeps working. | **Back off and retry** after that many seconds. On a named `budgetRow`, switch to other work on the account rather than backing off across the board. |\n| `7` | Transient platform fault: a request that got no response at all (network error, DNS failure, timeout) or one that came back as something other than a valid API answer. Carries `retryLikelyToSucceed: true`. | Retry with backoff. |\n| `8` | Account or connection state. Read `error.code`: `ACCOUNT_RESTRICTED`, `LINKEDIN_AUTH_FAILED`, `LINKEDIN_COOKIE_INVALID` need a reconnect. | Depends on `error.code`. |\n| `10` | The edit or delete window expired, or the recipient is unreachable. | Not retryable as sent. Do not resend. |\n| `13` | `BUDGET_EXHAUSTED`: a safety rule of your own refused the send, not LinkedIn. Read `error.safetyReason`: `ceiling` means the row named in `error.budgetRow` hit its configured limit; `activity_window` means the account is outside the hours it works in (no `budgetRow` on that one). **Nothing reached LinkedIn and nothing was spent; the message was not delivered.** `reset_at` can be weeks out, and may be `null` where no clock frees it. | **Do not back off and retry.** `error.safetyHint.parameter` names the exact setting to change. Read `quotas[]` via `curviate account get \u003Cacc_id> --json`, then wait for the named reset or change that setting. |\n| `14` | `NOT_STORED`: a `cache_only` read the store cannot answer. | Re-read with `refill`, `auto` or `live`. |\n","# Curviate: inbox and messaging\n\nMessaging is the highest-consequence surface here: every send lands in a real person's inbox and\ncannot be unsent. Preview first, always.\n\nCommand surface established against CLI `0.33.0`.\n\n## Before any command\n\n```bash\nnpm install -g @curviate\u002Fcli && curviate --version    # needs Node 18 or newer\ncurviate login --api-key \u003Ckey>                        # or export CURVIATE_API_KEY\ncurviate account list --json                          # the acc_id for --account\n```\n\n- **Credentials resolve flag > environment > stored profile** (`CURVIATE_API_KEY`,\n  `CURVIATE_BASE_URL`, `CURVIATE_ACCOUNT`).\n- **`--profile \u003Cname>` picks the stored credential set; `--account \u003Cacc_id>` picks which connected\n  LinkedIn account sends this message.** On a multi-account tenant, getting this wrong sends from the\n  wrong person. Name the account explicitly on every write.\n- **`--preview` before every send.** It renders the resolved request (recipient, text, acting\n  account) without sending. On a read command it is refused with exit `2`.\n- **`--json` on anything you parse**; **`--fields a,b,c`** to project (a message carries 22 fields);\n  **`--verbose`** when a slim response looks suspiciously empty.\n- **Put global flags at the end of the command.**\n- **Branch on the exit code, never on prose.** See the table at the end.\n\n### Text input\n\nMessage text is a positional argument, and `-` reads stdin. **Use a quoted heredoc**: the quoted\ndelimiter disables every shell expansion, so apostrophes, accents, `$` and backticks survive intact.\nAn unquoted heredoc has produced an empty message that went out blank.\n\n```bash\ncat \u003C\u003C'EOF' | curviate message send \"\u003Cchat_id>\" - --preview\nHi Thomas,\n\nthanks for connecting. I saw the work you shared last week.\nEOF\n```\n\n## Retrieval mode: `--mode` and `--max-age`\n\nExactly four reads decide between a stored copy and a live LinkedIn call: `profile me`,\n`profile \u003Cid>`, `inbox get` and `inbox messages`. Two of them are here.\n\n| `--mode` | Behaviour |\n|---|---|\n| `auto` (default) | A stored copy while it is fresh, otherwise fetch. |\n| `live` | Always fetch from LinkedIn. |\n| `refill` | A stored copy at any age; fetch only when nothing is stored. |\n| `cache_only` | Never fetch. A store miss is refused, not fetched. |\n\n`--max-age \u003Cseconds>` (0 to 31536000) overrides those presets in both directions; `--max-age 0` is\nthe same as `--mode live`. Every response carries `source: store | live` plus `observed_at` under\n`--json`, and a `provenance:` line on stderr in human mode. Read `source` rather than assuming.\n\n- **`cache_only` with `--max-age` is a usage error, exit `2`**, raised before any network call.\n  `cache_only` never reaches LinkedIn at any age, so a freshness threshold cannot change its answer.\n  Drop `--max-age`, or use `--mode refill`.\n- **`cache_only` on a store miss is exit `14` (`NOT_STORED`)**: the chat may exist perfectly well on\n  LinkedIn, this API just holds no copy. It is not \"not found\" (`4`), so re-checking the chat id is\n  the wrong move, and it is not retryable as sent. Re-read with `refill`, `auto` or `live`.\n- **`inbox messages`: one bare `--mode live` page restarts the chat walk and leaves it unservable by\n  `cache_only` afterwards.** A listing is served from the store only over a *closed* walk.\n  `inbox messages --all` walks to `cursor: null` and closes it. When you need a chat to be\n  `cache_only`-servable later, reach for `--all` rather than a single live page.\n- **Every other command refuses the flags outright rather than ignoring them**: `unknown flag\n  --mode`, exit `2`.\n\n## Reading: `inbox`\n\n| Command | What it does | Confidence |\n|---|---|---|\n| `curviate inbox list` | Conversations, newest activity first, 20 by default. `--unread` \u002F `--no-unread` filter by read state; `--inbox \u003Cfolder>` selects `primary` (default), `inmail`, `archived`, `spam`, `jobs` or `starred`. | proven |\n| `curviate inbox get \u003Cchat_id>` | One chat's detail including `last_message` (full text and sender), the cheap triage read. Accepts `--mode`\u002F`--max-age`. | proven |\n| `curviate inbox messages \u003Cchat_id>` | The messages in one chat. Full `text` per message; `is_sender` (0 or 1) says who sent each. `--before`\u002F`--after` take ISO-8601 UTC with a `Z` suffix. Accepts `--mode`\u002F`--max-age`. | proven |\n| `curviate inbox search \"\u003Cquery>\"` | Free-text search of the account's own inbox: participant names and message content. | proven |\n| `curviate inbox mark-read \u003Cchat_id>` | Mark a chat read. | proven |\n\n**Listing chats does not mark anything read**, so triage freely.\n\nA chat item already carries the counterpart's identity: `user_id` (the `ACoAA…` member id), an\nembedded `user{}` (`id`, `type`, `display_name`, `profile_url`, `public_picture_url`), and `name`,\nthe chat's own display name, which is populated on direct messages. Escalate to `curviate profile\n\u003Cuser_id>` only for what `user{}` does not carry: headline, network distance, the full profile.\n\n### Traps\n\n- **`--limit` on `inbox list` and `inbox messages` is validated client-side to 1-25** (default 20).\n  Outside that range the command exits `2`.\n- **Neither `inbox list` nor `inbox search` reliably answers \"does a chat with X exist\".** A single\n  `inbox list --limit 25` call has repeatedly omitted a chat created seconds earlier, across\n  candidates, not a one-off race. `inbox search` has a different defect: its result set is ranked\n  and capped rather than exhaustive, so a common first name can omit an exact match that a rarer name\n  finds immediately. When the answer matters, walk `inbox list` by `--cursor` to exhaustion (or a\n  generous `--max-pages`) rather than trusting one page or the search.\n- **Inbox threads carry no vanity slug.** `user.profile_url` is built from the member id and\n  `public_identifier` is absent even under `--verbose`. Join inbox-driven flows on the member id.\n- **`inbox list` has no date-range flags.** `--before`\u002F`--after` exist on `inbox messages` only, and\n  filter messages within one chat. Filter a chat list client-side on `last_message_timestamp`.\n- **A very recent send or delete can take minutes to appear in `inbox messages`** (LinkedIn-side\n  indexing). `message get \u003Cchat_id> \u003Cmessage_id>` reflects it immediately, use that to confirm a\n  send, not a re-list.\n\n## Discovering inboxes: `inboxes`\n\n| Command | What it does | Confidence |\n|---|---|---|\n| `curviate inboxes list` | Every inbox the account can act in: its own, plus the company pages it administers. `--kind personal\\|company` and `--company-id \u003Cid>` narrow it. Beta. | proven |\n| `curviate inboxes chats \u003Cinbox_id>` | One inbox's conversations. Each chat id is send-ready. Beta. | proven |\n\n**A `COMPANY_…` chat id sends as that page, with no extra flag.** Pass it to `message send` and the\nmessage goes out from the page rather than from you; the output confirms with\n`Sent as \u003Cname> (company page)`. Company inboxes are reply-only: they cannot start a conversation.\nThe page's own admin inbox has a second, richer surface under `company` (see `curviate-profile`).\n\n## Sending: `message`\n\n| Command | What it does | Confidence |\n|---|---|---|\n| `curviate message new --to \u003Crecipient> \"\u003Ctext>\"` | Start a new chat. `--to` takes a profile URL, a bare slug or a member id, and resolves it for you. `--attach \u003Cfile>` is repeatable. | proven |\n| `curviate message send \u003Cchat_id> \"\u003Ctext>\"` | Reply in an existing chat. A `COMPANY_` chat id sends as that page. | proven |\n| `curviate message get \u003Cchat_id> \u003Cmessage_id>` | One message. Reflects a very recent send immediately, unlike the thread listing. | proven |\n| `curviate message edit \u003Cchat_id> \u003Cmessage_id> \"\u003Ctext>\"` | Edit a message within LinkedIn's allowed window. | proven |\n| `curviate message delete \u003Cchat_id> \u003Cmessage_id>` | Delete a message. | proven |\n| `curviate message react \u003Cchat_id> \u003Cmessage_id> \u003Cemoji>` | Add an emoji reaction to a message. | proven |\n| `curviate message attachment \u003Cchat_id> \u003Cmessage_id> \u003Cattachment_id>` | Download an attachment. | proven |\n| `curviate message inmail --to \u003Crecipient> --subject \"\u003Csubject>\" \"\u003Ctext>\"` | Send an InMail. Both `--to` and `--subject` are required. Consumes an InMail credit. | proven |\n| `curviate message inmail-balance` | Remaining InMail credits. Check before a run that depends on them. | proven |\n\n**Chat ids** look like `CLASSIC_2-MzJmZTg1…` for a personal chat and `COMPANY_\u003Cid>_2-…` for a page.\n\n**There is no idempotency key and no server-side de-duplication.** A send that times out may already\nhave landed. Re-read the thread (`inbox messages`, or `message get` for the id you just wrote)\nbefore re-issuing anything.\n\n## Event delivery: `webhook`\n\nMessage and account events arrive by webhook rather than by polling.\n\n| Command | What it does | Confidence |\n|---|---|---|\n| `curviate webhook create --source \u003Cs> --request-url \u003Chttps url> --account-ids \u003Cids>` | Register an endpoint. `--source` is `messaging`, `user` or `account_status`. Also `--name`, `--events`, `--data`, `--no-enabled`. | proven |\n| `curviate webhook list` | Registered webhooks. | proven |\n| `curviate webhook events` | The canonical event catalogue, read it before subscribing to a name. | proven |\n| `curviate webhook get \u003Cid>` | One webhook. | proven |\n| `curviate webhook update \u003Cid>` | Update in place. `--request-url`, `--name`, `--enabled`, `--events`, `--data`, `--account-ids`. The source is immutable. | proven |\n| `curviate webhook delete \u003Cid>` | Remove a subscription permanently. | proven |\n| `curviate webhook verify --secret \u003Cs> --header \u003Csig> --body \u003Cjson\\|file\\|->` | Verify a delivery signature offline, no network call. `--max-age-secs` rejects a replay older than the given age (default 300). | proven |\n\nVerify the signature on every delivery before acting on its body.\n\n## Full command surface\n\n\u003C!-- generated: command surface, CLI 0.33.0 -->\n\nRead from the CLI's own `--help` at version 0.33.0. Descriptions, traps and confidence\ntags elsewhere in this skill are hand-written and carry the version they were established against.\n\nEvery command below that takes flags at all also accepts `--json`.\n\n| Command | Arguments | Flags |\n|---|---|---|\n| `curviate inbox list` | *(none)* | `--api-key`, `--profile`, `--account`, `--base-url`, `--timeout`, `--fields`, `--limit`, `--cursor`, `--all`, `--max-pages`, `--page-delay`, `--preview`, `--verbose`, `--beta`, `--unread`, `--inbox` |\n| `curviate inbox get` | `CHATID` | `--api-key`, `--profile`, `--account`, `--base-url`, `--timeout`, `--fields`, `--preview`, `--verbose`, `--beta`, `--mode`, `--max-age` |\n| `curviate inbox mark-read` | `CHATID` | `--api-key`, `--profile`, `--account`, `--base-url`, `--timeout`, `--fields`, `--preview`, `--verbose`, `--beta` |\n| `curviate inbox messages` | `CHATID` | `--api-key`, `--profile`, `--account`, `--base-url`, `--timeout`, `--fields`, `--limit`, `--cursor`, `--all`, `--max-pages`, `--page-delay`, `--preview`, `--verbose`, `--beta`, `--mode`, `--max-age`, `--before`, `--after` |\n| `curviate inbox search` | `QUERY` | `--api-key`, `--profile`, `--account`, `--base-url`, `--timeout`, `--fields`, `--limit`, `--cursor`, `--all`, `--max-pages`, `--page-delay`, `--preview`, `--verbose`, `--beta` |\n| `curviate inboxes list` | *(none)* | `--api-key`, `--profile`, `--account`, `--base-url`, `--timeout`, `--fields`, `--preview`, `--verbose`, `--beta`, `--kind`, `--company-id` |\n| `curviate inboxes chats` | `INBOXID` | `--api-key`, `--profile`, `--account`, `--base-url`, `--timeout`, `--fields`, `--limit`, `--cursor`, `--all`, `--max-pages`, `--page-delay`, `--preview`, `--verbose`, `--beta` |\n| `curviate message` | `CHATID` `TEXT` | `--api-key`, `--profile`, `--account`, `--base-url`, `--timeout`, `--preview`, `--verbose`, `--beta`, `--attach` |\n| `curviate message new` | `TEXT` | `--api-key`, `--profile`, `--account`, `--base-url`, `--timeout`, `--preview`, `--verbose`, `--beta`, `--to` *(required)*, `--attach` |\n| `curviate message send` | `CHATID` `TEXT` | `--api-key`, `--profile`, `--account`, `--base-url`, `--timeout`, `--preview`, `--verbose`, `--beta`, `--attach` |\n| `curviate message get` | `CHATID` `MESSAGEID` | `--api-key`, `--profile`, `--account`, `--base-url`, `--timeout`, `--fields`, `--preview`, `--verbose`, `--beta` |\n| `curviate message edit` | `CHATID` `MESSAGEID` `TEXT` | `--api-key`, `--profile`, `--account`, `--base-url`, `--timeout`, `--preview`, `--verbose`, `--beta` |\n| `curviate message delete` | `CHATID` `MESSAGEID` | `--api-key`, `--profile`, `--account`, `--base-url`, `--timeout`, `--preview`, `--verbose`, `--beta` |\n| `curviate message react` | `CHATID` `MESSAGEID` `EMOJI` | `--api-key`, `--profile`, `--account`, `--base-url`, `--timeout`, `--preview`, `--verbose`, `--beta`, `-emoji, --emojiAlias` |\n| `curviate message attachment` | `CHATID` `MESSAGEID` `ATTACHMENTID` | `--api-key`, `--profile`, `--account`, `--base-url`, `--timeout`, `--fields`, `--preview`, `--verbose`, `--beta`, `-o, --output` |\n| `curviate message inmail` | `TEXT` | `--api-key`, `--profile`, `--account`, `--base-url`, `--timeout`, `--preview`, `--verbose`, `--beta`, `--to` *(required)*, `--subject` *(required)* |\n| `curviate message inmail-balance` | *(none)* | `--api-key`, `--profile`, `--account`, `--base-url`, `--timeout`, `--fields`, `--preview`, `--verbose`, `--beta` |\n| `curviate webhook create` | *(none)* | `--api-key`, `--profile`, `--account`, `--base-url`, `--timeout`, `--fields`, `--limit`, `--cursor`, `--preview`, `--verbose`, `--beta`, `--source` *(required)*, `--request-url` *(required)*, `--account-ids` *(required)*, `--name`, `--no-enabled`, `--events`, `--data` |\n| `curviate webhook list` | *(none)* | `--api-key`, `--profile`, `--account`, `--base-url`, `--timeout`, `--fields`, `--limit`, `--cursor`, `--all`, `--max-pages`, `--page-delay`, `--preview`, `--verbose`, `--beta` |\n| `curviate webhook events` | *(none)* | `--api-key`, `--profile`, `--account`, `--base-url`, `--timeout`, `--fields`, `--limit`, `--cursor`, `--preview`, `--verbose`, `--beta` |\n| `curviate webhook get` | `ID` | `--api-key`, `--profile`, `--account`, `--base-url`, `--timeout`, `--fields`, `--limit`, `--cursor`, `--preview`, `--verbose`, `--beta` |\n| `curviate webhook update` | `ID` | `--api-key`, `--profile`, `--account`, `--base-url`, `--timeout`, `--fields`, `--limit`, `--cursor`, `--preview`, `--verbose`, `--beta`, `--request-url`, `--name`, `--enabled`, `--events`, `--data`, `--account-ids` |\n| `curviate webhook delete` | `ID` | `--api-key`, `--profile`, `--account`, `--base-url`, `--timeout`, `--fields`, `--limit`, `--cursor`, `--preview`, `--verbose`, `--beta` |\n| `curviate webhook verify` | *(none)* | `--secret` *(required)*, `--header` *(required)*, `--body` *(required)*, `--max-age-secs` |\n\n\u003C!-- \u002Fgenerated -->\n\n## Exit codes to branch on here\n\n| Code | Meaning | What to do |\n|---|---|---|\n| `1` | `INTERNAL` from the server itself: a genuine bug on the platform side. | Worth one retry; if it repeats it is a bug to report, not a state to work around. |\n| `2` | Usage or invalid input, often raised before any network call: a `--limit` outside 1-25, `cache_only` with `--max-age`, a missing `--subject` on an InMail. | Fix the invocation. Never retry unchanged. |\n| `4` | Not found: a wrong chat, message or member identifier. | Re-resolve the id; do not retry as sent. |\n| `5` | Three causes, one code: read `error.code`. `NO_ACTIVE_SEAT`: the account is on no active seat. `LINKEDIN_FEATURE_NOT_SUBSCRIBED`: LinkedIn itself lacks the feature. `BETA_NOT_ENABLED`: the operation is beta-gated and this workspace has not opted in (pass `--beta` for one call, or a human enables it in Settings). | Branch on `error.code`: the three fixes have nothing in common, and none is fixed by retrying unchanged. |\n| `6` | `PLATFORM_RATE_LIMIT` and its siblings. Carries `retry_after` in whole seconds. A response naming `budgetRow` means only that row is paused; every other row on the account keeps working. | **Back off and retry** after that many seconds. On a named `budgetRow`, switch to other work on the account rather than backing off across the board. |\n| `7` | Transient platform fault: a request that got no response at all (network error, DNS failure, timeout) or one that came back as something other than a valid API answer. Carries `retryLikelyToSucceed: true`. | Retry with backoff. |\n| `8` | Account or connection state. Read `error.code`: `ACCOUNT_RESTRICTED`, `LINKEDIN_AUTH_FAILED`, `LINKEDIN_COOKIE_INVALID` need a reconnect. | Depends on `error.code`. |\n| `10` | The edit or delete window expired, or the recipient is unreachable. | Not retryable as sent. Do not resend. |\n| `13` | `BUDGET_EXHAUSTED`: a safety rule of your own refused the send, not LinkedIn. Read `error.safetyReason`: `ceiling` means the row named in `error.budgetRow` hit its configured limit; `activity_window` means the account is outside the hours it works in (no `budgetRow` on that one). **Nothing reached LinkedIn and nothing was spent; the message was not delivered.** `reset_at` can be weeks out, and may be `null` where no clock frees it. | **Do not back off and retry.** `error.safetyHint.parameter` names the exact setting to change. Read `quotas[]` via `curviate account get \u003Cacc_id> --json`, then wait for the named reset or change that setting. |\n| `14` | `NOT_STORED`: a `cache_only` read the store cannot answer. | Re-read with `refill`, `auto` or `live`. |\n",{"name":5,"license":15,"metadata":49,"description":7},{"tags":50,"author":56,"version":57,"repository":58},[51,52,53,54,35,55],"LinkedIn","CLI","Agents","Sales","Outreach","Curviate","0.1.0","https:\u002F\u002Fgithub.com\u002FCurviate\u002Fcurviate-plugin","main","2b749c82b5d11fac39d9a6e021ce3f5b8a541bd1","cli-tool\u002Fcomponents\u002Fskills\u002Fcurviate\u002Fcurviate-inbox",3931,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates","https:\u002F\u002Faitmpl.com","https:\u002F\u002Fgithub.com\u002Fdavila7","https:\u002F\u002Fdanielavila.me","Building AI dev tools with LLMs","2026-11-14 06:14:46",{"source":8,"skillName":5,"commands":70,"prompt":80,"zipAvailable":81},[71,74,77],{"tool":72,"command":73},"npx","npx skills add davila7\u002Fclaude-code-templates --skill curviate-inbox",{"tool":75,"command":76},"bunx","bunx skills add davila7\u002Fclaude-code-templates --skill curviate-inbox",{"tool":78,"command":79},"pnpm","pnpm dlx skills add davila7\u002Fclaude-code-templates --skill curviate-inbox","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fcurviate\u002Fcurviate-inbox\u002FSKILL.md",true,[],[84,115,142,175,209,233],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":95,"publishedAt":44},"01M70NHBTQ8BV0A2SCAZXEPHCX","wealthville-pool-scoring","Score DeFi liquidity pools before providing liquidity. Returns a 0-100 pool score and an Enter\u002FHold\u002FExit\u002FReduce\u002FAvoid verdict with calibrated confidence for ~68,800 Solana pools and 575 EVM pools, plus a public miss-inclusive track record. Use when asked whether a pool is worth LPing into, which pools look best right now, or how accurate the scores have actually been.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fweb-data\u002Fwealthville-pool-scoring\u002FSKILL.md",[90],{"categoryNo":91,"categoryName":92,"taxonomyType":93,"taxonomyTypeDesc":94},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[96,97,98,99,100,101,102,103,104,24,105,106,107,108,109,110,111,112,113,114],"scoring","pool","wealthville pool scoring","liquidity","which","for","exit","now","use","reduce","with","record","track","verdict","evm","solana","how","public","look",{"skillNo":116,"name":117,"nameZh":6,"description":118,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":119,"categories":120,"keywords":122,"publishedAt":44},"01M70MB6VR8ERJ4EM8D5KHBMEV","technical-debt-auditor","Scans a codebase and produces a quantified technical debt report with a prioritized remediation plan. Analyzes dead code, TODO\u002FFIXME\u002FHACK markers, dependency staleness, complexity hotspots, code duplication signals, test coverage gaps, unused exports, and outdated patterns. Use this skill when the user asks to audit their codebase for tech debt, wants a health check of their code quality, says things like \"where should I focus refactoring\", \"find code smells\", \"audit my codebase\", \"what technical debt do we have\", \"prioritize cleanup work\", or asks about code quality metrics. Also trigger when the user mentions \"code rot\", \"legacy cleanup\", \"refactoring priorities\", or wants to understand the overall health of a project before a major effort. Trigger even if the user doesn't say \"technical debt\" explicitly — any request to systematically assess code quality and identify improvement priorities belongs here.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdevelopment\u002Ftechnical-debt-auditor\u002FSKILL.md",[121],{"categoryNo":91,"categoryName":92,"taxonomyType":93,"taxonomyTypeDesc":94},[123,124,125,126,127,128,129,130,131,132,133,24,134,135,136,137,138,139,140,141],"technical debt","debt","technical","technical debt auditor","auditor","coverage","complexity","markers","project","cleanup","unused","code","todo","work","plan","focus","signals","audit","dependency",{"skillNo":143,"name":144,"nameZh":6,"description":145,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":146,"categories":147,"keywords":157,"publishedAt":44},"01M70KPYH9QNHCNME5GJQGE22K","readonly-sql-guard","Make an agent's database access provably read-only. Use when an agent runs caller-supplied SQL against a production\u002FERP\u002Fanalytics database (a \"query\" MCP tool, text-to-SQL, an admin console), or when reviewing DB-access code for write\u002FDDL\u002Fside-effect\u002Ftransaction-escape risks. Checks what a statement CALLS, not just its shape.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdatabase\u002Freadonly-sql-guard\u002FSKILL.md",[148,151,152],{"categoryNo":149,"categoryName":150,"taxonomyType":93,"taxonomyTypeDesc":94},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":91,"categoryName":92,"taxonomyType":93,"taxonomyTypeDesc":94},{"categoryNo":153,"categoryName":154,"taxonomyType":155,"taxonomyTypeDesc":156},"01JBSEEDCAT000000000000033","数据分析师","PROFESSION","适用职业",[158,159,160,161,162,163,164,101,165,166,167,168,169,170,171,104,172,173,24,174],"readonly","guard","sql guard","sql","readonly sql guard","erp","effect","read-only","db","just","tool","calls","only","MCP","access","database","query",{"skillNo":176,"name":177,"nameZh":6,"description":178,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":179,"licenseFileUrl":180,"sourceHtmlUrl":181,"categories":182,"keywords":186,"publishedAt":44},"01M6AFY6F7CC2BBZP1QD6VTNVC","web-artifacts-builder","Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn\u002Fui). Use for complex artifacts requiring state management, routing, or shadcn\u002Fui components - not for simple single-file HTML\u002FJSX artifacts.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Futilities\u002Fweb-artifacts-builder\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Futilities\u002Fweb-artifacts-builder\u002FSKILL.md",[183],{"categoryNo":184,"categoryName":185,"taxonomyType":93,"taxonomyTypeDesc":94},"01JBSEEDCAT000000000000009","前端开发",[187,188,189,190,191,192,193,194,195,196,197,198,199,200,201,202,41,203,204,205,206,207,101,208],"artifacts builder","web","web artifacts builder","artifacts","builder","state","routing","state management","component","css","frontend","ui","Tools","file","components","shadcn","Tailwind","suite","jsx","html","single-file","ui components",{"skillNo":210,"name":211,"nameZh":6,"description":212,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":179,"licenseFileUrl":213,"sourceHtmlUrl":214,"categories":215,"keywords":220,"publishedAt":44},"01M6AFWF33SFV9Z3SF4PEEE4BF","webapp-testing","Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fsecurity\u002Fwebapp-testing\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fsecurity\u002Fwebapp-testing\u002FSKILL.md",[216,219],{"categoryNo":217,"categoryName":218,"taxonomyType":93,"taxonomyTypeDesc":94},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":184,"categoryName":185,"taxonomyType":93,"taxonomyTypeDesc":94},[221,222,223,224,225,188,226,197,198,227,228,229,230,101,231,106,232],"webapp testing","testing","webapp","browser","playwright","applications","debugging","toolkit","logs","screenshots","local","behavior",{"skillNo":234,"name":235,"nameZh":6,"description":236,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":179,"licenseFileUrl":237,"sourceHtmlUrl":238,"categories":239,"keywords":247,"publishedAt":44},"01M6AF67Q67JJJ5V51JR2P52KA","discernment-nudge","After you give a substantive answer or draft that the user may act on — advice or recommendations, drafted artifacts such as goals, plans, pitches, proposals, or emails, estimates or projections, analysis or interpretation of data, factual claims they may rely on, or a multi-step argument — invoke this skill BEFORE finalizing your reply and then, if it applies, append 2-3 short follow-up questions, each tied to something specific in what you just produced, that help the user check key facts, probe the reasoning or assumptions, and notice missing context. Do this at most once per conversation. Skip it when the user asked a trivial how-to or simple lookup, wants a purely educational explanation, asked you only to format, convert, or assemble a file from content they provided, is writing code they will run, is doing creative writing or casual chat, or already asked you to double-check, cite, or review — the skill file explains these boundaries and the exact output format.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fproductivity\u002Fdiscernment-nudge\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fproductivity\u002Fdiscernment-nudge\u002FSKILL.md",[240,243,244],{"categoryNo":241,"categoryName":242,"taxonomyType":93,"taxonomyTypeDesc":94},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":91,"categoryName":92,"taxonomyType":93,"taxonomyTypeDesc":94},{"categoryNo":245,"categoryName":246,"taxonomyType":155,"taxonomyTypeDesc":156},"01JBSEEDCAT000000000000036","内容创作者",[248,249,250,251,252,253,254,255,190,256,200,134,257,258,259,260,261,170,262,24,263,264,265,266,267,112,268],"discernment nudge","nudge","interpretation","help","run","reasoning","data","writing","lookup","content","review","conversation","short","up","invoke","you","analysis","claims","argument","assemble","recommendations"]