[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M74FSNSFRFWJYGN2JNAWQ3SE":3,"skill-same:01M74FSNSFRFWJYGN2JNAWQ3SE":95},{"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":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":44,"commitSha":45,"skillDirectory":46,"forksCount":47,"repositoryHtmlUrl":48,"repositoryHomepageUrl":6,"ownerHtmlUrl":49,"ownerBlogUrl":50,"ownerDescription":51,"updatedAt":52,"install":53,"resources":66},"01M74FSNSFRFWJYGN2JNAWQ3SE","issue",null,"Manages issues — create, update, search\u002Flist, and bulk — across GitHub (gh CLI), GitLab (glab CLI), Linear (MCP) or local issue files, with the active tracker and the host it talks to chosen per-repo by a committed config (.tituskirch-skills.json), self-hosted instances included. Drafts title and body from a free-text description plus session context, previews once, and creates only after confirmation; switches to plan-only when asked. Use when the user wants to create, open, update, or find an issue or ticket, mentions GitHub issues, GitLab issues or Linear, or says things like \"open an issue\", \"create a ticket\", \"find the issue about X\", \"Issue erstellen\", \"Ticket anlegen\".","TitusKirch\u002Fskills","TitusKirch","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F16943133?v=4","01M74FN1AAM5K2NH5EG292B2HZ","Titus Kirch","01M74FN1AX7TX6RAECBHE5PMNT",3,"MIT","https:\u002F\u002Fgithub.com\u002FTitusKirch\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fwork\u002Fissue\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: issue\nmetadata:\n  summary: Creates\u002Fupdates\u002Fsearches issues across GitHub (gh), GitLab (glab), Linear (MCP) or local files, tracker chosen by config.\ndescription: Manages issues — create, update, search\u002Flist, and bulk — across GitHub (gh CLI), GitLab (glab CLI), Linear (MCP) or local issue files, with the active tracker and the host it talks to chosen per-repo by a committed config (.tituskirch-skills.json), self-hosted instances included. Drafts title and body from a free-text description plus session context, previews once, and creates only after confirmation; switches to plan-only when asked. Use when the user wants to create, open, update, or find an issue or ticket, mentions GitHub issues, GitLab issues or Linear, or says things like \"open an issue\", \"create a ticket\", \"find the issue about X\", \"Issue erstellen\", \"Ticket anlegen\".\nallowed-tools:\n  - Read\n  - Grep\n  - Glob\n  - Bash(jq:*)\n  - Bash(printf:*)\n  - Bash(mkdir:*)\n  - Bash(git rev-parse:*)\n  - Bash(gh issue list:*)\n  - Bash(gh issue view:*)\n  - Bash(gh search issues:*)\n  - Bash(gh label list:*)\n  - Bash(gh project list:*)\n  - Bash(gh repo view:*)\n  - Bash(glab issue list:*)\n  - Bash(glab issue view:*)\n  - Bash(glab label list:*)\n  - Bash(glab repo view:*)\n---\n\n# issue\n\nCreate, update, and search issues without caring which tracker the repo uses. One skill, four trackers — **GitHub** (via `gh`), **GitLab** (via `glab`), **Linear** (via its MCP server) or **local files** — picked per-repo by a small committed config, which also settles **which host** a forge-native tracker talks to. The skill drafts the issue from your free-text description plus the session context, shows it once, and writes it only after you confirm — or just prints the command when you ask for a plan.\n\n**Opted out?** If the repo config sets `issue` to `false`, this skill is **disabled** for the repo — stop immediately and tell the user the issue skill is turned off in `.tituskirch-skills.json`. An _absent_ `issue` block is **not** disabled (it falls back to detection\u002Fdefaults). Check `.issue == false` on the resolved config before any action — and before indexing `.issue.tracker`. A missing `jq` or config exits non-zero too, so a pass is not evidence the config was read.\n\n## Workflow\n\n### 1. Load config & cache (guided setup on first run)\n\n- **Config** — resolve `.tituskirch-skills.json` via [`templates\u002Fresolve-config.sh`](templates\u002Fresolve-config.sh), never by reading the raw file ([REFERENCE.md](REFERENCE.md#reading-the-config) states how, missing `jq` included). The `issue.*` section holds the tracker and rules; the root `grillWith` holds the [interview engine](REFERENCE.md#which-engine--the-root-grillwith-key) — three states, so it is read by **presence**, never as a label-or-off. Resolution per setting: **config → native → built-in default**.\n- **No \u002F incomplete config, or `\u002Fissue setup`** → run the guided setup (step below). Setup is also where the catalog cache is first filled.\n- **Catalog cache** — read `$(git rev-parse --git-common-dir)\u002Ftituskirch-skills\u002Fissue` (JSON). Reuse when younger than ~3 days **and** the `tracker` is unchanged; refresh when missing, stale, the tracker changed, or the user passes `--refresh`. Label staleness in the plan header (`Catalogs (cached, 2d ago): …`).\n\nConfig\u002Fcache schema, the full setup flow and everything a run needs whatever its tracker: [REFERENCE.md](REFERENCE.md). The tracker recipes are one file each, and step 2 settles which: [`trackers\u002Fgithub.md`](trackers\u002Fgithub.md), [`trackers\u002Fgitlab.md`](trackers\u002Fgitlab.md), [`trackers\u002Flinear.md`](trackers\u002Flinear.md), [`trackers\u002Flocal.md`](trackers\u002Flocal.md).\n\n### 2. Determine the tracker\n\nFrom `issue.tracker` (`github` | `gitlab` | `linear` | `local`). A forge-native tracker also needs its **host**, resolved per repo — config, then the `origin` remote, then whatever the CLI is already authenticated against ([REFERENCE.md](REFERENCE.md#the-forge-and-its-host)); never resolve it once and reuse it across repos. Then check availability: GitHub → `gh repo view --json nameWithOwner`; GitLab → `glab repo view` against the resolved host; Linear → confirm the Linear MCP tools are present and authenticated, on the server connected to the configured workspace (`issue.linear.workspace`, [trackers\u002Flinear.md](trackers\u002Flinear.md)); `local` → the issue directory (nothing to authenticate). Unavailable\u002Funauthenticated → say so, **naming the host that was tried**, and point to the fix (`glab auth login --hostname …`, authenticate the Linear MCP); don't guess another tracker.\n\n### 3. Detect the action\n\nFrom the phrasing: **create** (default for a new description), **update** (an issue number \u002F `#N` is named, \"edit\", \"close\", \"relabel\"), or **search\u002Flist** (\"find\", \"list\", \"is there an issue about…\"). Before creating, a quick search to avoid an obvious duplicate is good practice.\n\n### 4. Draft the content\n\n**Sharpen a thin request first.** When the free-text description plus session context is **thin or ambiguous**, engage a **grilling** pass _on the skill's own initiative_ — drive the repo's interview engine to resolve the open decisions before they harden into a draft, one question at a time with a recommended answer each. A clear, complete request **skips it**; `--grill` \u002F \"grill me first\" **forces** it. **Which engine is the root `grillWith` key** — absent means `grilling`, a name means that skill, and `null` \u002F `false` means never grill and draft directly. The named engine must be one a skill may drive: **not installed** degrades to drafting as today rather than failing the run, and one declaring **`disable-model-invocation: true`** (`grill-me` and `batch-grill-me` both do) is a **config error to report**, never silently swapped for another engine. Grilling feeds the draft; it never replaces the single confirmation gate at step 6. Signals, override, the key and its three fallbacks: [REFERENCE.md](REFERENCE.md#sharpening-the-request-grilling).\n\n**The template is chosen first** — it settles part of the body _and_ part of the labels before either is drafted. Then, in order:\n\n- **Template** — `issue.template` forces one; unset, pick by the templates' own `description` (`.yml`) \u002F `about` (`.md`) text. Read on **both trackers**: the tracker decides where an issue is filed, never what shape its body has.\n- **Title** — the essence in a few words (aim ≤ ~60 chars), **not** a sentence with trailing clauses; that detail belongs in the body. A template's `title:` prefix is already decided — keep it verbatim. Style from `issue.title.convention` (default **plain**).\n- **Body** — a template is the body's **skeleton**: fill its sections, never replace them with a shape of your own. Without one, the [default structure](REFERENCE.md#default-body-structure) applies. Drafted from the description **plus the session context**, in `issue.language` (falling back to the root `language`).\n- **Labels \u002F state \u002F team** — a template's `labels:` and `assignees:` are the repo's own declaration; only **add** what they don't cover, from the **cached catalog** and contextually for this issue. Skip anything matching `issue.labels.exclude`. Linear needs a `team`.\n- **Priority** — a **native field** on Linear, a **`priority:` label** on GitHub. Neither crosses over; a tracker's own field is not a missing label.\n\nWhat each of those rests on — how a template is picked and what `blank_issues_enabled: false` binds, the title translation rule, what may never appear in a body, label resolution against the catalog, the repo-scope pin, the Linear priority mapping: [**Drafting — the full rules**](REFERENCE.md#drafting--the-full-rules).\n\n### 5. Bulk & sub-issues\n\n- \"Make X issues\" \u002F \"split this into sub-issues\" → draft **all** of them and present as **one** bundled plan.\n- Parent\u002Fchild: Linear via `parentId`; GitHub via the sub-issues API. Mechanics: [`trackers\u002Fgithub.md`](trackers\u002Fgithub.md#sub-issues).\n\n### 6. Present the plan (always, before any write)\n\nOne preview: tracker · action · template · title · body · labels\u002Fpriority\u002Fstate\u002Fteam (and the full list for bulk). Flag anything guessed or missing (no team for Linear, possible duplicate). **The chosen template is part of the preview** — path plus how it was chosen — because it is the drafting decision a human can only correct if they see it before the write. Format: [REFERENCE.md](REFERENCE.md#plan-output).\n\n### 7. Execute — or stop\n\n- **Plan-only triggers** (\"nur den Plan\", \"don't create\", \"dry run\", \"just show me\", \"nicht erstellen\") → print the exact `gh` command \u002F MCP call and **stop**.\n- **Otherwise** → confirm, then execute (create\u002Fupdate\u002Fsearch). Report the result (issue URL \u002F id). For bulk, execute in order and report each.\n\n\u003Cskills-plan>\n\n## Presenting the plan\n\nEverything this skill puts in front of a human — plan, preview, candidate list, findings report —\nis read **once, in a terminal**, and answered there. So **every section of it renders on arrival**,\nwith no interaction needed to reveal it: prose, lists, tables, fenced code.\n\n**Never fold content behind a control.** `\u003Cdetails>`\u002F`\u003Csummary>` is a browser widget, and a\nterminal has no way to open it: the summary line prints and everything under it does not. The plan\nthen arrives as headings with nothing beneath them, and the failure is silent on **both** sides —\nthe skill believes it reported, and the reader sees no marker saying anything is missing, so a\nhuman confirms a plan whose contents never reached them. What gets folded is whatever ran long,\nwhich is to say the part the decision actually rested on. The same holds for anything else needing\na click: a tab strip, an accordion, a \"show more\".\n\n**Length is handled by shortening, never by hiding.** This is a fixed rule of the skill, not a\nper-run judgement, so it holds however long the list runs. Trim to what the decision needs, group\nthe rest by something the reader already thinks in (ecosystem, kind, verdict) with a count per\ngroup, or split it across sections. What is left out is left out **visibly**: say how many, why,\nand the exact command that shows the rest.\n\n**This binds what the skill presents, not what it writes.** A `\u003Cdetails>` block inside a README, an\nissue body, a pull request description or a docs page is rendered by a browser and is entirely\nlegitimate there. The rule is about the message a human reads to decide — never about the content\nof a file.\n\n\u003C\u002Fskills-plan>\n\n## Guardrails\n\n- **Plan first, write only after confirmation.** Respect plan-only mode.\n- **Grill thin input, not clear input.** A thin or ambiguous request auto-engages a skippable grilling pass before drafting (and `--grill` forces one on any request); a complete request drafts straight through. Grilling only sharpens the draft — it never replaces the one confirmation gate. **The engine is whichever skill `grillWith` names**, `grilling` by default: a missing one degrades to today's behaviour rather than failing, one no skill may drive is **reported rather than substituted**, and `grillWith: null` \u002F `false` means the pass never runs at all.\n- **Keep titles\u002Fbodies attribution-free** — no `Generated with`\u002F🤖 line, no session\u002Fpermalink URL, no agent self-naming (Claude, Codex, Copilot, Cursor, or any future assistant). Strip it if the harness injects it.\n- **No secrets** in titles\u002Fbodies — scan the drafted content and the session context for `.env`, keys, tokens; warn and exclude.\n- **Body states intent, not implementation** — describe _what_ is wanted (outcome, context, open questions), not _how_ to build it. Never reverse-engineer the repo's conventions into build steps, and never explore the codebase to pad the body — **unless the user explicitly asks** for an implementation plan.\n- **Never file a blank issue where the repo forbids one** — `blank_issues_enabled: false` binds the skill even though the API ignores it.\n- **Never send a label or assignee the tracker can't resolve** — including one a template declares. Resolve against the catalog first, report what was skipped, and never create one to make a template fit.\n- **Cache never committed** — it lives in the git common dir.\n- **Only the requested action** — never close, reassign, or relabel anything you weren't asked to.\n- **Tracker is never silently chosen** — first run always asks (see setup).\n\n## Reference\n\nConfig\u002Fcache schema, the guided setup flow, the tracker-neutral issue-template rules, the default body structure for when none applies, the plan-output format, and worked examples — everything a run needs whatever its tracker: [REFERENCE.md](REFERENCE.md).\n\n**One file per tracker recipe, and a repo reads exactly one.** `issue.tracker` is a single value, so step 2 settles the branch before any recipe is opened: [`trackers\u002Fgithub.md`](trackers\u002Fgithub.md), [`trackers\u002Fgitlab.md`](trackers\u002Fgitlab.md), [`trackers\u002Flinear.md`](trackers\u002Flinear.md), [`trackers\u002Flocal.md`](trackers\u002Flocal.md) (sub-issue mechanics ride with the GitHub one).\n","# issue\n\nCreate, update, and search issues without caring which tracker the repo uses. One skill, four trackers — **GitHub** (via `gh`), **GitLab** (via `glab`), **Linear** (via its MCP server) or **local files** — picked per-repo by a small committed config, which also settles **which host** a forge-native tracker talks to. The skill drafts the issue from your free-text description plus the session context, shows it once, and writes it only after you confirm — or just prints the command when you ask for a plan.\n\n**Opted out?** If the repo config sets `issue` to `false`, this skill is **disabled** for the repo — stop immediately and tell the user the issue skill is turned off in `.tituskirch-skills.json`. An _absent_ `issue` block is **not** disabled (it falls back to detection\u002Fdefaults). Check `.issue == false` on the resolved config before any action — and before indexing `.issue.tracker`. A missing `jq` or config exits non-zero too, so a pass is not evidence the config was read.\n\n## Workflow\n\n### 1. Load config & cache (guided setup on first run)\n\n- **Config** — resolve `.tituskirch-skills.json` via [`templates\u002Fresolve-config.sh`](templates\u002Fresolve-config.sh), never by reading the raw file ([REFERENCE.md](REFERENCE.md#reading-the-config) states how, missing `jq` included). The `issue.*` section holds the tracker and rules; the root `grillWith` holds the [interview engine](REFERENCE.md#which-engine--the-root-grillwith-key) — three states, so it is read by **presence**, never as a label-or-off. Resolution per setting: **config → native → built-in default**.\n- **No \u002F incomplete config, or `\u002Fissue setup`** → run the guided setup (step below). Setup is also where the catalog cache is first filled.\n- **Catalog cache** — read `$(git rev-parse --git-common-dir)\u002Ftituskirch-skills\u002Fissue` (JSON). Reuse when younger than ~3 days **and** the `tracker` is unchanged; refresh when missing, stale, the tracker changed, or the user passes `--refresh`. Label staleness in the plan header (`Catalogs (cached, 2d ago): …`).\n\nConfig\u002Fcache schema, the full setup flow and everything a run needs whatever its tracker: [REFERENCE.md](REFERENCE.md). The tracker recipes are one file each, and step 2 settles which: [`trackers\u002Fgithub.md`](trackers\u002Fgithub.md), [`trackers\u002Fgitlab.md`](trackers\u002Fgitlab.md), [`trackers\u002Flinear.md`](trackers\u002Flinear.md), [`trackers\u002Flocal.md`](trackers\u002Flocal.md).\n\n### 2. Determine the tracker\n\nFrom `issue.tracker` (`github` | `gitlab` | `linear` | `local`). A forge-native tracker also needs its **host**, resolved per repo — config, then the `origin` remote, then whatever the CLI is already authenticated against ([REFERENCE.md](REFERENCE.md#the-forge-and-its-host)); never resolve it once and reuse it across repos. Then check availability: GitHub → `gh repo view --json nameWithOwner`; GitLab → `glab repo view` against the resolved host; Linear → confirm the Linear MCP tools are present and authenticated, on the server connected to the configured workspace (`issue.linear.workspace`, [trackers\u002Flinear.md](trackers\u002Flinear.md)); `local` → the issue directory (nothing to authenticate). Unavailable\u002Funauthenticated → say so, **naming the host that was tried**, and point to the fix (`glab auth login --hostname …`, authenticate the Linear MCP); don't guess another tracker.\n\n### 3. Detect the action\n\nFrom the phrasing: **create** (default for a new description), **update** (an issue number \u002F `#N` is named, \"edit\", \"close\", \"relabel\"), or **search\u002Flist** (\"find\", \"list\", \"is there an issue about…\"). Before creating, a quick search to avoid an obvious duplicate is good practice.\n\n### 4. Draft the content\n\n**Sharpen a thin request first.** When the free-text description plus session context is **thin or ambiguous**, engage a **grilling** pass _on the skill's own initiative_ — drive the repo's interview engine to resolve the open decisions before they harden into a draft, one question at a time with a recommended answer each. A clear, complete request **skips it**; `--grill` \u002F \"grill me first\" **forces** it. **Which engine is the root `grillWith` key** — absent means `grilling`, a name means that skill, and `null` \u002F `false` means never grill and draft directly. The named engine must be one a skill may drive: **not installed** degrades to drafting as today rather than failing the run, and one declaring **`disable-model-invocation: true`** (`grill-me` and `batch-grill-me` both do) is a **config error to report**, never silently swapped for another engine. Grilling feeds the draft; it never replaces the single confirmation gate at step 6. Signals, override, the key and its three fallbacks: [REFERENCE.md](REFERENCE.md#sharpening-the-request-grilling).\n\n**The template is chosen first** — it settles part of the body _and_ part of the labels before either is drafted. Then, in order:\n\n- **Template** — `issue.template` forces one; unset, pick by the templates' own `description` (`.yml`) \u002F `about` (`.md`) text. Read on **both trackers**: the tracker decides where an issue is filed, never what shape its body has.\n- **Title** — the essence in a few words (aim ≤ ~60 chars), **not** a sentence with trailing clauses; that detail belongs in the body. A template's `title:` prefix is already decided — keep it verbatim. Style from `issue.title.convention` (default **plain**).\n- **Body** — a template is the body's **skeleton**: fill its sections, never replace them with a shape of your own. Without one, the [default structure](REFERENCE.md#default-body-structure) applies. Drafted from the description **plus the session context**, in `issue.language` (falling back to the root `language`).\n- **Labels \u002F state \u002F team** — a template's `labels:` and `assignees:` are the repo's own declaration; only **add** what they don't cover, from the **cached catalog** and contextually for this issue. Skip anything matching `issue.labels.exclude`. Linear needs a `team`.\n- **Priority** — a **native field** on Linear, a **`priority:` label** on GitHub. Neither crosses over; a tracker's own field is not a missing label.\n\nWhat each of those rests on — how a template is picked and what `blank_issues_enabled: false` binds, the title translation rule, what may never appear in a body, label resolution against the catalog, the repo-scope pin, the Linear priority mapping: [**Drafting — the full rules**](REFERENCE.md#drafting--the-full-rules).\n\n### 5. Bulk & sub-issues\n\n- \"Make X issues\" \u002F \"split this into sub-issues\" → draft **all** of them and present as **one** bundled plan.\n- Parent\u002Fchild: Linear via `parentId`; GitHub via the sub-issues API. Mechanics: [`trackers\u002Fgithub.md`](trackers\u002Fgithub.md#sub-issues).\n\n### 6. Present the plan (always, before any write)\n\nOne preview: tracker · action · template · title · body · labels\u002Fpriority\u002Fstate\u002Fteam (and the full list for bulk). Flag anything guessed or missing (no team for Linear, possible duplicate). **The chosen template is part of the preview** — path plus how it was chosen — because it is the drafting decision a human can only correct if they see it before the write. Format: [REFERENCE.md](REFERENCE.md#plan-output).\n\n### 7. Execute — or stop\n\n- **Plan-only triggers** (\"nur den Plan\", \"don't create\", \"dry run\", \"just show me\", \"nicht erstellen\") → print the exact `gh` command \u002F MCP call and **stop**.\n- **Otherwise** → confirm, then execute (create\u002Fupdate\u002Fsearch). Report the result (issue URL \u002F id). For bulk, execute in order and report each.\n\n\u003Cskills-plan>\n\n## Presenting the plan\n\nEverything this skill puts in front of a human — plan, preview, candidate list, findings report —\nis read **once, in a terminal**, and answered there. So **every section of it renders on arrival**,\nwith no interaction needed to reveal it: prose, lists, tables, fenced code.\n\n**Never fold content behind a control.** `\u003Cdetails>`\u002F`\u003Csummary>` is a browser widget, and a\nterminal has no way to open it: the summary line prints and everything under it does not. The plan\nthen arrives as headings with nothing beneath them, and the failure is silent on **both** sides —\nthe skill believes it reported, and the reader sees no marker saying anything is missing, so a\nhuman confirms a plan whose contents never reached them. What gets folded is whatever ran long,\nwhich is to say the part the decision actually rested on. The same holds for anything else needing\na click: a tab strip, an accordion, a \"show more\".\n\n**Length is handled by shortening, never by hiding.** This is a fixed rule of the skill, not a\nper-run judgement, so it holds however long the list runs. Trim to what the decision needs, group\nthe rest by something the reader already thinks in (ecosystem, kind, verdict) with a count per\ngroup, or split it across sections. What is left out is left out **visibly**: say how many, why,\nand the exact command that shows the rest.\n\n**This binds what the skill presents, not what it writes.** A `\u003Cdetails>` block inside a README, an\nissue body, a pull request description or a docs page is rendered by a browser and is entirely\nlegitimate there. The rule is about the message a human reads to decide — never about the content\nof a file.\n\n\u003C\u002Fskills-plan>\n\n## Guardrails\n\n- **Plan first, write only after confirmation.** Respect plan-only mode.\n- **Grill thin input, not clear input.** A thin or ambiguous request auto-engages a skippable grilling pass before drafting (and `--grill` forces one on any request); a complete request drafts straight through. Grilling only sharpens the draft — it never replaces the one confirmation gate. **The engine is whichever skill `grillWith` names**, `grilling` by default: a missing one degrades to today's behaviour rather than failing, one no skill may drive is **reported rather than substituted**, and `grillWith: null` \u002F `false` means the pass never runs at all.\n- **Keep titles\u002Fbodies attribution-free** — no `Generated with`\u002F🤖 line, no session\u002Fpermalink URL, no agent self-naming (Claude, Codex, Copilot, Cursor, or any future assistant). Strip it if the harness injects it.\n- **No secrets** in titles\u002Fbodies — scan the drafted content and the session context for `.env`, keys, tokens; warn and exclude.\n- **Body states intent, not implementation** — describe _what_ is wanted (outcome, context, open questions), not _how_ to build it. Never reverse-engineer the repo's conventions into build steps, and never explore the codebase to pad the body — **unless the user explicitly asks** for an implementation plan.\n- **Never file a blank issue where the repo forbids one** — `blank_issues_enabled: false` binds the skill even though the API ignores it.\n- **Never send a label or assignee the tracker can't resolve** — including one a template declares. Resolve against the catalog first, report what was skipped, and never create one to make a template fit.\n- **Cache never committed** — it lives in the git common dir.\n- **Only the requested action** — never close, reassign, or relabel anything you weren't asked to.\n- **Tracker is never silently chosen** — first run always asks (see setup).\n\n## Reference\n\nConfig\u002Fcache schema, the guided setup flow, the tracker-neutral issue-template rules, the default body structure for when none applies, the plan-output format, and worked examples — everything a run needs whatever its tracker: [REFERENCE.md](REFERENCE.md).\n\n**One file per tracker recipe, and a repo reads exactly one.** `issue.tracker` is a single value, so step 2 settles the branch before any recipe is opened: [`trackers\u002Fgithub.md`](trackers\u002Fgithub.md), [`trackers\u002Fgitlab.md`](trackers\u002Fgitlab.md), [`trackers\u002Flinear.md`](trackers\u002Flinear.md), [`trackers\u002Flocal.md`](trackers\u002Flocal.md) (sub-issue mechanics ride with the GitHub one).\n",{"name":5,"metadata":24,"description":7,"allowed-tools":26},{"summary":25},"Creates\u002Fupdates\u002Fsearches issues across GitHub (gh), GitLab (glab), Linear (MCP) or local files, tracker chosen by config.",[27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"Read","Grep","Glob","Bash(jq:*)","Bash(printf:*)","Bash(mkdir:*)","Bash(git rev-parse:*)","Bash(gh issue list:*)","Bash(gh issue view:*)","Bash(gh search issues:*)","Bash(gh label list:*)","Bash(gh project list:*)","Bash(gh repo view:*)","Bash(glab issue list:*)","Bash(glab issue view:*)","Bash(glab label list:*)","Bash(glab repo view:*)","main","0343b3844cdfe00ebabe556f2a63c0515208e92c","skills\u002Fwork\u002Fissue",0,"https:\u002F\u002Fgithub.com\u002FTitusKirch\u002Fskills","https:\u002F\u002Fgithub.com\u002FTitusKirch","https:\u002F\u002Fkirch.dev\u002F","💼 Self-employed Web Developer\r\n🎓 B. Sc. Computer Science","2026-11-02 00:46:17",{"source":8,"skillName":5,"commands":54,"prompt":64,"zipAvailable":65},[55,58,61],{"tool":56,"command":57},"npx","npx skills add TitusKirch\u002Fskills --skill issue",{"tool":59,"command":60},"bunx","bunx skills add TitusKirch\u002Fskills --skill issue",{"tool":62,"command":63},"pnpm","pnpm dlx skills add TitusKirch\u002Fskills --skill issue","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FTitusKirch\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fwork\u002Fissue\u002FSKILL.md",true,[67,73,79,83,87,91],{"path":68,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":71,"sourceHtmlUrl":72},"REFERENCE.md","REFERENCE","参考文档",55088,"https:\u002F\u002Fgithub.com\u002FTitusKirch\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fwork\u002Fissue\u002FREFERENCE.md",{"path":74,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":77,"sourceHtmlUrl":78},"templates\u002Fresolve-config.sh","SCRIPT","脚本",2402,"https:\u002F\u002Fgithub.com\u002FTitusKirch\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fwork\u002Fissue\u002Ftemplates\u002Fresolve-config.sh",{"path":80,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":81,"sourceHtmlUrl":82},"trackers\u002Fgithub.md",2533,"https:\u002F\u002Fgithub.com\u002FTitusKirch\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fwork\u002Fissue\u002Ftrackers\u002Fgithub.md",{"path":84,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":85,"sourceHtmlUrl":86},"trackers\u002Fgitlab.md",3040,"https:\u002F\u002Fgithub.com\u002FTitusKirch\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fwork\u002Fissue\u002Ftrackers\u002Fgitlab.md",{"path":88,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":89,"sourceHtmlUrl":90},"trackers\u002Flinear.md",5735,"https:\u002F\u002Fgithub.com\u002FTitusKirch\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fwork\u002Fissue\u002Ftrackers\u002Flinear.md",{"path":92,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":93,"sourceHtmlUrl":94},"trackers\u002Flocal.md",4317,"https:\u002F\u002Fgithub.com\u002FTitusKirch\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fwork\u002Fissue\u002Ftrackers\u002Flocal.md",[96,103,110,117,124,131],{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"publishedAt":19},"01M74FV6SYWA6MEBCX3EY64484","gamma","The third fixture skill — carries the worklock, plan and tldr blocks, and names the resolver without hosting the config block.","https:\u002F\u002Fgithub.com\u002FTitusKirch\u002Fskills\u002Fblob\u002Fmain\u002Ftest\u002Ffixtures\u002Fregistry\u002Fskills\u002Fwork\u002Fgamma\u002FSKILL.md",[],[],{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"publishedAt":19},"01M74FV4K7PNY8GTJH2M8ZTJGT","beta","The second fixture skill — carries the tagged blocks but no config block.","https:\u002F\u002Fgithub.com\u002FTitusKirch\u002Fskills\u002Fblob\u002Fmain\u002Ftest\u002Ffixtures\u002Fregistry\u002Fskills\u002Frepo\u002Fbeta\u002FSKILL.md",[],[],{"skillNo":111,"name":112,"nameZh":6,"description":113,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":114,"categories":115,"keywords":116,"publishedAt":19},"01M74FV2JYBQ3VRP180AZEVQFC","alpha","The first fixture skill — carries the config block and the resolver.","https:\u002F\u002Fgithub.com\u002FTitusKirch\u002Fskills\u002Fblob\u002Fmain\u002Ftest\u002Ffixtures\u002Fregistry\u002Fskills\u002Frepo\u002Falpha\u002FSKILL.md",[],[],{"skillNo":118,"name":119,"nameZh":6,"description":120,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":121,"categories":122,"keywords":123,"publishedAt":19},"01M74FTVVHVDTMTP0EX4W924NK","work-review","Reviews a single tracked issue's pushed implementation across GitHub (gh), GitLab (glab), Linear (MCP) or local issue files as a fresh, independent agent — reads the issue's requirements and the pushed diff, adversarially checks whether the work is correct and complete, and writes a verdict that routes the issue to done (accepted), changes-requested (feedback, back to the implement loop), needs-human (escalation), or blocked. It never implements or fixes anything — review only. It also applies a human's verdict on a needs-human issue. Tracker, labels and the round cap come from the committed config (.tituskirch-skills.json). Use when the user wants to review, check, or sign off one specific issue's AI work, mentions an issue awaiting review, or says things like \"review issue 42\", \"check the work on issue 42\", \"reviewe Issue 42\", or gives a verdict on an escalated issue.","https:\u002F\u002Fgithub.com\u002FTitusKirch\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fwork\u002Fwork-review\u002FSKILL.md",[],[],{"skillNo":125,"name":126,"nameZh":6,"description":127,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":128,"categories":129,"keywords":130,"publishedAt":19},"01M74FTNQ1RCJTZ929GNJ2FBX5","work-review-queue","Drains a repo's queue of issues awaiting AI review across GitHub (gh), GitLab (glab), Linear (MCP) or local issue files — selects every issue in review, then reviews each with a fresh, independent agent by delegating to work-review, routing each to done, changes-requested (back to the implement loop), needs-human, or blocked. Starts by reconciling issues whose PR a human merged or closed out-of-band. Honours a per-run cap, single-flight-locked with a lock separate from the implement loop's, so review and implement drains run concurrently. Use when the user wants to review, drain, or auto-review the pushed AI work, run the review loop, says things like \"review the queue\", \"reviewe die Issues\", \"drain the review queue\", or starts a repeating driver.","https:\u002F\u002Fgithub.com\u002FTitusKirch\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fwork\u002Fwork-review-queue\u002FSKILL.md",[],[],{"skillNo":132,"name":133,"nameZh":6,"description":134,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":135,"categories":136,"keywords":137,"publishedAt":19},"01M74FTFKF2GBCKMKKHN5QJW0G","work-implement","Implements a single tracked issue across GitHub (gh), GitLab (glab), Linear (MCP) or local issue files — claims it via the lifecycle label, implements on a branch (fresh from ready, or re-work from changes-requested after review feedback), runs the repo's checks, commits and PUSHES, and hands the issue to the review loop by advancing the label to review. It never reviews its own work — the separate work-review skill does that. Tracker, label lifecycle and branch strategy come from the committed config (.tituskirch-skills.json). Use when the user wants to work, implement, action or pick up one specific issue or ticket, mentions an ai-ready issue, or says things like \"work issue 42\", \"arbeite Issue 42 ab\", \"implementiere Ticket X\", or \"address the review feedback on issue Y\".","https:\u002F\u002Fgithub.com\u002FTitusKirch\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fwork\u002Fwork-implement\u002FSKILL.md",[],[]]