[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MJGJZF5ZJGY7NFJFEXHMR8":3,"skill-same:01M6MJGJZF5ZJGY7NFJFEXHMR8":72},{"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":23,"publishedAt":43,"linkOnly":44,"markdownContent":45,"markdownBody":46,"frontMatter":47,"refName":48,"commitSha":49,"skillDirectory":50,"forksCount":51,"repositoryHtmlUrl":52,"repositoryHomepageUrl":53,"ownerHtmlUrl":54,"ownerBlogUrl":55,"ownerDescription":56,"updatedAt":57,"install":58,"resources":71},"01M6MJGJZF5ZJGY7NFJFEXHMR8","report-bug",null,"Report a defect of reviewer or its plugin as an anonymized GitHub issue in mimfort\u002Frag_for_git, after explicit user approval. Use when a reviewer tool breaks its own contract, a skill prescribes an impossible step, a stated invariant fails, or the user asks to report a reviewer bug.","hashgraph-online\u002Fawesome-codex-plugins","hashgraph-online","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F160371962?v=4","01M6CNB6NRJVNNGN14TR01Q6D3","HOL (Hashgraph Online)","01M6JT1HSKKG9V68KQAQGBA7XP",1575,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fmimfort\u002Frag_for_git\u002Fplugin\u002Fskills\u002Freport-bug\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000034","行政与办公人员","PROFESSION","适用职业",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42],"report","report bug","bug","use","when","defect","for","as","contract","issue","github issue","github","approval","user","reviewer","tool","git","plugin","rag","2026-11-10 10:12:30",false,"---\nname: report-bug\ndescription: Report a defect of reviewer or its plugin as an anonymized GitHub issue in mimfort\u002Frag_for_git, after explicit user approval. Use when a reviewer tool breaks its own contract, a skill prescribes an impossible step, a stated invariant fails, or the user asks to report a reviewer bug.\n---\n\n# Report Bug\n\nReply in Russian. This channel reports defects **of the tool**, never problems of the user's\nproject. The server triages, anonymizes, assembles the issue and publishes it; the skill only\ncarries the conversation and the approval.\n\n**The plugin runs on commercial codebases.** Never pre-redact by hand and never paste source\ncode, paths, repo\u002Fbranch\u002Ffile names, task keys, board URLs, hosts or tokens into the arguments\nin the hope of \"cleaning them up\" — pass what you observed and let the server anonymize it. The\nsanitizer is deterministic Python; a model rewriting the text first only hides what it should\nhave removed.\n\n1. **Decide whether it is ours.** Pick `kind` from the tool contract, and pass it as observed —\n   the server, not you, decides whether the channel speaks:\n   - ours: `tool_exception`, `contract_violation`, `skill_impossible`, `skill_contradiction`,\n     `invariant_violation`, `deterministic_repro`;\n   - not ours: `environment`, `external_service`, `user_code`, `permission`, `llm_behaviour`.\n   The one exception: the model misbehaved **because a skill instruction was contradictory** →\n   still `llm_behaviour`, but set `caused_by_skill_instruction=True` (a prompt bug is our bug).\n   A `not_reported` status is a normal outcome — report nothing to the user beyond a brief note.\n2. **Pick severity.** `blocker` (no workaround), `degraded` (workaround or manual fallback\n   exists), `contract` (documentation and behaviour disagree, work continues). Offer `blocker`\n   and `degraded` immediately; the server marks `contract` with `defer=true` — collect those and\n   offer them as one batch at the end of the session.\n3. **Preview (never skip).** Call\n   ```\n   report_bug(kind=\u003Ckind>, summary=…, expected=…, actual=…, steps=[…], severity=\u003Clevel>,\n              tool=\u003Cmcp tool name>, skill_step=\u003Cskill and step>, error_class=\u003Cexception class>,\n              details=…, repo=\u003Cowner\u002Fname>, branch=\u003Cbranch>,\n              client_environment={\"orchestrator_model\": …, \"subagent_models\": …,\n                                  \"mode\": \"subagent|inline\", \"cli\": …, \"cli_version\": …},\n              scale={\"clusters\": N, \"files\": N, \"findings\": N, \"tasks\": N},\n              index_drift=\u003Cint or null>)\n   ```\n   without `confirmed`. Nothing is published. Handle the status: `disabled` — the channel is off\n   for this repo or deploy, say so and stop; `not_reported` \u002F `suppressed` — stop quietly.\n4. **Show and ask.** Show the returned `issue_text` **in full, verbatim** — no summary, no\n   abridgement — plus the target repository, the `environment_keys` list, and the\n   `identity_notice`: the issue is published from the user's GitHub account and their username\n   will be visible in a public repository; the alternative is to decline and open the issue by\n   hand from the prepared markdown. Offer to trim the Environment block: any lines, or the whole\n   block. Then ask for an explicit yes.\n5. **Publish only on an explicit yes.** Repeat the same call with `confirmed=True` and, if the\n   user trimmed anything, `environment_exclude=[…]` (or `environment_include=[…]`). In a\n   headless, cron or background run there is no human to approve: pass `non_interactive=True`,\n   which makes the server return a `fallback` markdown instead of publishing. Never publish\n   autonomously in any mode.\n   - `published` — report the issue URL.\n   - `commented` — a matching open issue existed; report that a comment was added and give both\n     URLs.\n   - `fallback` — publication was not possible (no token, no rights, no network, headless):\n     relay the reason, show the markdown and the `fallback_url` so the user can post it by hand.\n     This is not a session failure — continue the work that was interrupted.\n6. **On a refusal** call `report_bug(kind=…, summary=…, decline=True)` with the same arguments,\n   so the same symptom is not offered again in this session.\n\nEvery read is fail-open, and the `confirmed=True` call is the only write. If the channel itself\nfails, say so in one line and carry on with the original task.\n","# Report Bug\n\nReply in Russian. This channel reports defects **of the tool**, never problems of the user's\nproject. The server triages, anonymizes, assembles the issue and publishes it; the skill only\ncarries the conversation and the approval.\n\n**The plugin runs on commercial codebases.** Never pre-redact by hand and never paste source\ncode, paths, repo\u002Fbranch\u002Ffile names, task keys, board URLs, hosts or tokens into the arguments\nin the hope of \"cleaning them up\" — pass what you observed and let the server anonymize it. The\nsanitizer is deterministic Python; a model rewriting the text first only hides what it should\nhave removed.\n\n1. **Decide whether it is ours.** Pick `kind` from the tool contract, and pass it as observed —\n   the server, not you, decides whether the channel speaks:\n   - ours: `tool_exception`, `contract_violation`, `skill_impossible`, `skill_contradiction`,\n     `invariant_violation`, `deterministic_repro`;\n   - not ours: `environment`, `external_service`, `user_code`, `permission`, `llm_behaviour`.\n   The one exception: the model misbehaved **because a skill instruction was contradictory** →\n   still `llm_behaviour`, but set `caused_by_skill_instruction=True` (a prompt bug is our bug).\n   A `not_reported` status is a normal outcome — report nothing to the user beyond a brief note.\n2. **Pick severity.** `blocker` (no workaround), `degraded` (workaround or manual fallback\n   exists), `contract` (documentation and behaviour disagree, work continues). Offer `blocker`\n   and `degraded` immediately; the server marks `contract` with `defer=true` — collect those and\n   offer them as one batch at the end of the session.\n3. **Preview (never skip).** Call\n   ```\n   report_bug(kind=\u003Ckind>, summary=…, expected=…, actual=…, steps=[…], severity=\u003Clevel>,\n              tool=\u003Cmcp tool name>, skill_step=\u003Cskill and step>, error_class=\u003Cexception class>,\n              details=…, repo=\u003Cowner\u002Fname>, branch=\u003Cbranch>,\n              client_environment={\"orchestrator_model\": …, \"subagent_models\": …,\n                                  \"mode\": \"subagent|inline\", \"cli\": …, \"cli_version\": …},\n              scale={\"clusters\": N, \"files\": N, \"findings\": N, \"tasks\": N},\n              index_drift=\u003Cint or null>)\n   ```\n   without `confirmed`. Nothing is published. Handle the status: `disabled` — the channel is off\n   for this repo or deploy, say so and stop; `not_reported` \u002F `suppressed` — stop quietly.\n4. **Show and ask.** Show the returned `issue_text` **in full, verbatim** — no summary, no\n   abridgement — plus the target repository, the `environment_keys` list, and the\n   `identity_notice`: the issue is published from the user's GitHub account and their username\n   will be visible in a public repository; the alternative is to decline and open the issue by\n   hand from the prepared markdown. Offer to trim the Environment block: any lines, or the whole\n   block. Then ask for an explicit yes.\n5. **Publish only on an explicit yes.** Repeat the same call with `confirmed=True` and, if the\n   user trimmed anything, `environment_exclude=[…]` (or `environment_include=[…]`). In a\n   headless, cron or background run there is no human to approve: pass `non_interactive=True`,\n   which makes the server return a `fallback` markdown instead of publishing. Never publish\n   autonomously in any mode.\n   - `published` — report the issue URL.\n   - `commented` — a matching open issue existed; report that a comment was added and give both\n     URLs.\n   - `fallback` — publication was not possible (no token, no rights, no network, headless):\n     relay the reason, show the markdown and the `fallback_url` so the user can post it by hand.\n     This is not a session failure — continue the work that was interrupted.\n6. **On a refusal** call `report_bug(kind=…, summary=…, decline=True)` with the same arguments,\n   so the same symptom is not offered again in this session.\n\nEvery read is fail-open, and the `confirmed=True` call is the only write. If the channel itself\nfails, say so in one line and carry on with the original task.\n",{"name":5,"description":7},"main","2b63f856ce19c2a797929cacabd9e0fc936812fa","plugins\u002Fmimfort\u002Frag_for_git\u002Fplugin\u002Fskills\u002Freport-bug",491,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins","https:\u002F\u002Fhol.org\u002Fplugins\u002Fbest-codex-plugins","https:\u002F\u002Fgithub.com\u002Fhashgraph-online","https:\u002F\u002Fhol.org","Open-source standards and developer tools for interoperable AI agents: discovery, identity, communication, payments, privacy and security.","2026-11-14 14:06:13",{"source":8,"skillName":5,"commands":59,"prompt":69,"zipAvailable":70},[60,63,66],{"tool":61,"command":62},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill report-bug",{"tool":64,"command":65},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill report-bug",{"tool":67,"command":68},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill report-bug","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fmimfort\u002Frag_for_git\u002Fplugin\u002Fskills\u002Freport-bug\u002FSKILL.md",true,[],[73,83,91,99,107,115],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":77,"licenseFileUrl":78,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":82},"01M7DV332YQMGD8WTRJ9DZQXTB","worktable-review-with-annotations","Create, inspect, reply to, update, or resolve situated Worktable annotations. Use when feedback belongs to a Doc section, block, text range, or HTML Doc, or when the user asks to address existing review feedback and coordinate a requested artifact edit.","MIT","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":77,"licenseFileUrl":87,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":82},"01M7DV2YGHCZVBEB1AHYB6CGHE","worktable-find-and-synthesize-context","Find, assess, and synthesize context from Worktable Docs and Records. Use when the user asks what a workspace contains, wants workspace-backed research, needs current facts reconciled across artifacts, or requests a cited synthesis without changing workspace state.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FSKILL.md",[],[],{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":77,"licenseFileUrl":95,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":82},"01M7DV2TQN1H11ME2SAF9MXN7V","worktable-create-or-update-docs","Create, edit, rename, or maintain narrative Worktable Docs. Use for plans, decisions, briefs, notes, research syntheses, and other durable prose when the user requests a new artifact or a safe update to an existing one.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FSKILL.md",[],[],{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":77,"licenseFileUrl":103,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":82},"01M7DV2NE452NEA8TXATKSNAJH","worktable-create-or-manage-records","Organize repeated structured information as durable Worktable Records. Use for research datasets, inventories, directories, pipelines, trackers, and other collections whose items need identity, fields, filtering, links, validation, or individual updates.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FSKILL.md",[],[],{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":77,"licenseFileUrl":111,"sourceHtmlUrl":112,"categories":113,"keywords":114,"publishedAt":82},"01M7DV2HENRBR2KSCVM064WH0Y","worktable-create-or-manage-interactive-html","Create or improve durable visual and interactive artifacts in Worktable. Use for dashboards, trackers, calculators, mini apps, slide presentations, and other requests that benefit from a polished HTML Doc.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FSKILL.md",[],[],{"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":77,"licenseFileUrl":119,"sourceHtmlUrl":120,"categories":121,"keywords":122,"publishedAt":82},"01M7DV2CADR5R7RQFFYPNAGR9Y","worktable-collaborate-threads","Read, answer, and hand off messages through durable Worktable threads with users or other authenticated participants. Use when the user asks to check addressed messages, reply to a participant, continue a thread, request another agent's help, wait briefly for a response, or watch for comments and messages sent to the agent.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FSKILL.md",[],[]]