[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M74KDVH470SS6WPS8WK3VSW3":3,"skill-same:01M74KDVH470SS6WPS8WK3VSW3":50},{"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":28,"commitSha":29,"skillDirectory":30,"forksCount":31,"repositoryHtmlUrl":32,"repositoryHomepageUrl":33,"ownerHtmlUrl":34,"ownerBlogUrl":6,"ownerDescription":35,"updatedAt":36,"install":37,"resources":49},"01M74KDVH470SS6WPS8WK3VSW3","triage",null,"Move issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, and write agent-ready briefs.","Acauhi99\u002Fopencode-agent-system","Acauhi99","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F109399110?v=4","01M74JTV4VH2YAER6TABE78RKF","Acauhi","01M74JTV5CXNC5DEV2XR5SBFG3",1,"MIT","https:\u002F\u002Fgithub.com\u002FAcauhi99\u002Fopencode-agent-system\u002Fblob\u002Fmain\u002Fskills\u002Ftriage\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: triage\ndescription: Move issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, and write agent-ready briefs.\nlicense: MIT\ncompatibility: opencode\nmetadata:\n  source: \"Adapted from mattpocock\u002Fskills (MIT)\"\n  disable-model-invocation: true\n---\n\n> **Tool mapping (OpenCode):** This skill uses:\n> - `question` tool for user prompts\n> - `task` tool for subagents\n> - `skill({ name: \"...\" })` to load other skills\n> - `codegraph_explore`, `codegraph_search` for codebase exploration (preferred)\n> - `grep`, `glob`, `read`, `bash` as fallback\n> - `gh` CLI for GitHub issue management\n>\n> **Context rule:** This skill supersedes any prior skill instructions. Follow ONLY these instructions now.\n\n# Triage\n\nMove issues on the project issue tracker through a small state machine of triage roles.\n\nIf this repo treats external pull requests as a request surface, triage covers them too: **a PR is an issue with attached code** — same roles, same states, same machine, with a few deltas marked \"for a PR\" below.\n\nEvery comment or issue posted to the issue tracker during triage **must** start with this disclaimer:\n\n```\n> *This was generated by AI during triage.*\n```\n\n## Roles\n\nTwo **category** roles:\n\n- `bug` — something is broken\n- `enhancement` — new feature or improvement\n\nFive **state** roles:\n\n- `needs-triage` — maintainer needs to evaluate\n- `needs-info` — waiting on reporter for more information\n- `ready-for-agent` — fully specified, ready for an AFK agent\n- `ready-for-human` — needs human implementation\n- `wontfix` — will not be actioned\n\nEvery triaged issue should carry exactly one category role and one state role. If state roles conflict, flag it and ask the maintainer before doing anything else.\n\nState transitions: an unlabeled issue normally goes to `needs-triage` first; from there it moves to `needs-info`, `ready-for-agent`, `ready-for-human`, or `wontfix`. `needs-info` returns to `needs-triage` once the reporter replies. The maintainer can override at any time — flag transitions that look unusual and ask before proceeding.\n\n## Invocation\n\nThe maintainer invokes `\u002Ftriage` and describes what they want in natural language. Interpret the request and act. Examples:\n\n- \"Show me anything that needs my attention\"\n- \"Let's look at #42\" (issue or PR)\n- \"Move #42 to ready-for-agent\"\n- \"What's ready for agents to pick up?\"\n\n## Show what needs attention\n\nQuery the issue tracker and present three buckets, oldest first:\n\n1. **Unlabeled** — never triaged.\n2. **`needs-triage`** — evaluation in progress.\n3. **`needs-info`** with reporter activity since the last triage notes — needs re-evaluation.\n\nShow counts and a one-line summary per item. Let the maintainer pick.\n\n## Triage a specific issue or PR\n\n1. **Gather context.** Read the full issue or PR (body, comments, labels, author, dates; for a PR, the diff too). Parse any prior triage notes so you don't re-ask resolved questions. Explore the codebase using the project's domain glossary, respecting ADRs in the area. Run two checks against the codebase: (a) **redundancy** — search for an existing implementation of the requested behavior by domain concept (not just the request's wording), and report where you looked. If found, it's an already-implemented `wontfix` (step 5). (b) **prior rejection** — check if this request was previously rejected.\n\n2. **Recommend.** Tell the maintainer your category and state recommendation with reasoning, plus a brief codebase summary relevant to the request — including whether it's already implemented. Wait for direction.\n\n3. **Verify the claim.** Before any grilling, check that the claim holds up. For a bug, reproduce it from the reporter's steps. For a PR, confirm the diff does what it claims — check it out, run the relevant tests or commands. Report what happened: confirmed (with code path), failed, or insufficient detail (a strong `needs-info` signal). A confirmed verification makes a much stronger agent brief.\n\n4. **Grill (if needed).** If the request needs fleshing out, invoke `skill({ name: \"grill-me\" })` — grill it into shape one question at a time, sharpening domain terms and updating `CONTEXT.md`\u002FADRs inline as decisions land.\n\n5. **Apply the outcome:**\n   - `ready-for-agent` — post an agent brief comment (concise, actionable, with acceptance criteria).\n   - `ready-for-human` — same structure as an agent brief, but note why it can't be delegated (judgment calls, external access, design decisions, manual testing).\n   - `needs-info` — post triage notes (template below).\n   - `wontfix` — close, with the comment depending on *why*:\n     - **Already implemented** — point to where it lives.\n     - **Rejected (bug)** — polite explanation, then close.\n     - **Rejected (enhancement)** — explain rationale, then close.\n   - `needs-triage` — apply the role. Optional comment if there's partial progress.\n\n## Quick state override\n\nIf the maintainer says \"move #42 to ready-for-agent\", trust them and apply the role directly. Confirm what you're about to do (role changes, comment, close), then act. Skip grilling.\n\n## Needs-info template\n\n```markdown\n## Triage Notes\n\n**What we've established so far:**\n\n- point 1\n- point 2\n\n**What we still need from you (@reporter):**\n\n- question 1\n- question 2\n```\n\nCapture everything resolved during grilling under \"established so far\" so the work isn't lost. Questions must be specific and actionable, not \"please provide more info\".\n\n## Resuming a previous session\n\nIf prior triage notes exist on the issue or PR, read them, check whether the reporter has answered any outstanding questions, and present an updated picture before continuing. Don't re-ask resolved questions.\n\n## NEVER\n\n- **NEVER triage without reading the full issue\u002FPR first**\n  **Instead:** Read body, comments, labels, and any prior triage notes before making recommendations.\n  **Why:** Surface-level triage asks already-answered questions and loses reporter trust.\n\n- **NEVER skip the redundancy check**\n  **Instead:** Search for existing implementations before recommending new work.\n  **Why:** Implementing something that already exists is the most common waste of agent time.\n\n- **NEVER post to the issue tracker without the AI disclaimer**\n  **Instead:** Start every comment with `> *This was generated by AI during triage.*`\n  **Why:** Transparency about AI-generated content builds trust with reporters.\n","> **Tool mapping (OpenCode):** This skill uses:\n> - `question` tool for user prompts\n> - `task` tool for subagents\n> - `skill({ name: \"...\" })` to load other skills\n> - `codegraph_explore`, `codegraph_search` for codebase exploration (preferred)\n> - `grep`, `glob`, `read`, `bash` as fallback\n> - `gh` CLI for GitHub issue management\n>\n> **Context rule:** This skill supersedes any prior skill instructions. Follow ONLY these instructions now.\n\n# Triage\n\nMove issues on the project issue tracker through a small state machine of triage roles.\n\nIf this repo treats external pull requests as a request surface, triage covers them too: **a PR is an issue with attached code** — same roles, same states, same machine, with a few deltas marked \"for a PR\" below.\n\nEvery comment or issue posted to the issue tracker during triage **must** start with this disclaimer:\n\n```\n> *This was generated by AI during triage.*\n```\n\n## Roles\n\nTwo **category** roles:\n\n- `bug` — something is broken\n- `enhancement` — new feature or improvement\n\nFive **state** roles:\n\n- `needs-triage` — maintainer needs to evaluate\n- `needs-info` — waiting on reporter for more information\n- `ready-for-agent` — fully specified, ready for an AFK agent\n- `ready-for-human` — needs human implementation\n- `wontfix` — will not be actioned\n\nEvery triaged issue should carry exactly one category role and one state role. If state roles conflict, flag it and ask the maintainer before doing anything else.\n\nState transitions: an unlabeled issue normally goes to `needs-triage` first; from there it moves to `needs-info`, `ready-for-agent`, `ready-for-human`, or `wontfix`. `needs-info` returns to `needs-triage` once the reporter replies. The maintainer can override at any time — flag transitions that look unusual and ask before proceeding.\n\n## Invocation\n\nThe maintainer invokes `\u002Ftriage` and describes what they want in natural language. Interpret the request and act. Examples:\n\n- \"Show me anything that needs my attention\"\n- \"Let's look at #42\" (issue or PR)\n- \"Move #42 to ready-for-agent\"\n- \"What's ready for agents to pick up?\"\n\n## Show what needs attention\n\nQuery the issue tracker and present three buckets, oldest first:\n\n1. **Unlabeled** — never triaged.\n2. **`needs-triage`** — evaluation in progress.\n3. **`needs-info`** with reporter activity since the last triage notes — needs re-evaluation.\n\nShow counts and a one-line summary per item. Let the maintainer pick.\n\n## Triage a specific issue or PR\n\n1. **Gather context.** Read the full issue or PR (body, comments, labels, author, dates; for a PR, the diff too). Parse any prior triage notes so you don't re-ask resolved questions. Explore the codebase using the project's domain glossary, respecting ADRs in the area. Run two checks against the codebase: (a) **redundancy** — search for an existing implementation of the requested behavior by domain concept (not just the request's wording), and report where you looked. If found, it's an already-implemented `wontfix` (step 5). (b) **prior rejection** — check if this request was previously rejected.\n\n2. **Recommend.** Tell the maintainer your category and state recommendation with reasoning, plus a brief codebase summary relevant to the request — including whether it's already implemented. Wait for direction.\n\n3. **Verify the claim.** Before any grilling, check that the claim holds up. For a bug, reproduce it from the reporter's steps. For a PR, confirm the diff does what it claims — check it out, run the relevant tests or commands. Report what happened: confirmed (with code path), failed, or insufficient detail (a strong `needs-info` signal). A confirmed verification makes a much stronger agent brief.\n\n4. **Grill (if needed).** If the request needs fleshing out, invoke `skill({ name: \"grill-me\" })` — grill it into shape one question at a time, sharpening domain terms and updating `CONTEXT.md`\u002FADRs inline as decisions land.\n\n5. **Apply the outcome:**\n   - `ready-for-agent` — post an agent brief comment (concise, actionable, with acceptance criteria).\n   - `ready-for-human` — same structure as an agent brief, but note why it can't be delegated (judgment calls, external access, design decisions, manual testing).\n   - `needs-info` — post triage notes (template below).\n   - `wontfix` — close, with the comment depending on *why*:\n     - **Already implemented** — point to where it lives.\n     - **Rejected (bug)** — polite explanation, then close.\n     - **Rejected (enhancement)** — explain rationale, then close.\n   - `needs-triage` — apply the role. Optional comment if there's partial progress.\n\n## Quick state override\n\nIf the maintainer says \"move #42 to ready-for-agent\", trust them and apply the role directly. Confirm what you're about to do (role changes, comment, close), then act. Skip grilling.\n\n## Needs-info template\n\n```markdown\n## Triage Notes\n\n**What we've established so far:**\n\n- point 1\n- point 2\n\n**What we still need from you (@reporter):**\n\n- question 1\n- question 2\n```\n\nCapture everything resolved during grilling under \"established so far\" so the work isn't lost. Questions must be specific and actionable, not \"please provide more info\".\n\n## Resuming a previous session\n\nIf prior triage notes exist on the issue or PR, read them, check whether the reporter has answered any outstanding questions, and present an updated picture before continuing. Don't re-ask resolved questions.\n\n## NEVER\n\n- **NEVER triage without reading the full issue\u002FPR first**\n  **Instead:** Read body, comments, labels, and any prior triage notes before making recommendations.\n  **Why:** Surface-level triage asks already-answered questions and loses reporter trust.\n\n- **NEVER skip the redundancy check**\n  **Instead:** Search for existing implementations before recommending new work.\n  **Why:** Implementing something that already exists is the most common waste of agent time.\n\n- **NEVER post to the issue tracker without the AI disclaimer**\n  **Instead:** Start every comment with `> *This was generated by AI during triage.*`\n  **Why:** Transparency about AI-generated content builds trust with reporters.\n",{"name":5,"license":15,"metadata":24,"description":7,"compatibility":27},{"source":25,"disable-model-invocation":26},"Adapted from mattpocock\u002Fskills (MIT)",true,"opencode","main","a40966cd3b7323e693a9fd665ab9c720d8bf9634","skills\u002Ftriage",0,"https:\u002F\u002Fgithub.com\u002FAcauhi99\u002Fopencode-agent-system","https:\u002F\u002Fwww.npmjs.com\u002Fpackage\u002F@acauhi\u002Fopencode-agent-system","https:\u002F\u002Fgithub.com\u002FAcauhi99","@github Backend Engineer","2026-07-07 22:24:45",{"source":8,"skillName":5,"commands":38,"prompt":48,"zipAvailable":26},[39,42,45],{"tool":40,"command":41},"npx","npx skills add Acauhi99\u002Fopencode-agent-system --skill triage",{"tool":43,"command":44},"bunx","bunx skills add Acauhi99\u002Fopencode-agent-system --skill triage",{"tool":46,"command":47},"pnpm","pnpm dlx skills add Acauhi99\u002Fopencode-agent-system --skill triage","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FAcauhi99\u002Fopencode-agent-system\u002Fblob\u002Fmain\u002Fskills\u002Ftriage\u002FSKILL.md",[],[51,57,63,69,76,82],{"skillNo":52,"name":53,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":54,"categories":55,"keywords":56,"publishedAt":19},"01M74KEHKFCSF2H23R44MR5DN8","write-tests","https:\u002F\u002Fgithub.com\u002FAcauhi99\u002Fopencode-agent-system\u002Fblob\u002Fmain\u002Fskills\u002Fwrite-tests\u002FSKILL.md",[],[],{"skillNo":58,"name":59,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":19},"01M74KEEXZW2185BZ3VJCM7AF6","update-changelog","https:\u002F\u002Fgithub.com\u002FAcauhi99\u002Fopencode-agent-system\u002Fblob\u002Fmain\u002Fskills\u002Fupdate-changelog\u002FSKILL.md",[],[],{"skillNo":64,"name":65,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":19},"01M74KDKGNY0MQXQ0ZHAGYSJJ4","to-prd","https:\u002F\u002Fgithub.com\u002FAcauhi99\u002Fopencode-agent-system\u002Fblob\u002Fmain\u002Fskills\u002Fto-prd\u002FSKILL.md",[],[],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":19},"01M74KD9YN0K59GWMWDT5YHBKY","to-issues","Break a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bullet vertical slices.","https:\u002F\u002Fgithub.com\u002FAcauhi99\u002Fopencode-agent-system\u002Fblob\u002Fmain\u002Fskills\u002Fto-issues\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":19},"01M74KD14VJAJZ8E4ENN0KP9GV","testing-plan","https:\u002F\u002Fgithub.com\u002FAcauhi99\u002Fopencode-agent-system\u002Fblob\u002Fmain\u002Fskills\u002Ftesting-plan\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":19},"01M74KCJJ99RTMHTEPA9A5MWKN","tdd","Test-driven development with red-green-refactor loop. Use when the user wants to build features or fix bugs test-first, mentions \"red-green-refactor\", or wants integration tests. Builds features one vertical slice at a time.","https:\u002F\u002Fgithub.com\u002FAcauhi99\u002Fopencode-agent-system\u002Fblob\u002Fmain\u002Fskills\u002Ftdd\u002FSKILL.md",[],[]]