[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78F64BJSAH43EDC5CMXKZCV":3,"skill-same:01M78F64BJSAH43EDC5CMXKZCV":79},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":23,"commitSha":24,"skillDirectory":25,"forksCount":26,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":29,"install":30,"resources":43},"01M78F64BJSAH43EDC5CMXKZCV","copilot-finding-triage",null,"Tiers each Copilot gate finding from a converge run, verifies each code concern with an executed check, then routes it — auto-fix a self-healing finding, resolve a refuted one, page the user only for an inconclusive one. Triggers: 'copilot finding triage', 'user review gate', 'tier copilot findings', 'triage the copilot gate'.","jl-cmd-projects\u002Fclaude-dev-env","jl-cmd-projects","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F338158757?v=4","01M78F4M55P4QY5YPN27XBQA9N","01M78F4M65AGEYC88NV6PW4715",7,"MIT","https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fpackages\u002Fclaude-dev-env\u002F.agents\u002Fskills-archived\u002Fcopilot-finding-triage\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: copilot-finding-triage\ndescription: >-\n  Tiers each Copilot gate finding from a converge run, verifies each code concern\n  with an executed check, then routes it — auto-fix a self-healing finding,\n  resolve a refuted one, page the user only for an inconclusive one. Triggers:\n  'copilot finding triage', 'user review gate', 'tier copilot findings', 'triage\n  the copilot gate'.\n---\n\n# Copilot Finding Triage\n\nAfter a converge run's Copilot gate returns its findings, this skill tiers each\none, verifies every code concern with an executed check, then acts on it.\nFindings scoped to style, type hints, or tests heal themselves inside the run. A\nlogic, security, or behavior finding goes to a verifier that runs a check against\nHEAD: a confirmed defect joins the fix round carrying its repro, a refuted claim\nis answered on the thread with the check evidence, and only a finding the check\nleaves inconclusive pages the user and holds the run until they answer or a\n45-minute deadline passes.\n\n## When this applies\n\nReach for this skill when a Copilot review on the round's HEAD returns findings\ninside one of these callers:\n\n- `autoconverge` — the single-run converge workflow, at its Copilot wait-gate.\n- `pr-converge` — the looping converge workflow, at each Copilot tick.\n\nEach caller already fetches the review and carries a fix-and-push flow. This\nskill decides, per finding, whether that flow runs on its own or waits behind\nthe user gate.\n\n## The tier split\n\nRead the complete rubric in `reference\u002Ftier-rubric.md`. The short form:\n\n- **SELF-HEALING** — the fix cannot change what a production caller sees at\n  runtime. Style, type hints, misplaced or unused imports, magic-value\n  extraction, reshapes limited to tests, doc-versus-code mismatches, and\n  de-duplication.\n- **CODE CONCERN** — the fix changes observable production behavior or needs a\n  product decision. Logic or correctness defects, security, data handling,\n  error-handling semantics, and concurrency.\n\nA finding that straddles both tiers sorts to CODE CONCERN. Any doubt about the\ntier sorts the finding to CODE CONCERN.\n\n## The verification stage\n\nTiering names who might act; the verification stage between tiering and the user\ngate settles it for every code concern. Each code-concern finding goes to its own\nverifier agent, all in parallel, inside the run. The verifier runs a check\nagainst the flagged HEAD and returns one of three verdicts.\n\n**The governing rule: a verdict is conclusive only if an actual check was\nexecuted.** Reading the source and reasoning about it, however sound, never\nproduces a conclusive verdict. A check is a concrete command the verifier runs\nagainst the flagged HEAD — executing the code path with crafted inputs, forcing\nthe claimed error condition, or running a purpose-built test — whose captured\noutput demonstrates the behavior in question. Each verdict carries\n`{verdict, checkCommand, checkOutput, evidence}`; a conclusive verdict whose\n`checkCommand` or `checkOutput` is empty carries no executed check, so the run\ndowngrades it to inconclusive.\n\n- **CONFIRMED** — the check reproduces the defect. The finding becomes\n  self-healing: it joins the fix round carrying its repro. The fix re-runs the\n  same repro check and shows it passes, adds the repro to the test suite as a\n  regression test where the suite covers that surface, lands in one commit and\n  pushes, replies to the thread with the fix SHA plus the before\u002Fafter check\n  output, and resolves the thread. No page.\n- **REFUTED** — the check shows the code already behaves correctly in the exact\n  scenario the finding claims is broken. The run replies to the thread with the\n  command(s) and captured output, resolves the thread, and counts the finding\n  clean. No page.\n- **INCONCLUSIVE** — everything else: no runnable check exists, the check is\n  infeasible in this environment, the results are ambiguous, or the fix needs a\n  product decision between defensible behaviors. The verifier defaults to\n  inconclusive, and any doubt sorts here. These findings, and only these, flow\n  into the user gate.\n\nA run with zero inconclusive findings never reaches the user gate.\n\n## Self-healing flow\n\nA self-healing finding never pages the user. This covers a finding tiered\nself-healing and a code concern the verifier confirmed.\n\n1. Fix the finding through the caller's existing fix flow.\n2. Verify the fix.\n3. Commit and push on the caller's branch.\n4. Count the round toward convergence.\n\n## User gate protocol\n\nRun this protocol when one or more code-concern findings stayed inconclusive\nafter verification on the round's HEAD.\n\n### Step 1 — Page the user\n\nRun `scripts\u002Fnotify_ntfy.py` with:\n\n- `--title` naming the PR.\n- `--message` summarizing each inconclusive finding, one line each, as\n  `file:line — severity — one sentence`, followed by the verifier's one-line\n  evidence note stating what check was attempted and why it was not decisive.\n  Build the body from `templates\u002Fnotification.md`.\n- `--click-url` set to the Copilot review URL, so tapping the page opens the\n  review.\n\nThe topic reads from the `NTFY_TOPIC` environment variable, and the server\nreads from `NTFY_SERVER` with a default of `https:\u002F\u002Fntfy.sh`. A missing topic\nfails loudly with a clear message. A failed page holds the gate open; it never\ncounts as approval.\n\n### Step 2 — Hold and wait\n\nBranch the hold on the caller's pacer (or on whether a durable wake surface is\npresent when the caller has not selected a pacer):\n\n- **Native pacer** (`pacer=schedule_wakeup`, `pacer=workflow`, or\n  `ScheduleWakeup` present): arm `ScheduleWakeup` for a 45-minute deadline.\n  Where `ScheduleWakeup` is absent on that native path, use `send_later`.\n- **Portable pacer** (`pacer=portable`, or no durable wake): do not call\n  `ScheduleWakeup` or `send_later`. Hold with an in-session deadline poll, or\n  write handoff and stop, per\n  [`..\u002F..\u002Fskills\u002F_shared\u002Fpr-loop\u002Fportable-driver.md`](..\u002F..\u002Fskills\u002F_shared\u002Fpr-loop\u002Fportable-driver.md).\n  Callers may override this step after the ntfy page and apply their own\n  portable hold.\n\nThe clock starts when the page reaches the user, which is the moment the script\nexits zero.\n\n- If the user answers, follow their direction.\n- If the deadline passes with no answer, run the caller's normal teardown and\n  report the un-reviewed findings in the final report.\n\n### Step 3 — Self-healing and confirmed findings run in parallel\n\nSelf-healing findings and confirmed code concerns on the same HEAD do not wait\nfor the gate. Fix, verify, commit, and push them through the caller's fix flow,\nand count the round toward convergence. A confirmed finding carries its repro, so\nits fix re-runs that same check and posts the before\u002Fafter output on the thread.\n\n## Gate checklist\n\n- [ ] Every finding on HEAD carries a tier.\n- [ ] Each self-healing finding is fixed, verified, and pushed.\n- [ ] Each code-concern finding carries a verifier verdict from an executed check.\n- [ ] Each confirmed finding is fixed with its repro re-run and pushed.\n- [ ] Each refuted finding's thread carries the check evidence and is resolved.\n- [ ] Each inconclusive finding appears as one line in the ntfy body with its\n      evidence note.\n- [ ] The page carries the PR name, the per-finding summary, and the review URL.\n- [ ] `scripts\u002Fnotify_ntfy.py` exited zero before the 45-minute clock started.\n- [ ] The hold is armed from a delivered page (45-minute `ScheduleWakeup` \u002F `send_later` on native pacer; portable in-session poll or handoff on `pacer=portable`).\n- [ ] A failed page kept the gate open rather than approving the round.\n\n## Files\n\n| Path | Role |\n|------|------|\n| `SKILL.md` | This hub: when it applies, the tier split, the verification stage, the gate protocol. |\n| `reference\u002Ftier-rubric.md` | The complete tier rubric, the three verdicts, and the executed-check standard. |\n| `templates\u002Fnotification.md` | The ntfy message body for an inconclusive-finding page. |\n| `scripts\u002Fnotify_ntfy.py` | The ntfy publish CLI. |\n| `scripts\u002Ftest_notify_ntfy.py` | Tests for the publish CLI. |\n\n## Gotchas\n\n- **A cloud MCP session refuses APPROVE reviews.** Any review this protocol posts\n  is event COMMENT. A cloud session cannot post an APPROVE event, so route\n  approvals through the user, never through a posted review.\n- **A failed page is not consent.** A failed ntfy POST holds the gate open. It\n  does not auto-approve the round. Read the script's non-zero exit as a page that\n  never reached the user, and keep the run held.\n- **A conclusive verdict needs an executed check.** Source reading, however\n  sound, never confirms or refutes a finding. A confirmed or refuted verdict\n  whose `checkCommand` or `checkOutput` is empty downgrades to inconclusive and\n  pages the user.\n- **Doubt sorts to INCONCLUSIVE.** When an executed check does not pin down the\n  behavior, the verifier defaults to inconclusive and the finding pages the user.\n  The safe default never auto-fixes a finding whose behavior a check did not show.\n- **The 45-minute clock starts at page success.** The timer starts when the page\n  reaches the user, which is the moment `scripts\u002Fnotify_ntfy.py` exits zero, not\n  the moment the finding is classified.\n","# Copilot Finding Triage\n\nAfter a converge run's Copilot gate returns its findings, this skill tiers each\none, verifies every code concern with an executed check, then acts on it.\nFindings scoped to style, type hints, or tests heal themselves inside the run. A\nlogic, security, or behavior finding goes to a verifier that runs a check against\nHEAD: a confirmed defect joins the fix round carrying its repro, a refuted claim\nis answered on the thread with the check evidence, and only a finding the check\nleaves inconclusive pages the user and holds the run until they answer or a\n45-minute deadline passes.\n\n## When this applies\n\nReach for this skill when a Copilot review on the round's HEAD returns findings\ninside one of these callers:\n\n- `autoconverge` — the single-run converge workflow, at its Copilot wait-gate.\n- `pr-converge` — the looping converge workflow, at each Copilot tick.\n\nEach caller already fetches the review and carries a fix-and-push flow. This\nskill decides, per finding, whether that flow runs on its own or waits behind\nthe user gate.\n\n## The tier split\n\nRead the complete rubric in `reference\u002Ftier-rubric.md`. The short form:\n\n- **SELF-HEALING** — the fix cannot change what a production caller sees at\n  runtime. Style, type hints, misplaced or unused imports, magic-value\n  extraction, reshapes limited to tests, doc-versus-code mismatches, and\n  de-duplication.\n- **CODE CONCERN** — the fix changes observable production behavior or needs a\n  product decision. Logic or correctness defects, security, data handling,\n  error-handling semantics, and concurrency.\n\nA finding that straddles both tiers sorts to CODE CONCERN. Any doubt about the\ntier sorts the finding to CODE CONCERN.\n\n## The verification stage\n\nTiering names who might act; the verification stage between tiering and the user\ngate settles it for every code concern. Each code-concern finding goes to its own\nverifier agent, all in parallel, inside the run. The verifier runs a check\nagainst the flagged HEAD and returns one of three verdicts.\n\n**The governing rule: a verdict is conclusive only if an actual check was\nexecuted.** Reading the source and reasoning about it, however sound, never\nproduces a conclusive verdict. A check is a concrete command the verifier runs\nagainst the flagged HEAD — executing the code path with crafted inputs, forcing\nthe claimed error condition, or running a purpose-built test — whose captured\noutput demonstrates the behavior in question. Each verdict carries\n`{verdict, checkCommand, checkOutput, evidence}`; a conclusive verdict whose\n`checkCommand` or `checkOutput` is empty carries no executed check, so the run\ndowngrades it to inconclusive.\n\n- **CONFIRMED** — the check reproduces the defect. The finding becomes\n  self-healing: it joins the fix round carrying its repro. The fix re-runs the\n  same repro check and shows it passes, adds the repro to the test suite as a\n  regression test where the suite covers that surface, lands in one commit and\n  pushes, replies to the thread with the fix SHA plus the before\u002Fafter check\n  output, and resolves the thread. No page.\n- **REFUTED** — the check shows the code already behaves correctly in the exact\n  scenario the finding claims is broken. The run replies to the thread with the\n  command(s) and captured output, resolves the thread, and counts the finding\n  clean. No page.\n- **INCONCLUSIVE** — everything else: no runnable check exists, the check is\n  infeasible in this environment, the results are ambiguous, or the fix needs a\n  product decision between defensible behaviors. The verifier defaults to\n  inconclusive, and any doubt sorts here. These findings, and only these, flow\n  into the user gate.\n\nA run with zero inconclusive findings never reaches the user gate.\n\n## Self-healing flow\n\nA self-healing finding never pages the user. This covers a finding tiered\nself-healing and a code concern the verifier confirmed.\n\n1. Fix the finding through the caller's existing fix flow.\n2. Verify the fix.\n3. Commit and push on the caller's branch.\n4. Count the round toward convergence.\n\n## User gate protocol\n\nRun this protocol when one or more code-concern findings stayed inconclusive\nafter verification on the round's HEAD.\n\n### Step 1 — Page the user\n\nRun `scripts\u002Fnotify_ntfy.py` with:\n\n- `--title` naming the PR.\n- `--message` summarizing each inconclusive finding, one line each, as\n  `file:line — severity — one sentence`, followed by the verifier's one-line\n  evidence note stating what check was attempted and why it was not decisive.\n  Build the body from `templates\u002Fnotification.md`.\n- `--click-url` set to the Copilot review URL, so tapping the page opens the\n  review.\n\nThe topic reads from the `NTFY_TOPIC` environment variable, and the server\nreads from `NTFY_SERVER` with a default of `https:\u002F\u002Fntfy.sh`. A missing topic\nfails loudly with a clear message. A failed page holds the gate open; it never\ncounts as approval.\n\n### Step 2 — Hold and wait\n\nBranch the hold on the caller's pacer (or on whether a durable wake surface is\npresent when the caller has not selected a pacer):\n\n- **Native pacer** (`pacer=schedule_wakeup`, `pacer=workflow`, or\n  `ScheduleWakeup` present): arm `ScheduleWakeup` for a 45-minute deadline.\n  Where `ScheduleWakeup` is absent on that native path, use `send_later`.\n- **Portable pacer** (`pacer=portable`, or no durable wake): do not call\n  `ScheduleWakeup` or `send_later`. Hold with an in-session deadline poll, or\n  write handoff and stop, per\n  [`..\u002F..\u002Fskills\u002F_shared\u002Fpr-loop\u002Fportable-driver.md`](..\u002F..\u002Fskills\u002F_shared\u002Fpr-loop\u002Fportable-driver.md).\n  Callers may override this step after the ntfy page and apply their own\n  portable hold.\n\nThe clock starts when the page reaches the user, which is the moment the script\nexits zero.\n\n- If the user answers, follow their direction.\n- If the deadline passes with no answer, run the caller's normal teardown and\n  report the un-reviewed findings in the final report.\n\n### Step 3 — Self-healing and confirmed findings run in parallel\n\nSelf-healing findings and confirmed code concerns on the same HEAD do not wait\nfor the gate. Fix, verify, commit, and push them through the caller's fix flow,\nand count the round toward convergence. A confirmed finding carries its repro, so\nits fix re-runs that same check and posts the before\u002Fafter output on the thread.\n\n## Gate checklist\n\n- [ ] Every finding on HEAD carries a tier.\n- [ ] Each self-healing finding is fixed, verified, and pushed.\n- [ ] Each code-concern finding carries a verifier verdict from an executed check.\n- [ ] Each confirmed finding is fixed with its repro re-run and pushed.\n- [ ] Each refuted finding's thread carries the check evidence and is resolved.\n- [ ] Each inconclusive finding appears as one line in the ntfy body with its\n      evidence note.\n- [ ] The page carries the PR name, the per-finding summary, and the review URL.\n- [ ] `scripts\u002Fnotify_ntfy.py` exited zero before the 45-minute clock started.\n- [ ] The hold is armed from a delivered page (45-minute `ScheduleWakeup` \u002F `send_later` on native pacer; portable in-session poll or handoff on `pacer=portable`).\n- [ ] A failed page kept the gate open rather than approving the round.\n\n## Files\n\n| Path | Role |\n|------|------|\n| `SKILL.md` | This hub: when it applies, the tier split, the verification stage, the gate protocol. |\n| `reference\u002Ftier-rubric.md` | The complete tier rubric, the three verdicts, and the executed-check standard. |\n| `templates\u002Fnotification.md` | The ntfy message body for an inconclusive-finding page. |\n| `scripts\u002Fnotify_ntfy.py` | The ntfy publish CLI. |\n| `scripts\u002Ftest_notify_ntfy.py` | Tests for the publish CLI. |\n\n## Gotchas\n\n- **A cloud MCP session refuses APPROVE reviews.** Any review this protocol posts\n  is event COMMENT. A cloud session cannot post an APPROVE event, so route\n  approvals through the user, never through a posted review.\n- **A failed page is not consent.** A failed ntfy POST holds the gate open. It\n  does not auto-approve the round. Read the script's non-zero exit as a page that\n  never reached the user, and keep the run held.\n- **A conclusive verdict needs an executed check.** Source reading, however\n  sound, never confirms or refutes a finding. A confirmed or refuted verdict\n  whose `checkCommand` or `checkOutput` is empty downgrades to inconclusive and\n  pages the user.\n- **Doubt sorts to INCONCLUSIVE.** When an executed check does not pin down the\n  behavior, the verifier defaults to inconclusive and the finding pages the user.\n  The safe default never auto-fixes a finding whose behavior a check did not show.\n- **The 45-minute clock starts at page success.** The timer starts when the page\n  reaches the user, which is the moment `scripts\u002Fnotify_ntfy.py` exits zero, not\n  the moment the finding is classified.\n",{"name":5,"description":7},"main","974284b42eeb4609e94d4ebc1f6e36df400d54ca","packages\u002Fclaude-dev-env\u002F.agents\u002Fskills-archived\u002Fcopilot-finding-triage",1,"https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env","https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects","2026-11-15 05:02:47",{"source":8,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add jl-cmd-projects\u002Fclaude-dev-env --skill copilot-finding-triage",{"tool":36,"command":37},"bunx","bunx skills add jl-cmd-projects\u002Fclaude-dev-env --skill copilot-finding-triage",{"tool":39,"command":40},"pnpm","pnpm dlx skills add jl-cmd-projects\u002Fclaude-dev-env --skill copilot-finding-triage","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fpackages\u002Fclaude-dev-env\u002F.agents\u002Fskills-archived\u002Fcopilot-finding-triage\u002FSKILL.md",true,[44,50,56,60,63,67,71,75],{"path":45,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":48,"sourceHtmlUrl":49},"reference\u002Ftier-rubric.md","REFERENCE","参考文档",4794,"https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fpackages\u002Fclaude-dev-env\u002F.agents\u002Fskills-archived\u002Fcopilot-finding-triage\u002Freference\u002Ftier-rubric.md",{"path":51,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":54,"sourceHtmlUrl":55},"scripts\u002Fconftest.py","SCRIPT","脚本",255,"https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fpackages\u002Fclaude-dev-env\u002F.agents\u002Fskills-archived\u002Fcopilot-finding-triage\u002Fscripts\u002Fconftest.py",{"path":57,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":58,"sourceHtmlUrl":59},"scripts\u002Fcopilot_finding_triage_constants\u002F__init__.py",0,"https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fpackages\u002Fclaude-dev-env\u002F.agents\u002Fskills-archived\u002Fcopilot-finding-triage\u002Fscripts\u002Fcopilot_finding_triage_constants\u002F__init__.py",{"path":61,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":58,"sourceHtmlUrl":62},"scripts\u002Fcopilot_finding_triage_constants\u002Fconfig\u002F__init__.py","https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fpackages\u002Fclaude-dev-env\u002F.agents\u002Fskills-archived\u002Fcopilot-finding-triage\u002Fscripts\u002Fcopilot_finding_triage_constants\u002Fconfig\u002F__init__.py",{"path":64,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":65,"sourceHtmlUrl":66},"scripts\u002Fcopilot_finding_triage_constants\u002Fconfig\u002Fnotify_ntfy_constants.py",981,"https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fpackages\u002Fclaude-dev-env\u002F.agents\u002Fskills-archived\u002Fcopilot-finding-triage\u002Fscripts\u002Fcopilot_finding_triage_constants\u002Fconfig\u002Fnotify_ntfy_constants.py",{"path":68,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":69,"sourceHtmlUrl":70},"scripts\u002Fnotify_ntfy.py",6413,"https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fpackages\u002Fclaude-dev-env\u002F.agents\u002Fskills-archived\u002Fcopilot-finding-triage\u002Fscripts\u002Fnotify_ntfy.py",{"path":72,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":73,"sourceHtmlUrl":74},"scripts\u002Ftest_notify_ntfy.py",4960,"https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fpackages\u002Fclaude-dev-env\u002F.agents\u002Fskills-archived\u002Fcopilot-finding-triage\u002Fscripts\u002Ftest_notify_ntfy.py",{"path":76,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":77,"sourceHtmlUrl":78},"templates\u002Fnotification.md",1405,"https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fpackages\u002Fclaude-dev-env\u002F.agents\u002Fskills-archived\u002Fcopilot-finding-triage\u002Ftemplates\u002Fnotification.md",[80,87,94,101,108,115],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":18},"01M78FER7S09AE87MMJFT1E87E","update","Fast-forwards a local repository's main branch to a remote's main after confirming the repo path and source remote through AskUserQuestion. Use when the user says '\u002Fupdate', 'update main', 'fast-forward main', 'sync main from origin', 'pull latest main into \u003Cpath>', or 'bring main up to date'.","https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fskill-archive\u002Fupdate\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":18},"01M78FENWZS01MB4PMGX6801X6","source-command-sr-loop","Converging cleanup loop: repeat \u002Fsimplify until clean, then repeat \u002Fcode-review --fix until clean","https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fskill-archive\u002Fsource-command-sr-loop\u002FSKILL.md",[],[],{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":18},"01M78FEGZ7JDWEG3RM78M9Y8F8","skill-builder","Skill lifecycle: classify, scaffold, write via the skill-writer-agent, self-audit, compose sub-skills, polish description triggers, enforce deterministic scripts. Triggers: build a skill, new skill workflow, improve this skill, optimize skill description, skill development lifecycle, skill modularity, skill composition, description trigger catalog, deterministic skill scripts.","https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fskill-archive\u002Fskill-builder\u002FSKILL.md",[],[],{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":107,"publishedAt":18},"01M78FEDEYHJYKTER9S566DMEZ","session-tidy","Audit, clean, and consolidate session logs in the Obsidian vault. Fixes format drift, resolves orphaned next-steps, updates stale statuses, and generates project rollup summaries. Use when session logs feel cluttered or before starting a new project milestone. Triggers on '\u002Fsession-tidy', 'tidy sessions', 'clean up session logs', 'session audit'.","https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fskill-archive\u002Fsession-tidy\u002FSKILL.md",[],[],{"skillNo":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":112,"categories":113,"keywords":114,"publishedAt":18},"01M78FE8QR789SKBF3A78N2T13","session-log","Logs a session report as an HTML page, tracks vault context, extracts decisions, and outputs a \u002Frename command. Use for \u002Fsession-log, 'journal this session', 'log this work', 'session report', 'summarize\u002Flog\u002Frecord this session', 'save session', 'capture session', or 'document what we did'.","https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fskill-archive\u002Fsession-log\u002FSKILL.md",[],[],{"skillNo":116,"name":117,"nameZh":6,"description":118,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":119,"categories":120,"keywords":121,"publishedAt":18},"01M78FE4JDJHKTJPWRWNQEX2HT","run-claude-dev-env","Build, install, run, and test the claude-dev-env installer. Use when asked to run claude-dev-env, install the Claude Code config into ~\u002F.claude, drive the installer, smoke-test it against a sandbox, or run its test suite.","https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fskill-archive\u002Frun-claude-dev-env\u002FSKILL.md",[],[]]