[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EF4S67EX2XKMZC2ZHMRF3R":3,"skill-same:01M7EF4S67EX2XKMZC2ZHMRF3R":45},{"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":24,"commitSha":25,"skillDirectory":26,"forksCount":14,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":29,"ownerDescription":6,"updatedAt":30,"install":31,"resources":44},"01M7EF4S67EX2XKMZC2ZHMRF3R","address-gh-review",null,"Use when a reviewer left comments on a GitHub PR of this repository and they need working through (\"I added comments\", \"address the review\", \"обработай комменты\", \"ответь на ревью\").","pharosone\u002Fdev-harness","pharosone","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F286743270?v=4","01M7EF4QCYY7VXGV0CCKEBZT74","PharosOne","01M7EF4QE6P8EG9QQ5B6CA8KWW",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fpharosone\u002Fdev-harness\u002Fblob\u002Fmain\u002Fskills\u002Faddress-gh-review\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: address-gh-review\ndescription: \"Use when a reviewer left comments on a GitHub PR of this repository and they need working through (\\\"I added comments\\\", \\\"address the review\\\", \\\"обработай комменты\\\", \\\"ответь на ревью\\\").\"\n---\n\nRead `harness\u002Fcore\u002FREADME.md`, the active runtime adapter and, when present,\n`harness\u002Fproject\u002Fskills\u002Faddress-gh-review.md` (this skill's project specifics) before following\nthis procedure. `harness\u002Fproject` in this skill means the overlay in use: `$HARNESS_PROJECT` when set; `python3 harness\u002Fcore\u002Fscripts\u002Fproject.py overlay` prints it. Resolve task artifacts with `python3 harness\u002Fcore\u002Fscripts\u002Ftask_state.py locate\n\u003Ctask>`; use the returned absolute directory, including for an existing legacy run. `\u003Crun-dir>`\nbelow means that resolved directory. Reuse existing user authorization; publish comments or\nreviews only when the user explicitly requested it or explicitly invoked a skill authorizing\nthat action.\n\n**Dispatch authority:** resolve every orchestrator\u002Fworker model and effort from\n`harness\u002Fcore\u002Fadapters\u002Fmodels.json` deep-merged with the active\n`harness\u002Fproject\u002Fmodels.json` (or `$HARNESS_PROJECT\u002Fmodels.json`). Record profile, model\nand effort. Never select from personal memory or saved preferences; router shadow is\nadvisory and cannot replace the actual static profile choice. Lane progress goes to\n`\u003Creport>.progress.md`; write final `\u003Creport>` only at the end. Requests use\n`\u003Crun>\u002Flanes\u002F\u003Cwork>.flag.md` or `tripwire.py flag`; never type into another pane.\n\n# Address a GitHub PR review\n\nThe unit of work is the whole review round, not one comment: one push and one reply per thread,\nafter the full pipeline is green again. A reply pointing at a half-tested push is worse than no\nreply. Cap: one round per invocation; stop and report after it.\n\n## Efficient testing authority\n\nApply `harness\u002Fcore\u002Frules\u002Fefficient-testing.md` to this workflow's tests and recommendations.\nChoose in-process fakes first, then one shared long-lived test service with owned logical\nisolation, then per-run services, then per-test containers only for a written correctness\nreason. Reuse expensive setup with complete content-hash keys. Keep build\u002Fresult\u002Fdependency\u002F\nimage caches enabled; bypass only a named test\u002Fstep for an input that its cache cannot see.\nRun affected cases\u002Fpackages first locally; the full suite remains required in CI\u002Fpre-PR.\nHeavy gates\u002Fevals\u002Freviews use `harness\u002Fcore\u002Fscripts\u002Fload_guard.py` for adaptive load\u002Fmemory\nadmission, never fixed slots; targeted runs\nand nested admitted work do not wait. Infrastructure changes name the isolation boundary,\ncleanup and measured cold\u002Fwarm wall\u002Fresource cost. Never replace required real paired model\nmeasurements or real-service boundary coverage with a fake.\n\n## 1. Collect\n\n`gh pr view --comments` misses inline threads. Read all three sources (`gh api` fills in\n`{owner}\u002F{repo}` from the current checkout):\n\n```bash\ngh api repos\u002F{owner}\u002F{repo}\u002Fpulls\u002F\u003Cn>\u002Fcomments --paginate \\\n  --jq '.[] | {id, user: .user.login, path, line, original_commit_id, in_reply_to_id, body}'\ngh api repos\u002F{owner}\u002F{repo}\u002Fpulls\u002F\u003Cn>\u002Freviews --jq '.[] | {id, user: .user.login, state, body}'\ngh api repos\u002F{owner}\u002F{repo}\u002Fissues\u002F\u003Cn>\u002Fcomments --jq '.[] | {id, user: .user.login, body}'\n```\n\nA thread root has `in_reply_to_id: null`; skip threads that already carry the author's reply.\n`line` refers to `original_commit_id`: read `git show \u003Coriginal_commit_id>:\u003Cpath>` before mapping\nit to the current head.\n\n## 2. Triage and plan\n\nRead the code under each thread, then one verdict: take, reject (with the reason), investigate.\n\n- \"Verify with \u003Cagent>\" (perf, security, design) → dispatch that agent first, in the background,\n  with file:line anchors and the exact question; it is the long pole.\n- A \"how can this happen\" question is a design challenge: answer with facts; when the answer is\n  \"it cannot\", the fix is fail-fast, not a tolerated branch.\n- \"Remember it as a gotcha\" \u002F \"add a rule\" → `harness\u002Fproject\u002Frules\u002F*.md` for a path-scoped\n  rule, the project's map (AGENTS.md) for a repo-wide one, a QA gotchas file for a QA check\n  (`harness\u002Fproject\u002Freferences\u002Fqa-gotchas.md`; a check that holds for any stack is proposed to\n  the core instead, never edited into `harness\u002Fcore` in place) — and apply it to this PR's code.\n  Log the harness change in `harness\u002Fproject\u002FHARNESS_LOG.md`.\n- \"Do X everywhere\" means the whole repo, in its own commit.\n\nWrite the plan to `\u003Crun-dir>\u002Freview-round-\u003Ck>.md`: one row per thread — comment id,\nfull comment text, verdict, change, the test that proves it.\n\n## 3. Fix\n\nNew commits on the branch (conventional messages), or `git commit --fixup \u003Csha>` +\n`GIT_SEQUENCE_EDITOR=true git rebase -i --autosquash \u003Cbase>` when the user prefers a clean\nhistory. Nothing leaves the machine yet.\n\n## 4. Re-run the whole pipeline\n\nNot only the tests the fixes touch: every gate from `submit-pr` step 1, the panel lenses on the\nround's delta (triage their findings like the reviewer's), new screenshots from the\n`ui-design-verifier` when the change reaches the screen, and a re-check of the manual test plan and the PR body against the new diff.\n\n## 5. Push, then reply\n\nPush (`--force-with-lease` after a rebase), update the PR body, post the round's verdict comment\n(Taken \u002F Rejected \u002F Deferred). When CI is green, reply in every thread:\n\n```bash\ngh api -X POST repos\u002F{owner}\u002F{repo}\u002Fpulls\u002F\u003Cn>\u002Fcomments\u002F\u003Cid>\u002Freplies -F body=@reply.md\n```\n\n- Verdict first on its own line (\"Done —\", \"Fixed —\", \"Kept —\"), then the evidence: commit,\n  number, or file:line. Plain English, every fact kept.\n- Never resolve a thread; the reviewer resolves it after reading.\n- Reply to the author's own self-review threads too.\n\n## 6. Report\n\nOne line per thread with its verdict, then CI state, new screenshots and the PR link.\n","Read `harness\u002Fcore\u002FREADME.md`, the active runtime adapter and, when present,\n`harness\u002Fproject\u002Fskills\u002Faddress-gh-review.md` (this skill's project specifics) before following\nthis procedure. `harness\u002Fproject` in this skill means the overlay in use: `$HARNESS_PROJECT` when set; `python3 harness\u002Fcore\u002Fscripts\u002Fproject.py overlay` prints it. Resolve task artifacts with `python3 harness\u002Fcore\u002Fscripts\u002Ftask_state.py locate\n\u003Ctask>`; use the returned absolute directory, including for an existing legacy run. `\u003Crun-dir>`\nbelow means that resolved directory. Reuse existing user authorization; publish comments or\nreviews only when the user explicitly requested it or explicitly invoked a skill authorizing\nthat action.\n\n**Dispatch authority:** resolve every orchestrator\u002Fworker model and effort from\n`harness\u002Fcore\u002Fadapters\u002Fmodels.json` deep-merged with the active\n`harness\u002Fproject\u002Fmodels.json` (or `$HARNESS_PROJECT\u002Fmodels.json`). Record profile, model\nand effort. Never select from personal memory or saved preferences; router shadow is\nadvisory and cannot replace the actual static profile choice. Lane progress goes to\n`\u003Creport>.progress.md`; write final `\u003Creport>` only at the end. Requests use\n`\u003Crun>\u002Flanes\u002F\u003Cwork>.flag.md` or `tripwire.py flag`; never type into another pane.\n\n# Address a GitHub PR review\n\nThe unit of work is the whole review round, not one comment: one push and one reply per thread,\nafter the full pipeline is green again. A reply pointing at a half-tested push is worse than no\nreply. Cap: one round per invocation; stop and report after it.\n\n## Efficient testing authority\n\nApply `harness\u002Fcore\u002Frules\u002Fefficient-testing.md` to this workflow's tests and recommendations.\nChoose in-process fakes first, then one shared long-lived test service with owned logical\nisolation, then per-run services, then per-test containers only for a written correctness\nreason. Reuse expensive setup with complete content-hash keys. Keep build\u002Fresult\u002Fdependency\u002F\nimage caches enabled; bypass only a named test\u002Fstep for an input that its cache cannot see.\nRun affected cases\u002Fpackages first locally; the full suite remains required in CI\u002Fpre-PR.\nHeavy gates\u002Fevals\u002Freviews use `harness\u002Fcore\u002Fscripts\u002Fload_guard.py` for adaptive load\u002Fmemory\nadmission, never fixed slots; targeted runs\nand nested admitted work do not wait. Infrastructure changes name the isolation boundary,\ncleanup and measured cold\u002Fwarm wall\u002Fresource cost. Never replace required real paired model\nmeasurements or real-service boundary coverage with a fake.\n\n## 1. Collect\n\n`gh pr view --comments` misses inline threads. Read all three sources (`gh api` fills in\n`{owner}\u002F{repo}` from the current checkout):\n\n```bash\ngh api repos\u002F{owner}\u002F{repo}\u002Fpulls\u002F\u003Cn>\u002Fcomments --paginate \\\n  --jq '.[] | {id, user: .user.login, path, line, original_commit_id, in_reply_to_id, body}'\ngh api repos\u002F{owner}\u002F{repo}\u002Fpulls\u002F\u003Cn>\u002Freviews --jq '.[] | {id, user: .user.login, state, body}'\ngh api repos\u002F{owner}\u002F{repo}\u002Fissues\u002F\u003Cn>\u002Fcomments --jq '.[] | {id, user: .user.login, body}'\n```\n\nA thread root has `in_reply_to_id: null`; skip threads that already carry the author's reply.\n`line` refers to `original_commit_id`: read `git show \u003Coriginal_commit_id>:\u003Cpath>` before mapping\nit to the current head.\n\n## 2. Triage and plan\n\nRead the code under each thread, then one verdict: take, reject (with the reason), investigate.\n\n- \"Verify with \u003Cagent>\" (perf, security, design) → dispatch that agent first, in the background,\n  with file:line anchors and the exact question; it is the long pole.\n- A \"how can this happen\" question is a design challenge: answer with facts; when the answer is\n  \"it cannot\", the fix is fail-fast, not a tolerated branch.\n- \"Remember it as a gotcha\" \u002F \"add a rule\" → `harness\u002Fproject\u002Frules\u002F*.md` for a path-scoped\n  rule, the project's map (AGENTS.md) for a repo-wide one, a QA gotchas file for a QA check\n  (`harness\u002Fproject\u002Freferences\u002Fqa-gotchas.md`; a check that holds for any stack is proposed to\n  the core instead, never edited into `harness\u002Fcore` in place) — and apply it to this PR's code.\n  Log the harness change in `harness\u002Fproject\u002FHARNESS_LOG.md`.\n- \"Do X everywhere\" means the whole repo, in its own commit.\n\nWrite the plan to `\u003Crun-dir>\u002Freview-round-\u003Ck>.md`: one row per thread — comment id,\nfull comment text, verdict, change, the test that proves it.\n\n## 3. Fix\n\nNew commits on the branch (conventional messages), or `git commit --fixup \u003Csha>` +\n`GIT_SEQUENCE_EDITOR=true git rebase -i --autosquash \u003Cbase>` when the user prefers a clean\nhistory. Nothing leaves the machine yet.\n\n## 4. Re-run the whole pipeline\n\nNot only the tests the fixes touch: every gate from `submit-pr` step 1, the panel lenses on the\nround's delta (triage their findings like the reviewer's), new screenshots from the\n`ui-design-verifier` when the change reaches the screen, and a re-check of the manual test plan and the PR body against the new diff.\n\n## 5. Push, then reply\n\nPush (`--force-with-lease` after a rebase), update the PR body, post the round's verdict comment\n(Taken \u002F Rejected \u002F Deferred). When CI is green, reply in every thread:\n\n```bash\ngh api -X POST repos\u002F{owner}\u002F{repo}\u002Fpulls\u002F\u003Cn>\u002Fcomments\u002F\u003Cid>\u002Freplies -F body=@reply.md\n```\n\n- Verdict first on its own line (\"Done —\", \"Fixed —\", \"Kept —\"), then the evidence: commit,\n  number, or file:line. Plain English, every fact kept.\n- Never resolve a thread; the reviewer resolves it after reading.\n- Reply to the author's own self-review threads too.\n\n## 6. Report\n\nOne line per thread with its verdict, then CI state, new screenshots and the PR link.\n",{"name":5,"description":7},"main","a88770aee5bc4b664c660ce05b4da13854e51726","skills\u002Faddress-gh-review","https:\u002F\u002Fgithub.com\u002Fpharosone\u002Fdev-harness","https:\u002F\u002Fgithub.com\u002Fpharosone","https:\u002F\u002Fpharosone.ai\u002F","2026-10-14 19:18:56",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add pharosone\u002Fdev-harness --skill address-gh-review",{"tool":37,"command":38},"bunx","bunx skills add pharosone\u002Fdev-harness --skill address-gh-review",{"tool":40,"command":41},"pnpm","pnpm dlx skills add pharosone\u002Fdev-harness --skill address-gh-review","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fpharosone\u002Fdev-harness\u002Fblob\u002Fmain\u002Fskills\u002Faddress-gh-review\u002FSKILL.md",true,[],[46,53,60,67,74,81],{"skillNo":47,"name":48,"nameZh":6,"description":49,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":50,"categories":51,"keywords":52,"publishedAt":19},"01M7EF616KZ861AS6GKEWX1B8W","deploy-app","Use when the fixture app has to be deployed to its staging host.","https:\u002F\u002Fgithub.com\u002Fpharosone\u002Fdev-harness\u002Fblob\u002Fmain\u002Ftests\u002Ffixture\u002Fharness\u002Fproject\u002Fskills\u002Fdeploy-app\u002FSKILL.md",[],[],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":19},"01M7EF5VNNSHBGNMWW5M9RR0V9","submit-pr","Use when the user asks to open, update or finalize a pull request for work in this repository (\"сделай PR\", \"открой PR\", \"submit\", \"push and open a PR\"). Never on its own initiative.","https:\u002F\u002Fgithub.com\u002Fpharosone\u002Fdev-harness\u002Fblob\u002Fmain\u002Fskills\u002Fsubmit-pr\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":19},"01M7EF5NA40X2Y4YHRXE5P3MT7","pharos-investigate","Use when something must be understood before anyone acts: a bug whose cause is not known yet (intermittent, data-dependent, only in one environment, a fix that did not hold), research of data or options for a decision, or understanding how unfamiliar code really works. On \"разберись\", \"почему\", \"найди причину\", \"исследуй\", \"что выбрать\", \"investigate\", \"root cause\".","https:\u002F\u002Fgithub.com\u002Fpharosone\u002Fdev-harness\u002Fblob\u002Fmain\u002Fskills\u002Fpharos-investigate\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":19},"01M7EF5EN0FX3R1Y4AHFFBM9J1","pharos-discover","Use when a feature, endpoint, screen or behaviour change in this repository needs requirements, alternative approaches and an approved specification with TDD units; also when a spec lacks its Requirements interview, its Placement, its Taste gates or a section a project interview row requires.","https:\u002F\u002Fgithub.com\u002Fpharosone\u002Fdev-harness\u002Fblob\u002Fmain\u002Fskills\u002Fpharos-discover\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":19},"01M7EF5729KFDQ8CGB6QS5C3E4","pharos-dev","Use when implementing, fixing or refactoring anything in this repository beyond a one-line edit — executing an approved spec, a feature, a bugfix — and on follow-ups (\"сделай\", \"реализуй\", \"исполни спеку\", \"почини\", \"продолжи\", \"перезапусти ревью\", \"redo the QA\"). A review-only request runs the review step alone.","https:\u002F\u002Fgithub.com\u002Fpharosone\u002Fdev-harness\u002Fblob\u002Fmain\u002Fskills\u002Fpharos-dev\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":19},"01M7EF531SZB34M9RYAJ28J056","manual-test-plan","Use when a PR in this repository needs its hand-executable verification plan written or executed (\"test plan\", \"план ручного тестирования\", \"lets start test plan\", \"начнём тест-план\"); submit-pr invokes it for every PR.","https:\u002F\u002Fgithub.com\u002Fpharosone\u002Fdev-harness\u002Fblob\u002Fmain\u002Fskills\u002Fmanual-test-plan\u002FSKILL.md",[],[]]