[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7FBVC09D5CCMCXT7TW7S3S2":3,"skill-same:01M7FBVC09D5CCMCXT7TW7S3S2":50},{"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":24,"commitSha":25,"skillDirectory":26,"forksCount":13,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":29,"install":30,"resources":43},"01M7FBVC09D5CCMCXT7TW7S3S2","pr-description",null,"Writes a pull request description in a fixed shape — a generated change-stat line (Logic \u002F Tests \u002F Docs), then Summary, What changed, Validation and Test this branch, plus Why, topic sections, Review notes and Screenshots only when the change needs them. Use when the user asks to write, draft or update a PR description, PR body or merge request text for the current branch.","marynabieliaieva\u002Fdev-ai-harness-marketplace","marynabieliaieva","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F7878548?v=4","01M7FBT0ZD7GRRYKNENTZ5EH2T","01M7FBT101PH91MN21MJ7XTKMY",0,"MIT","https:\u002F\u002Fgithub.com\u002Fmarynabieliaieva\u002Fdev-ai-harness-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fengineering-paved-path\u002Fskills\u002Fpr-description\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: pr-description\ndescription: Writes a pull request description in a fixed shape — a generated change-stat line (Logic \u002F Tests \u002F Docs), then Summary, What changed, Validation and Test this branch, plus Why, topic sections, Review notes and Screenshots only when the change needs them. Use when the user asks to write, draft or update a PR description, PR body or merge request text for the current branch.\nallowed-tools: Read, Grep, Glob, Bash(bash *change-stats.sh*), Bash(git diff *), Bash(git log *), Bash(git status *), Bash(git rev-parse *)\n---\n\n# PR description\n\n\u003C!-- TODO(cut off in source): the screenshot starts mid-page — any intro text and the heading\n     above the section table were not visible. Fill in or delete this comment. -->\n\nSections, in this order:\n\n```text\n> change-stat line             ← always the first line (section 1)\n## Summary                     ← always\n## Why \u003Csomething>             ← when a decision needs defending\n## What changed                ← always (name it for the PR: \"Package changes\", \"Public exports\", …)\n## \u003Ctopic sections>            ← as many as the change warrants\n## Review notes                ← when the diff will surprise a reviewer\n## Validation                  ← always\n## Screenshots                 ← when there is UI\n## Next steps                  ← when there are open questions or follow-ups (see Voice)\n## Test this branch            ← always, always the last section\n🤖 Generated with …            ← always, the last line (see Voice)\n```\n\nOnly **Summary**, **What changed**, **Validation** and **Test this branch** are mandatory.\nDo not pad the rest to look thorough.\n\n## 1. The change-stat line\n\nAlways the first line, a blockquote, no heading above it:\n\n```markdown\n> **Logic:** +897 \u002F −243 (23 files) · **Tests:** +943 \u002F −2 (8 files) · **Docs:** +0 \u002F −0 (0 files)\n```\n\nGenerate it — do not count by hand:\n\n```sh\nbash \"${CLAUDE_SKILL_DIR}\u002Fscripts\u002Fchange-stats.sh\"          # vs origin\u002Fmain\nbash \"${CLAUDE_SKILL_DIR}\u002Fscripts\u002Fchange-stats.sh\" main     # vs another base\n```\n\nThe script counts the branch since its merge base with the base (`base...HEAD`, what the PR\nshows), so commit first: uncommitted changes are not in the line. Fetch the base if the\nscript says it is unknown.\n\nTwo characters are easy to get wrong: the minus is **U+2212** (`−`), not a hyphen, and the\nseparator is **U+00B7** (`·`). Copy them from the script output rather than retyping.\n\nClassification: anything matching `*.test.*`, `*.spec.*`, `__tests__\u002F`, `__e2e-tests__\u002F`,\n`__mocks__\u002F`, or a test-runner config counts as **Tests**; `*.md`, `*.mdx`, and `docs\u002F`\ncount as **Docs**; everything else counts as **Logic**.\n\u003C!-- TODO(cut off in source): the sentence after \"everything else\" was cut at the right edge;\n     \"counts as Logic\" is inferred from the line format. The next sentence also starts in the\n     cut-off part — only its end is visible: \"…three categories in the line even at\n     +0 \u002F −0 (0 files) — a visible zero is the point.\" -->\nKeep all three categories in the line even at +0 \u002F −0 (0 files) — a visible zero is the\npoint.\n\nThe script treats these files as test-runner configs: `jest.config.*`, `vitest.config.*`,\n`vitest.workspace.*`, `playwright.config.*`, `cypress.config.*`, `karma.conf.*`. A file\nmatching a test pattern counts as Tests even inside `docs\u002F`. A renamed file counts once,\nunder its new path; a binary file counts as a file with +0 \u002F −0.\n\n## 2. Body sections\n\n**Summary** — two or three sentences. What this adds and where it lives. Link the ticket\ninline: `[ABC-123](https:\u002F\u002F\u003Cyour-tracker>\u002Fbrowse\u002FABC-123)` — replace `\u003Cyour-tracker>` with\nyour team's tracker host. Take the ticket key from the branch name, the commits or the user;\nif there is no key or the tracker host is unknown, ask instead of guessing. Name the\nupstream PR if this builds on\n\u003C!-- TODO(cut off in source): the rest of this sentence was cut at the right edge. -->\n\n**Why …** — only when a reviewer would reasonably ask \"why this way\". Name what you\ndeliberately did *not* do and what remains the paved road, with links.\n\n**What changed** — flat bullets, one change each, present tense, verb first: \"Adds …\",\n\"Maps …\", \"Gates the feature with `partnerReportsActivityLog`\". No sub-bullets.\n\n**Review notes** — the section reviewers actually thank you for. Use it for anything that\nmakes the diff misleading: whitespace-only reformatting, generated files, a large\ntest-to-logic ratio,\n\u003C!-- TODO(cut off in source): the middle of this list was cut at the right edge; the visible\n     tail is \"…regenerated locally before the build works.\" -->\n\n**Validation** — concrete results with real numbers, one per line. Never \"tests pass\".\n\n```markdown\n- TypeScript: passed\n- ESLint: passed with 0 errors\n- \u003Ctest suite>: 107 Jest suites and 744 tests passed\n- Production build: passed\n```\n\nIf something was skipped or failed, say so here. A Validation section that quietly omits a\nfailure is worse than none.\n\n**Screenshots** — only when there is UI.\n\u003C!-- TODO(not in source): neither screenshot shows rules for Screenshots or for topic\n     sections beyond the table above. Fill in or delete this comment. -->\n\n## 3. Test this branch\n\nAlways the last section, always this heading (even for packages — the old \"Test the\ncomponent\" wording is superseded).\n\nEach PR is deployed to:\n\n```text\nhttps:\u002F\u002Fpr-\u003CPR_NUMBER>-\u003Capp-host>\u002F\u003Capp path>\n```\n\n`\u003Capp-host>` is a placeholder: replace it with your app's preview host. If you don't know\nit, ask the user instead of guessing.\n\nTake a working deep link from test or local, swap the host, and substitute this PR's\nnumber. Link straight to the screen that exercises the change, not the app root:\n\n```markdown\n## Test this branch\n\n[Open \u003Cscreen> in the PR #\u003CPR_NUMBER> \u003Cenvironment name> environment](https:\u002F\u002Fpr-\u003CPR_NUMBER>-\u003Capp-host>\u002F\u003Cpath to the screen>)\n```\n\n\u003C!-- TODO(cut off in source): a line or two between the example link and the list below may\n     be missing (the second screenshot ends at the link, the third starts at the list). -->\n\nWhen there is nothing to click on this PR:\n\n- **A package with a consumer PR open** — link to the *consumer* PR's environment and say\n  which PR it is (for example: \"#\u003Cconsumer PR> exercises this, pointing at\n  `pr-\u003Cconsumer PR>`\").\n- **A package with nothing consuming it yet** — say so plainly and skip the link:\n\n  > This component is not integrated yet, so there is nothing to click through on this PR.\n  > It is exercised by unit tests only; integration lands in a follow-up.\n\n## Workflow\n\n1. Run `change-stats.sh` and put its line first, unchanged.\n2. Read the branch: `git log \u003Cbase>..HEAD` and `git diff \u003Cbase>...HEAD`.\n3. Write the mandatory sections; add an optional one only when its condition above holds.\n4. Show the draft to the user. Don't create or edit the PR yourself unless asked.\n\nThe URL needs the PR number, which does not exist until the PR does. So create first, then\nfill in: the first body already has the `## Test this branch` heading (the gate below needs\nit), only without the link; once the number is known, add the link and edit the PR.\n\n**With `gh`:**\n\n```sh\n# 1. body without the Test this branch link\ngh pr create --base main --title \"\u003Cconventional commit title>\" --body-file \u002Ftmp\u002Fpr-body.md\n\n# 2. the create command prints the number — add the link to the section, then\ngh pr edit \u003Cnumber> --body-file \u002Ftmp\u002Fpr-body.md\n```\n\nOn GitHub Enterprise prefix both commands with `GH_HOST=\u003Cyour-ghe-host>`: plain `gh`\ntargets github.com and fails to resolve the repo. Clean up the temp file afterwards.\n\n**With the GitHub MCP server** (no `gh` installed): `create_pull_request` with the first\nbody, then `update_pull_request` with the PR number from its result and the full body.\n\n## Enforcement\n\nThe `engineering-paved-path` plugin registers `scripts\u002Fcheck-pr-body.sh` as a `PreToolUse`\nhook on `Bash` and on the MCP `create_pull_request` \u002F `update_pull_request` tools. It is off\nuntil `PR_DESCRIPTION_GH_HOST` is set (for example `github.com` or `\u003Cyour-ghe-host>`, in the\n`env` of `.claude\u002Fsettings.json`). Then on a `gh pr create` \u002F `gh pr edit` or an MCP\ncreate\u002Fupdate that supplies a body, inside a repo whose `origin` contains that host, it\ndenies the call unless the body has both the `> **Logic:**` stat line and a\n`## Test this branch` section. Every other command passes untouched.\n\u003C!-- TODO(cut off in source): the host condition was cut at the right edge (\"inside a repo\n     whose origin contains …\"); the configurable PR_DESCRIPTION_GH_HOST stands in for it. -->\n\nSo a deny from that hook is not a bug — it means the body skipped this format. Rebuild it\nfrom this file and retry; do not work around the hook. `scripts\u002Fselftest.sh` pipe-tests the\ngate.\n\nThe hook only checks the two structural markers. Everything else here — real Validation\nnumbers, prerequisites under the deep link, Review notes — is on you.\n\n## Voice\n\nMatch the reference PRs:\n\n- Plain declarative sentences. No \"This PR …\", no selling, no adjectives doing persuasion.\n- Backticks on every identifier, flag, path, package, and env name.\n- Sentence-case `##` headings.\n- No emoji. No AI attribution or generation notices anywhere in the body — except the one\n  footer below.\n- Prefer a table for attribute\u002Fvalue or name\u002Fmeaning pairs; bullets for everything else.\n- Write the parts a reviewer cannot get from the diff: why this shape, what it deliberately\n  excludes, what to click. Never narrate the diff line by line.\n- Open questions and follow-ups belong in a closing `## Next steps` above\n  `## Test this branch`, not scattered inline.\n\nThe body ends with this footer as its last line, after `## Test this branch` and separated\nfrom it by a blank line. It is not a section, so `## Test this branch` stays the last\nsection; this is the only emoji and the only AI mention in the body:\n\n```markdown\n🤖 Generated with [Claude Code](https:\u002F\u002Fclaude.com\u002Fclaude-code)\n```\n\n\u003C!-- TODO(cut off in source): the third screenshot ends with a horizontal rule after Voice;\n     anything below it was not visible. -->\n","# PR description\n\n\u003C!-- TODO(cut off in source): the screenshot starts mid-page — any intro text and the heading\n     above the section table were not visible. Fill in or delete this comment. -->\n\nSections, in this order:\n\n```text\n> change-stat line             ← always the first line (section 1)\n## Summary                     ← always\n## Why \u003Csomething>             ← when a decision needs defending\n## What changed                ← always (name it for the PR: \"Package changes\", \"Public exports\", …)\n## \u003Ctopic sections>            ← as many as the change warrants\n## Review notes                ← when the diff will surprise a reviewer\n## Validation                  ← always\n## Screenshots                 ← when there is UI\n## Next steps                  ← when there are open questions or follow-ups (see Voice)\n## Test this branch            ← always, always the last section\n🤖 Generated with …            ← always, the last line (see Voice)\n```\n\nOnly **Summary**, **What changed**, **Validation** and **Test this branch** are mandatory.\nDo not pad the rest to look thorough.\n\n## 1. The change-stat line\n\nAlways the first line, a blockquote, no heading above it:\n\n```markdown\n> **Logic:** +897 \u002F −243 (23 files) · **Tests:** +943 \u002F −2 (8 files) · **Docs:** +0 \u002F −0 (0 files)\n```\n\nGenerate it — do not count by hand:\n\n```sh\nbash \"${CLAUDE_SKILL_DIR}\u002Fscripts\u002Fchange-stats.sh\"          # vs origin\u002Fmain\nbash \"${CLAUDE_SKILL_DIR}\u002Fscripts\u002Fchange-stats.sh\" main     # vs another base\n```\n\nThe script counts the branch since its merge base with the base (`base...HEAD`, what the PR\nshows), so commit first: uncommitted changes are not in the line. Fetch the base if the\nscript says it is unknown.\n\nTwo characters are easy to get wrong: the minus is **U+2212** (`−`), not a hyphen, and the\nseparator is **U+00B7** (`·`). Copy them from the script output rather than retyping.\n\nClassification: anything matching `*.test.*`, `*.spec.*`, `__tests__\u002F`, `__e2e-tests__\u002F`,\n`__mocks__\u002F`, or a test-runner config counts as **Tests**; `*.md`, `*.mdx`, and `docs\u002F`\ncount as **Docs**; everything else counts as **Logic**.\n\u003C!-- TODO(cut off in source): the sentence after \"everything else\" was cut at the right edge;\n     \"counts as Logic\" is inferred from the line format. The next sentence also starts in the\n     cut-off part — only its end is visible: \"…three categories in the line even at\n     +0 \u002F −0 (0 files) — a visible zero is the point.\" -->\nKeep all three categories in the line even at +0 \u002F −0 (0 files) — a visible zero is the\npoint.\n\nThe script treats these files as test-runner configs: `jest.config.*`, `vitest.config.*`,\n`vitest.workspace.*`, `playwright.config.*`, `cypress.config.*`, `karma.conf.*`. A file\nmatching a test pattern counts as Tests even inside `docs\u002F`. A renamed file counts once,\nunder its new path; a binary file counts as a file with +0 \u002F −0.\n\n## 2. Body sections\n\n**Summary** — two or three sentences. What this adds and where it lives. Link the ticket\ninline: `[ABC-123](https:\u002F\u002F\u003Cyour-tracker>\u002Fbrowse\u002FABC-123)` — replace `\u003Cyour-tracker>` with\nyour team's tracker host. Take the ticket key from the branch name, the commits or the user;\nif there is no key or the tracker host is unknown, ask instead of guessing. Name the\nupstream PR if this builds on\n\u003C!-- TODO(cut off in source): the rest of this sentence was cut at the right edge. -->\n\n**Why …** — only when a reviewer would reasonably ask \"why this way\". Name what you\ndeliberately did *not* do and what remains the paved road, with links.\n\n**What changed** — flat bullets, one change each, present tense, verb first: \"Adds …\",\n\"Maps …\", \"Gates the feature with `partnerReportsActivityLog`\". No sub-bullets.\n\n**Review notes** — the section reviewers actually thank you for. Use it for anything that\nmakes the diff misleading: whitespace-only reformatting, generated files, a large\ntest-to-logic ratio,\n\u003C!-- TODO(cut off in source): the middle of this list was cut at the right edge; the visible\n     tail is \"…regenerated locally before the build works.\" -->\n\n**Validation** — concrete results with real numbers, one per line. Never \"tests pass\".\n\n```markdown\n- TypeScript: passed\n- ESLint: passed with 0 errors\n- \u003Ctest suite>: 107 Jest suites and 744 tests passed\n- Production build: passed\n```\n\nIf something was skipped or failed, say so here. A Validation section that quietly omits a\nfailure is worse than none.\n\n**Screenshots** — only when there is UI.\n\u003C!-- TODO(not in source): neither screenshot shows rules for Screenshots or for topic\n     sections beyond the table above. Fill in or delete this comment. -->\n\n## 3. Test this branch\n\nAlways the last section, always this heading (even for packages — the old \"Test the\ncomponent\" wording is superseded).\n\nEach PR is deployed to:\n\n```text\nhttps:\u002F\u002Fpr-\u003CPR_NUMBER>-\u003Capp-host>\u002F\u003Capp path>\n```\n\n`\u003Capp-host>` is a placeholder: replace it with your app's preview host. If you don't know\nit, ask the user instead of guessing.\n\nTake a working deep link from test or local, swap the host, and substitute this PR's\nnumber. Link straight to the screen that exercises the change, not the app root:\n\n```markdown\n## Test this branch\n\n[Open \u003Cscreen> in the PR #\u003CPR_NUMBER> \u003Cenvironment name> environment](https:\u002F\u002Fpr-\u003CPR_NUMBER>-\u003Capp-host>\u002F\u003Cpath to the screen>)\n```\n\n\u003C!-- TODO(cut off in source): a line or two between the example link and the list below may\n     be missing (the second screenshot ends at the link, the third starts at the list). -->\n\nWhen there is nothing to click on this PR:\n\n- **A package with a consumer PR open** — link to the *consumer* PR's environment and say\n  which PR it is (for example: \"#\u003Cconsumer PR> exercises this, pointing at\n  `pr-\u003Cconsumer PR>`\").\n- **A package with nothing consuming it yet** — say so plainly and skip the link:\n\n  > This component is not integrated yet, so there is nothing to click through on this PR.\n  > It is exercised by unit tests only; integration lands in a follow-up.\n\n## Workflow\n\n1. Run `change-stats.sh` and put its line first, unchanged.\n2. Read the branch: `git log \u003Cbase>..HEAD` and `git diff \u003Cbase>...HEAD`.\n3. Write the mandatory sections; add an optional one only when its condition above holds.\n4. Show the draft to the user. Don't create or edit the PR yourself unless asked.\n\nThe URL needs the PR number, which does not exist until the PR does. So create first, then\nfill in: the first body already has the `## Test this branch` heading (the gate below needs\nit), only without the link; once the number is known, add the link and edit the PR.\n\n**With `gh`:**\n\n```sh\n# 1. body without the Test this branch link\ngh pr create --base main --title \"\u003Cconventional commit title>\" --body-file \u002Ftmp\u002Fpr-body.md\n\n# 2. the create command prints the number — add the link to the section, then\ngh pr edit \u003Cnumber> --body-file \u002Ftmp\u002Fpr-body.md\n```\n\nOn GitHub Enterprise prefix both commands with `GH_HOST=\u003Cyour-ghe-host>`: plain `gh`\ntargets github.com and fails to resolve the repo. Clean up the temp file afterwards.\n\n**With the GitHub MCP server** (no `gh` installed): `create_pull_request` with the first\nbody, then `update_pull_request` with the PR number from its result and the full body.\n\n## Enforcement\n\nThe `engineering-paved-path` plugin registers `scripts\u002Fcheck-pr-body.sh` as a `PreToolUse`\nhook on `Bash` and on the MCP `create_pull_request` \u002F `update_pull_request` tools. It is off\nuntil `PR_DESCRIPTION_GH_HOST` is set (for example `github.com` or `\u003Cyour-ghe-host>`, in the\n`env` of `.claude\u002Fsettings.json`). Then on a `gh pr create` \u002F `gh pr edit` or an MCP\ncreate\u002Fupdate that supplies a body, inside a repo whose `origin` contains that host, it\ndenies the call unless the body has both the `> **Logic:**` stat line and a\n`## Test this branch` section. Every other command passes untouched.\n\u003C!-- TODO(cut off in source): the host condition was cut at the right edge (\"inside a repo\n     whose origin contains …\"); the configurable PR_DESCRIPTION_GH_HOST stands in for it. -->\n\nSo a deny from that hook is not a bug — it means the body skipped this format. Rebuild it\nfrom this file and retry; do not work around the hook. `scripts\u002Fselftest.sh` pipe-tests the\ngate.\n\nThe hook only checks the two structural markers. Everything else here — real Validation\nnumbers, prerequisites under the deep link, Review notes — is on you.\n\n## Voice\n\nMatch the reference PRs:\n\n- Plain declarative sentences. No \"This PR …\", no selling, no adjectives doing persuasion.\n- Backticks on every identifier, flag, path, package, and env name.\n- Sentence-case `##` headings.\n- No emoji. No AI attribution or generation notices anywhere in the body — except the one\n  footer below.\n- Prefer a table for attribute\u002Fvalue or name\u002Fmeaning pairs; bullets for everything else.\n- Write the parts a reviewer cannot get from the diff: why this shape, what it deliberately\n  excludes, what to click. Never narrate the diff line by line.\n- Open questions and follow-ups belong in a closing `## Next steps` above\n  `## Test this branch`, not scattered inline.\n\nThe body ends with this footer as its last line, after `## Test this branch` and separated\nfrom it by a blank line. It is not a section, so `## Test this branch` stays the last\nsection; this is the only emoji and the only AI mention in the body:\n\n```markdown\n🤖 Generated with [Claude Code](https:\u002F\u002Fclaude.com\u002Fclaude-code)\n```\n\n\u003C!-- TODO(cut off in source): the third screenshot ends with a horizontal rule after Voice;\n     anything below it was not visible. -->\n",{"name":5,"description":7,"allowed-tools":23},"Read, Grep, Glob, Bash(bash *change-stats.sh*), Bash(git diff *), Bash(git log *), Bash(git status *), Bash(git rev-parse *)","main","3bcf689e2951ea8cef76e93d0e9a96a8443cec13","plugins\u002Fengineering-paved-path\u002Fskills\u002Fpr-description","https:\u002F\u002Fgithub.com\u002Fmarynabieliaieva\u002Fdev-ai-harness-marketplace","https:\u002F\u002Fgithub.com\u002Fmarynabieliaieva","2026-10-27 00:55:00",{"source":8,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add marynabieliaieva\u002Fdev-ai-harness-marketplace --skill pr-description",{"tool":36,"command":37},"bunx","bunx skills add marynabieliaieva\u002Fdev-ai-harness-marketplace --skill pr-description",{"tool":39,"command":40},"pnpm","pnpm dlx skills add marynabieliaieva\u002Fdev-ai-harness-marketplace --skill pr-description","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmarynabieliaieva\u002Fdev-ai-harness-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fengineering-paved-path\u002Fskills\u002Fpr-description\u002FSKILL.md",true,[44],{"path":45,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":48,"sourceHtmlUrl":49},"scripts\u002Fchange-stats.sh","SCRIPT","脚本",2409,"https:\u002F\u002Fgithub.com\u002Fmarynabieliaieva\u002Fdev-ai-harness-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fengineering-paved-path\u002Fskills\u002Fpr-description\u002Fscripts\u002Fchange-stats.sh",[51,58,65,72,79,86],{"skillNo":52,"name":53,"nameZh":6,"description":54,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":55,"categories":56,"keywords":57,"publishedAt":18},"01M7FBX6FAH2MGVNNE4RGG2RPF","workflow-retro","Retrospective of a finished multi-agent workflow run (e.g. \u002Fsdd-engineering:run-plan, a code review, spec → plan → execution) — collects run facts (agents spawned, spawn order and waves, tokens per agent and per type, fix rounds, caps hit, human interventions), extracts insights per agent type (what was hard, what was easy, what information was duplicated, what each gate missed and who caught it later) and turns them into concrete, evidence-backed proposals for agent\u002Fskill\u002Fplan changes. Writes a ledger entry to docs\u002Fretro\u002Fledger\u002F and a summary in chat. Data source is the current conversation by default; --deep also parses the session transcripts on disk. Invoked only by the user as \u002Fsdd-engineering:workflow-retro — never automatically, never by another skill or agent.","https:\u002F\u002Fgithub.com\u002Fmarynabieliaieva\u002Fdev-ai-harness-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fsdd-engineering\u002Fskills\u002Fworkflow-retro\u002FSKILL.md",[],[],{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":18},"01M7FBX11WK2ZEC50W955GVJ87","run-plan","Runs the Spec Driven Development execution workflow for an already-written Implementation Plan (docs\u002Fplans\u002F\u003Cslug>.md) — implementer tasks wave by wave along the plan's DAG, one plan-verifier pass with a fix loop, an architecture-review loop (review → fix → re-review until clean or the round cap), then one full test run. Accepts the plan, optionally the spec, extra requirements text and design files. Does NOT run spec-creator or implementation-planner (those are run manually first). Invoked only by the user as \u002Fsdd-engineering:run-plan.","https:\u002F\u002Fgithub.com\u002Fmarynabieliaieva\u002Fdev-ai-harness-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fsdd-engineering\u002Fskills\u002Frun-plan\u002FSKILL.md",[],[],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":18},"01M7FBWWYCS5F001B95Z8YXX3Q","engineering-insights","Captures a non-obvious engineering insight (a working pattern, an antipattern\u002Fdead end, a decision with its reason, or a recurring error and fix) found while working in this repo, and files it into the INSIGHTS.md of the package the session touched. Use at the end of a session that learned something substantial, or immediately when something surprising comes up — skip when nothing non-obvious happened.","https:\u002F\u002Fgithub.com\u002Fmarynabieliaieva\u002Fdev-ai-harness-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fsdd-engineering\u002Fskills\u002Fengineering-insights\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":18},"01M7FBWSMXJGXS3KSHKSVCZR8V","flaky-patterns","Reference catalogue of flaky-test causes — for each class, how it shows up in a stack trace, the real fix, the masking fixes to reject, and how to reproduce it deterministically without running the test many times. Use when diagnosing or reviewing a fix for a test that passes and fails on the same code.","https:\u002F\u002Fgithub.com\u002Fmarynabieliaieva\u002Fdev-ai-harness-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fflaky-fix\u002Fskills\u002Fflaky-patterns\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":18},"01M7FBWKCDZNTQE9AW5PYA47KS","flaky-fix","Triage and fix one flaky test without extra pipeline or test runs — from the test name, a stack trace, the date it became flaky and its failure rate to a Jira issue, a fix branch, a reviewed commit and a PR, with verification left to the normal runs of main after merge. Invoked only by the user as \u002Fflaky-fix:flaky-fix.","https:\u002F\u002Fgithub.com\u002Fmarynabieliaieva\u002Fdev-ai-harness-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fflaky-fix\u002Fskills\u002Fflaky-fix\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":90,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":18},"01M7FBWDF214X5KZ4YKD2XDJD8","zod","Zod schema validation best practices for type safety, parsing, and error handling. This skill should be used when defining z.object schemas, using z.string validations, safeParse, or z.infer. This skill does NOT cover form-library integration (e.g. React Hook Form resolvers) or OpenAPI client generation.","https:\u002F\u002Fgithub.com\u002Fmarynabieliaieva\u002Fdev-ai-harness-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fengineering-paved-path\u002Fskills\u002Fzod\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fmarynabieliaieva\u002Fdev-ai-harness-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fengineering-paved-path\u002Fskills\u002Fzod\u002FSKILL.md",[],[]]