[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DT64EQS172J3GFTSGW6MZR":3,"skill-same:01M6DT64EQS172J3GFTSGW6MZR":85},{"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":32,"linkOnly":33,"markdownContent":34,"markdownBody":35,"frontMatter":36,"refName":38,"commitSha":39,"skillDirectory":40,"forksCount":14,"repositoryHtmlUrl":41,"repositoryHomepageUrl":6,"ownerHtmlUrl":42,"ownerBlogUrl":43,"ownerDescription":44,"updatedAt":45,"install":46,"resources":58},"01M6DT64EQS172J3GFTSGW6MZR","verdict",null,"The Reviewer's Verdict on a PR: re-run the repo's verification skill at the PR's head, hold the PR's Evidence against it, and record pass or fail with nico-agent.","nicolasLuduena\u002Fskills","nicolasLuduena","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F47897388?v=4","01M6DT2J6QHQB14SH18EFBKT6D","Nicolás Ludueña","01M6DT2JBREQBVQYEQBR2AC31G",0,"MIT","https:\u002F\u002Fgithub.com\u002FnicolasLuduena\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Floop\u002Fverdict\u002FSKILL.md",[],[5,19,20,21,22,23,24,25,26,27,28,29,30,31],"pr","run","verification","reviewer","repo","evidence","record","head","it","with","re","true","at","2026-11-10 10:12:30",false,"---\nname: verdict\ndescription: \"The Reviewer's Verdict on a PR: re-run the repo's verification skill at the PR's head, hold the PR's Evidence against it, and record pass or fail with nico-agent.\"\ndisable-model-invocation: true\n---\n\n# Verdict\n\nYou are the Reviewer of one PR. Re-run the repo's verification at the PR's head, hold what you observe against the feature map and the PR's Evidence, and record **pass** when you drove the verification and it left no Finding, **fail** otherwise. A **mismatch** is anything you observe that differs from what a feature file or the PR's Evidence says should happen. Each mismatch becomes a **Finding**, numbered `F1`, `F2`, … afresh per Verdict and named by the head's first seven characters, the **short head**: `\u003Cshort head> F2`.\n\nThe invocation reads `verdict \u003CprUrl> for \u003CissueUrl>`. From it: the **issue key** (`owner\u002Frepo#n`, or a Linear key such as `BLE-12`), the **id** (`n`, or the Linear key; `VERIFY_RUN_ID` is the id), the **head** (`gh pr view \u003CprUrl> --json headRefOid`) and the **Evidence folder** (`.evidence\u002F\u003Cid>` in the worktree). The invocation may name any of these itself.\n\nYou write only the Evidence folder (never its `rulings.md`, which is the Implementer's), whatever the verification skill writes, and one `nico-agent verdict` call. GitHub and Linear are read-only: never push, comment, review, approve, label or mark ready. Leave the code as it is: a mismatch is a Finding, not a fix.\n\n## 1. Pin the head\n\n`git rev-parse HEAD` must be the head and `git status --porcelain --untracked-files=no` empty. Otherwise skip to step 4 with the single Finding `Worktree at \u003CHEAD>, PR head at \u003Chead>` (add `with uncommitted changes` when status is not empty).\n\n## 2. Read\n\n1. `ls -d .agents\u002Fskills\u002Fverify-*\u002F`. With none, skip to step 4 with the single Finding `No verification skill in this repo`. With one, read its `SKILL.md` and `features\u002FREADME.md`.\n2. `gh pr view \u003CprUrl> --json baseRefName,body`; `git fetch origin \u003CBase>`; `git diff origin\u002F\u003CBase>...HEAD`.\n3. Copy the body's `## Evidence` section (to the next `## `) to `\u003CEvidence folder>\u002Fpr-evidence.md`. No such section: write `No Evidence section.` there; that is a mismatch. Ignore the body's `## Findings` section, the Implementer's own tally.\n4. Pick the feature files to drive, each with the reason it was picked: every feature whose behaviour the diff changes, and every feature file the diff edits. When the diff touches none, the one closest to it.\n5. When `\u003CEvidence folder>\u002Frulings.md` exists, an earlier Verdict failed and the Implementer ruled on each Finding, one `## Findings at \u003Chead>` section per round, one line per Finding: `- **F\u003Cn>** \"\u003Ctitle>\": fixed in \u003Csha>` or `: dismissed. \u003Cwhy>`. Only the latest Ruling on a Finding counts: a Finding whose title names an earlier Ruling carries that Finding on, so its own Ruling replaces the earlier one. For each that counts:\n   - **fixed**: add the feature file the Finding came from to the picked ones, its reason `Ruling \u003Cshort head> F\u003Cn>: fixed`. A Finding on an Evidence claim is re-checked in step 3.3, a title-only one in step 1 or 2.1.\n   - **dismissed**: hold its why against the issue (`gh issue view \u003CissueUrl> --json title,body,comments`, or the Linear tool), the feature files and `PRODUCT.md`. It **holds** when they back it, and that mismatch is not raised again. Otherwise it is a Finding: `Dismissal of \u003Cshort head> F\u003Cn> does not hold: \u003Cwhat says otherwise, quoted>`.\n\nDone when you know the skill's Launch, Doctor, Evidence and Cleanup, `pr-evidence.md` exists, the picked feature files are listed with their reasons, and, with `rulings.md`, every dismissal that counts is marked held or not held.\n\n## 3. Drive\n\n1. `export VERIFY_RUN_ID=\u003Cid>`; follow the skill's Launch and Doctor. A failure the repo causes is a mismatch (record the command and output, Cleanup, skip to step 4); one your environment causes (sandbox, missing tool) is yours to fix and retry.\n2. For each picked feature file, drive every bullet of its `Driving it with` section, capturing Evidence under the Evidence folder. Note per bullet the command, the end state expected and the end state observed. When a drive leaves the run unusable, record that as a mismatch, then Cleanup, Launch and Doctor again for the next feature.\n3. Check each claim in `pr-evidence.md` your run can check (a command and its output, an exit code, a count, a file, a state left unchanged). Run verbatim any quoted command your drives did not, capturing it, except one that writes to GitHub or a remote: that claim stays unchecked. Names a run picks for itself (slugs, run ids, temp paths) may differ; anything else that differs is a mismatch.\n4. Run the skill's Cleanup.\n\nDone when every bullet of every picked feature file has an observed end state, every checkable claim is marked held or mismatched, and the Evidence files still exist after Cleanup.\n\n## 4. Write the findings\n\nWrite `\u003CEvidence folder>\u002Ffindings.md`:\n\n```markdown\n# Findings: \u003Cissue key> at \u003Chead>\n\n- **F1** \u003Cfeature file and bullet, or \"Evidence claim\">: `\u003Ccommand>`\n  Expected: \u003Cwhat the feature file or the Evidence says>\n  Observed: \u003Cwhat your run showed, quoted from the Evidence files>\n\nDriven: \u003Cfeature file> (\u003Cbullets driven>), ...\nUnchecked: \u003Ceach Evidence claim you could not check, and why>\nRulings: \u003Cshort head> F\u003Cn> fixed: held, \u003Cshort head> F\u003Cn> dismissed: not held (F\u003Cm>), ...\n```\n\nOne Finding per mismatch, except one a held dismissal covers; a mismatch a dismissal that does not hold covers is that dismissal's Finding alone. A Finding caused by an earlier one says which. A fixed Ruling whose mismatch still shows ends its title with `(still showing after Ruling \u003Cshort head> F\u003Cn>)`. A Finding with no command (steps 1 and 2.1, a dismissal that does not hold) is `- **F\u003Cn>** \u003Ctitle>` alone, and the single Finding of step 1 or 2.1 has no `Driven:`, `Unchecked:` or `Rulings:` line. `Rulings:` appears only with `rulings.md`, listing each Ruling that counts: a fixed one is `held` when its mismatch no longer shows, and `not held` when it shows or you could not drive it; a dismissed one as step 2.5 judged it. `not held` names the Finding that says why. With no Findings, the file reads `No mismatches.` followed by those lines.\n\nDone when every mismatch you noted in steps 2 and 3 is a numbered Finding, unless a held dismissal covers it; every dismissal that does not hold is one too; every Evidence claim is held, a Finding, or on the `Unchecked:` line; and, with `rulings.md`, every Ruling that counts is on the `Rulings:` line.\n\n## 5. Record the Verdict\n\n```sh\nnico-agent verdict \u003Cissue key> pass|fail --sha \u003Chead> --findings \"$PWD\u002F\u003CEvidence folder>\u002Ffindings.md\"\n```\n\n`pass` only when `findings.md` reads `No mismatches.`, `fail` otherwise. A refusal naming a newer head means the PR moved: end, a Reviewer is started for that head.\n\n- **Pass** is done when `findings.md` reads `No mismatches.` with every driven feature file on its `Driven:` line and, with `rulings.md`, every Ruling `held`, and `nico-agent` printed `verdict: \u003Cissue key> pass at \u003Chead>`.\n- **Fail** is done when `findings.md` holds one numbered Finding per mismatch and per dismissal that does not hold, and `nico-agent` printed `verdict: \u003Cissue key> fail at \u003Chead>`.\n\nEnd with the `nico-agent` output and the path of `findings.md`.\n","# Verdict\n\nYou are the Reviewer of one PR. Re-run the repo's verification at the PR's head, hold what you observe against the feature map and the PR's Evidence, and record **pass** when you drove the verification and it left no Finding, **fail** otherwise. A **mismatch** is anything you observe that differs from what a feature file or the PR's Evidence says should happen. Each mismatch becomes a **Finding**, numbered `F1`, `F2`, … afresh per Verdict and named by the head's first seven characters, the **short head**: `\u003Cshort head> F2`.\n\nThe invocation reads `verdict \u003CprUrl> for \u003CissueUrl>`. From it: the **issue key** (`owner\u002Frepo#n`, or a Linear key such as `BLE-12`), the **id** (`n`, or the Linear key; `VERIFY_RUN_ID` is the id), the **head** (`gh pr view \u003CprUrl> --json headRefOid`) and the **Evidence folder** (`.evidence\u002F\u003Cid>` in the worktree). The invocation may name any of these itself.\n\nYou write only the Evidence folder (never its `rulings.md`, which is the Implementer's), whatever the verification skill writes, and one `nico-agent verdict` call. GitHub and Linear are read-only: never push, comment, review, approve, label or mark ready. Leave the code as it is: a mismatch is a Finding, not a fix.\n\n## 1. Pin the head\n\n`git rev-parse HEAD` must be the head and `git status --porcelain --untracked-files=no` empty. Otherwise skip to step 4 with the single Finding `Worktree at \u003CHEAD>, PR head at \u003Chead>` (add `with uncommitted changes` when status is not empty).\n\n## 2. Read\n\n1. `ls -d .agents\u002Fskills\u002Fverify-*\u002F`. With none, skip to step 4 with the single Finding `No verification skill in this repo`. With one, read its `SKILL.md` and `features\u002FREADME.md`.\n2. `gh pr view \u003CprUrl> --json baseRefName,body`; `git fetch origin \u003CBase>`; `git diff origin\u002F\u003CBase>...HEAD`.\n3. Copy the body's `## Evidence` section (to the next `## `) to `\u003CEvidence folder>\u002Fpr-evidence.md`. No such section: write `No Evidence section.` there; that is a mismatch. Ignore the body's `## Findings` section, the Implementer's own tally.\n4. Pick the feature files to drive, each with the reason it was picked: every feature whose behaviour the diff changes, and every feature file the diff edits. When the diff touches none, the one closest to it.\n5. When `\u003CEvidence folder>\u002Frulings.md` exists, an earlier Verdict failed and the Implementer ruled on each Finding, one `## Findings at \u003Chead>` section per round, one line per Finding: `- **F\u003Cn>** \"\u003Ctitle>\": fixed in \u003Csha>` or `: dismissed. \u003Cwhy>`. Only the latest Ruling on a Finding counts: a Finding whose title names an earlier Ruling carries that Finding on, so its own Ruling replaces the earlier one. For each that counts:\n   - **fixed**: add the feature file the Finding came from to the picked ones, its reason `Ruling \u003Cshort head> F\u003Cn>: fixed`. A Finding on an Evidence claim is re-checked in step 3.3, a title-only one in step 1 or 2.1.\n   - **dismissed**: hold its why against the issue (`gh issue view \u003CissueUrl> --json title,body,comments`, or the Linear tool), the feature files and `PRODUCT.md`. It **holds** when they back it, and that mismatch is not raised again. Otherwise it is a Finding: `Dismissal of \u003Cshort head> F\u003Cn> does not hold: \u003Cwhat says otherwise, quoted>`.\n\nDone when you know the skill's Launch, Doctor, Evidence and Cleanup, `pr-evidence.md` exists, the picked feature files are listed with their reasons, and, with `rulings.md`, every dismissal that counts is marked held or not held.\n\n## 3. Drive\n\n1. `export VERIFY_RUN_ID=\u003Cid>`; follow the skill's Launch and Doctor. A failure the repo causes is a mismatch (record the command and output, Cleanup, skip to step 4); one your environment causes (sandbox, missing tool) is yours to fix and retry.\n2. For each picked feature file, drive every bullet of its `Driving it with` section, capturing Evidence under the Evidence folder. Note per bullet the command, the end state expected and the end state observed. When a drive leaves the run unusable, record that as a mismatch, then Cleanup, Launch and Doctor again for the next feature.\n3. Check each claim in `pr-evidence.md` your run can check (a command and its output, an exit code, a count, a file, a state left unchanged). Run verbatim any quoted command your drives did not, capturing it, except one that writes to GitHub or a remote: that claim stays unchecked. Names a run picks for itself (slugs, run ids, temp paths) may differ; anything else that differs is a mismatch.\n4. Run the skill's Cleanup.\n\nDone when every bullet of every picked feature file has an observed end state, every checkable claim is marked held or mismatched, and the Evidence files still exist after Cleanup.\n\n## 4. Write the findings\n\nWrite `\u003CEvidence folder>\u002Ffindings.md`:\n\n```markdown\n# Findings: \u003Cissue key> at \u003Chead>\n\n- **F1** \u003Cfeature file and bullet, or \"Evidence claim\">: `\u003Ccommand>`\n  Expected: \u003Cwhat the feature file or the Evidence says>\n  Observed: \u003Cwhat your run showed, quoted from the Evidence files>\n\nDriven: \u003Cfeature file> (\u003Cbullets driven>), ...\nUnchecked: \u003Ceach Evidence claim you could not check, and why>\nRulings: \u003Cshort head> F\u003Cn> fixed: held, \u003Cshort head> F\u003Cn> dismissed: not held (F\u003Cm>), ...\n```\n\nOne Finding per mismatch, except one a held dismissal covers; a mismatch a dismissal that does not hold covers is that dismissal's Finding alone. A Finding caused by an earlier one says which. A fixed Ruling whose mismatch still shows ends its title with `(still showing after Ruling \u003Cshort head> F\u003Cn>)`. A Finding with no command (steps 1 and 2.1, a dismissal that does not hold) is `- **F\u003Cn>** \u003Ctitle>` alone, and the single Finding of step 1 or 2.1 has no `Driven:`, `Unchecked:` or `Rulings:` line. `Rulings:` appears only with `rulings.md`, listing each Ruling that counts: a fixed one is `held` when its mismatch no longer shows, and `not held` when it shows or you could not drive it; a dismissed one as step 2.5 judged it. `not held` names the Finding that says why. With no Findings, the file reads `No mismatches.` followed by those lines.\n\nDone when every mismatch you noted in steps 2 and 3 is a numbered Finding, unless a held dismissal covers it; every dismissal that does not hold is one too; every Evidence claim is held, a Finding, or on the `Unchecked:` line; and, with `rulings.md`, every Ruling that counts is on the `Rulings:` line.\n\n## 5. Record the Verdict\n\n```sh\nnico-agent verdict \u003Cissue key> pass|fail --sha \u003Chead> --findings \"$PWD\u002F\u003CEvidence folder>\u002Ffindings.md\"\n```\n\n`pass` only when `findings.md` reads `No mismatches.`, `fail` otherwise. A refusal naming a newer head means the PR moved: end, a Reviewer is started for that head.\n\n- **Pass** is done when `findings.md` reads `No mismatches.` with every driven feature file on its `Driven:` line and, with `rulings.md`, every Ruling `held`, and `nico-agent` printed `verdict: \u003Cissue key> pass at \u003Chead>`.\n- **Fail** is done when `findings.md` holds one numbered Finding per mismatch and per dismissal that does not hold, and `nico-agent` printed `verdict: \u003Cissue key> fail at \u003Chead>`.\n\nEnd with the `nico-agent` output and the path of `findings.md`.\n",{"name":5,"description":7,"disable-model-invocation":37},true,"main","7ea7cd250b1d6a56795f2f23baf513a21420124b","skills\u002Floop\u002Fverdict","https:\u002F\u002Fgithub.com\u002FnicolasLuduena\u002Fskills","https:\u002F\u002Fgithub.com\u002FnicolasLuduena","https:\u002F\u002Fnico-luduena.online","Senior full-stack engineer at @txpipe · Rust, TypeScript, blockchain infrastructure, developer tooling, and privacy-preserving applications.","2026-11-10 04:46:43",{"source":8,"skillName":5,"commands":47,"prompt":57,"zipAvailable":37},[48,51,54],{"tool":49,"command":50},"npx","npx skills add nicolasLuduena\u002Fskills --skill verdict",{"tool":52,"command":53},"bunx","bunx skills add nicolasLuduena\u002Fskills --skill verdict",{"tool":55,"command":56},"pnpm","pnpm dlx skills add nicolasLuduena\u002Fskills --skill verdict","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FnicolasLuduena\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Floop\u002Fverdict\u002FSKILL.md",[59,65,69,73,77,81],{"path":60,"resourceType":61,"resourceTypeDesc":62,"sizeBytes":63,"sourceHtmlUrl":64},"agents\u002Fopenai.yaml","REFERENCE","参考文档",165,"https:\u002F\u002Fgithub.com\u002FnicolasLuduena\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Floop\u002Fverdict\u002Fagents\u002Fopenai.yaml",{"path":66,"resourceType":61,"resourceTypeDesc":62,"sizeBytes":67,"sourceHtmlUrl":68},"evals\u002Fevals.json",6143,"https:\u002F\u002Fgithub.com\u002Fpatinaproject\u002Fskills\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Frevops\u002Fevals\u002Fevals.json",{"path":70,"resourceType":61,"resourceTypeDesc":62,"sizeBytes":71,"sourceHtmlUrl":72},"references\u002Fautomation-playbooks.md",10861,"https:\u002F\u002Fgithub.com\u002Fpatinaproject\u002Fskills\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Frevops\u002Freferences\u002Fautomation-playbooks.md",{"path":74,"resourceType":61,"resourceTypeDesc":62,"sizeBytes":75,"sourceHtmlUrl":76},"references\u002Flifecycle-definitions.md",7019,"https:\u002F\u002Fgithub.com\u002Fpatinaproject\u002Fskills\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Frevops\u002Freferences\u002Flifecycle-definitions.md",{"path":78,"resourceType":61,"resourceTypeDesc":62,"sizeBytes":79,"sourceHtmlUrl":80},"references\u002Frouting-rules.md",6792,"https:\u002F\u002Fgithub.com\u002Fpatinaproject\u002Fskills\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Frevops\u002Freferences\u002Frouting-rules.md",{"path":82,"resourceType":61,"resourceTypeDesc":62,"sizeBytes":83,"sourceHtmlUrl":84},"references\u002Fscoring-models.md",7450,"https:\u002F\u002Fgithub.com\u002Fpatinaproject\u002Fskills\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Frevops\u002Freferences\u002Fscoring-models.md",[86,93,120,141,164,188],{"skillNo":87,"name":88,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":89,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":32},"01M717YJYMV0G9H52HJ9R259M2","improve","https:\u002F\u002Fgithub.com\u002FnicolasLuduena\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fhand\u002Fimprove\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FnicolasLuduena\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fhand\u002Fimprove\u002FSKILL.md",[],[88],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":104,"publishedAt":32},"01M6DT66VWY2M4VM3J7G2813T6","create-verification-skill","Generate a project-local verification skill that drives your app the way a user does — any language, framework, or platform. Use for \u002Fcreate-verification-skill, \"make a control skill for this repo\", or when a project has no scripted way to prove UI\u002FCLI\u002Fservice behavior.","https:\u002F\u002Fgithub.com\u002FnicolasLuduena\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fverify\u002Fcreate-verification-skill\u002FSKILL.md",[99],{"categoryNo":100,"categoryName":101,"taxonomyType":102,"taxonomyTypeDesc":103},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[105,106,21,107,108,109,110,111,112,113,114,38,24,19,115,23,116,117,118,119],"create verification skill","create","use","app","cli","control","platform","project","local","github","generated","verify","license","generate","harness",{"skillNo":121,"name":122,"nameZh":6,"description":123,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":124,"categories":125,"keywords":126,"publishedAt":32},"01M6DT604C3A5GRG03S2XM9QR4","tdd","Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions \"red-green-refactor\", or wants integration tests.","https:\u002F\u002Fgithub.com\u002FnicolasLuduena\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Floop\u002Ftdd\u002FSKILL.md",[],[122,127,128,129,130,131,132,107,133,134,135,136,137,138,139,140],"tests","development","driven","green","build","red-green-refactor","fix","user","first","refactor","integration","red","integration tests","test",{"skillNo":142,"name":143,"nameZh":6,"description":144,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":145,"categories":146,"keywords":148,"publishedAt":32},"01M6DT6ABQ8TMVEFEFRQ7SP58V","maintain-verification-skill","Periodic pass that keeps a project's verification skill and feature map honest: parallel source readers per feature, one live session driving every feature, at most one PR of proven corrections. Use for \u002Fmaintain-verification-skill or \"audit the verify skill\".","https:\u002F\u002Fgithub.com\u002FnicolasLuduena\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fverify\u002Fmaintain-verification-skill\u002FSKILL.md",[147],{"categoryNo":100,"categoryName":101,"taxonomyType":102,"taxonomyTypeDesc":103},[21,149,150,151,152,153,154,30,155,156,157,112,158,38,114,107,159,160,23,161,162,116,163,117,19],"maintain verification skill","maintain","periodic","normal","weekly","for","tree","as","feature","map","session","implementer","parallel","loop","audit",{"skillNo":165,"name":166,"nameZh":6,"description":167,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":168,"categories":169,"keywords":173,"publishedAt":32},"01M6DT5X7ZAHFMFDSMM1RA2500","research","Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading legwork delegated to a background agent.","https:\u002F\u002Fgithub.com\u002FnicolasLuduena\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Floop\u002Fresearch\u002FSKILL.md",[170],{"categoryNo":171,"categoryName":172,"taxonomyType":102,"taxonomyTypeDesc":103},"01JBSEEDCAT000000000000021","资料检索与研究",[166,134,174,23,175,176,177,178,179,180,107,181,182,183,184,185,186,156,187],"question","capture","markdown","investigate","api","file","docs","when","background","facts","high","reading","sources","trust",{"skillNo":189,"name":190,"nameZh":6,"description":191,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":192,"categories":193,"keywords":194,"publishedAt":32},"01M6DT5STG12ET75KKQ4M1CN1Z","quality-scan","Audit a Repo with ponytail-audit and a deepening scan and file the top findings as issues, at most five open at once, without editing code.","https:\u002F\u002Fgithub.com\u002FnicolasLuduena\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Floop\u002Fquality-scan\u002FSKILL.md",[],[195,196,197,30,198,31,199,28,156,23,200,201,163,179,202,203,204],"quality scan","scan","quality","deepening","top","editing","open","issues","code","ponytail"]