[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AMGV38CHBZ1K02JHCPPF0X":3,"skill-same:01M7AMGV38CHBZ1K02JHCPPF0X":53},{"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":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":30,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M7AMGV38CHBZ1K02JHCPPF0X","named-persona-adversarial-review",null,"Code review through the lens of real engineers' documented philosophies (Torvalds, Thompson, Carmack, Kent Beck, Jobs, Cagan). Complements abstract-role adversarial review with named, sourced perspectives. Use when automated review findings feel generic, when a PR has architectural or UX impact, or when the author wants pre-submit hardening beyond standard checks.","Cyrilthetecchieee\u002Fcyril-code-","Cyrilthetecchieee","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F219787998?v=4","01M7AF0MMMKRAA0H61XMJPV92H","Julian Cyril D ","01M7AF0MQ10AVG6QJQ1C2BC0F5",2,"MIT","https:\u002F\u002Fgithub.com\u002FCyrilthetecchieee\u002Fcyril-code-\u002Fblob\u002Fmain\u002Fsrc\u002Fcyril_code\u002Fassets\u002F.skills_repo\u002Fengineering-team\u002Fskills\u002Fnamed-persona-adversarial-review\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: \"named-persona-adversarial-review\"\ndescription: \"Code review through the lens of real engineers' documented philosophies (Torvalds, Thompson, Carmack, Kent Beck, Jobs, Cagan). Complements abstract-role adversarial review with named, sourced perspectives. Use when automated review findings feel generic, when a PR has architectural or UX impact, or when the author wants pre-submit hardening beyond standard checks.\"\n---\n\n# Named-Persona Adversarial Review\n\n> **TL;DR:** Abstract roles find abstract problems. Named engineers with *documented, sourced* philosophies find problems you would actually fix — as long as you cite the real principle and never invent the quote.\n\n**Triggers:** \"review this PR with real engineers\" | \"named persona review\" | \"philosophy-grounded review\"\n\n## Example Output\n\n```\nCRITICAL [Torvalds]: Special-case error handling at auth.ts:47 duplicates the\n  happy path. Torvalds' documented \"good taste\" principle: restructure so the\n  special case disappears rather than adding a branch. (confidence: high — TED 2016)\nWARNING  [Thompson]: parseConfig() does three unrelated things; the Unix\n  \"do one thing well\" principle argues to split it. (confidence: high)\nNOTE     [Jobs]: Error \"EACCES:13\" leaks an errno at the user surface; \"start\n  from the customer experience\" argues for a human message. (confidence: high — WWDC 1997)\nVerdict: CONCERNS — fix CRITICAL before merge.\n```\n\n## Problem\n\nAbstract adversarial review (\"act as a saboteur\") produces generic findings — the model imagines what a reviewer *might* say. This skill grounds each lens in a **real, sourced engineering philosophy** documented in [`references\u002Fpersona_principles.md`](references\u002Fpersona_principles.md): what Ken Thompson actually argued about trust, what Linus actually demonstrated about good taste — not what an AI imagines.\n\n**How it differs from `adversarial-reviewer`:** abstract roles → surface-level findings; named, sourced personas → findings anchored to a documented principle you can cite and defend.\n\n**Cost:** 1 round ≈ 8-12 min. Comparable to waiting for CI.\n\n## Attribution discipline (read this first — it is the load-bearing rule)\n\nThis skill puts named, real people's *principles* to work. That power is also its failure mode: **language models hallucinate quotes.** To stay honest:\n\n1. **Cite the principle, not a fabricated verbatim quote.** Prefer paraphrasing a documented position (\"Thompson's *Reflections on Trusting Trust* argues you can't trust code you didn't fully create\") over inventing quotation marks around words the person may never have said.\n2. **Attach a confidence level to every attribution** — `high` (documented, in `references\u002Fpersona_principles.md` with a source), `moderate` (widely attributed, source not pinned), `low`\u002F`unknown` (you're inferring). Mirrors `productivity\u002Fandreessen`'s citation discipline.\n3. **If you cannot ground a persona's lens in a real source, drop that persona.** A confidently-wrong quote attributed to a living engineer is worse than one fewer reviewer. Never fabricate a citation to hit the \"≥1 finding\" bar.\n4. **The finding must stand on its own technical merit.** The persona is a *lens that directs attention*, not the authority that makes the finding true. A real bug found \"through Carmack's lens\" is real because it's a bug, not because Carmack said so.\n\n## Rules\n\n- **Ground before role-play.** Anchor each persona in `references\u002Fpersona_principles.md` (or a verifiable search) first. Ungrounded = invalid.\n- **Findings stand on technical merit**, with the persona's principle as the lens — see the discipline above.\n- **Product persona mandatory every round.** Engineers miss UX. Always include one.\n- **Honesty over quantity.** Don't fabricate findings *or* citations. Clean dimensions get reported clean (with the zero-finding burden below).\n- **Zero-finding burden.** \"Looks fine\" is only valid if you name 3+ principles the code demonstrably satisfies, and how. Non-findings are as expensive as findings.\n\n## Persona Pools\n\nEach persona's documented principles + sources + confidence live in [`references\u002Fpersona_principles.md`](references\u002Fpersona_principles.md).\n\n**Product** (pick 1 per round — mandatory):\n\n| Persona | Documented principle | Best for |\n|---------|----------------------|----------|\n| Steve Jobs | Start from the customer experience, work back to the tech | UX, onboarding |\n| Marty Cagan | Fall in love with the problem, not the solution | PRDs, feature specs, scope creep |\n| Des Traynor (Intercom) | The first 30 seconds decide adoption | Docs, READMEs, quick starts |\n\n**Engineers** (pick 2 per round):\n\n| Persona | Documented principle | Best for | Blind spot |\n|---------|----------------------|----------|------------|\n| Ken Thompson | Trust boundaries; do one thing well | Architecture, supply chain, API | UX, docs |\n| Linus Torvalds | Eliminate the special case (\"good taste\"); never break userspace | Logic, data structures, compat | User empathy, DX |\n| John Carmack | Measure before you optimize; performance as craft | Algorithms, hot paths | Minimalism |\n| Kent Beck | Simple design; make it work → right → fast | Process, testability | Performance, security |\n| Fred Brooks | Essential vs. accidental complexity | System design, estimation | Low-level perf |\n\n**Routing (which personas when):**\n- Code correctness → Torvalds + Carmack + Jobs\n- Architecture \u002F design → Thompson + Brooks + Cagan\n- Documentation \u002F API → Thompson + Beck + Traynor\n- Performance → Carmack + Torvalds + Jobs\n- Security \u002F supply chain → Thompson + Torvalds + Cagan\n- 1st round on any PR → Torvalds + Thompson + Jobs (broadest coverage)\n\n## Severity Levels\n\n| Level | Definition | Action |\n|-------|-----------|--------|\n| BLOCKER | 2+ personas concur on a CRITICAL, or security \u002F data-loss risk | Fix before any further work |\n| CRITICAL | Wrong result, data loss, security hole, or violated core invariant | Fix before merge |\n| WARNING | Fragile, misleading, or likely to cause future bugs | Fix, or explain if deferred |\n| NOTE | Improvement that doesn't affect correctness | Optional; record for follow-up |\n\n**Promotion:** NOTE → WARNING → CRITICAL → BLOCKER. Two personas independently finding the same issue promotes it one level (concurrence is signal). BLOCKER is the ceiling.\n\n## The Process\n\n### Step 0: Read twice\n1. **Top-down** (comprehension): what changed, and why.\n2. **Bottom-up** (adversarial): read function by function, last to first. Ask what each function *actually* guarantees vs. what its name implies, where it can fail, and what it assumes about callers. Reading bottom-up breaks the author's mental model. Multi-file → trace one end-to-end path.\n\n### Step 1: Ground the principles first\nFor each persona, pull their documented principles from `references\u002Fpersona_principles.md` (or search `\"[Name] engineering philosophy principles\"` and extract only sourced positions) **before** looking at the code, so you apply the principle rather than retrofitting one to an opinion you already formed.\n\n### Step 2: Review (3 independent — 2 engineers + 1 product)\nEach persona gets: **Mindset** (one sentence from their principles), **Priorities** (3-5 criteria), **Findings** (each mapped to a documented principle + confidence level), or the **zero-finding burden** (3+ principles the code satisfies, with how).\n\n### Step 3: Synthesize & post\nMerge duplicates; count concurrences; promote per the rule; flag single-lens findings (often the most interesting). Post the report as a PR comment (default) or save to `.claude\u002Freview-[timestamp].md`.\n\n## Integrity Check (Feynman)\n\n> \"The first principle is that you must not fool yourself — and you are the easiest person to fool.\" — Richard Feynman, *Cargo Cult Science* (Caltech commencement, 1974)\n\nAfter each round, ask:\n1. Would this person's *documented* philosophy actually direct attention here — or am I projecting?\n2. Did I cite a real, sourced principle (confidence marked), or dress generic advice in a famous name?\n3. Are my findings true on technical merit independent of the name attached?\n4. All NOTE-level? Then I'm narrating one perspective in different voices. Switch ≥2 personas and re-review.\n\n## Exit Condition\n\n- **1 round minimum** for any PR.\n- **BLOCKER\u002FCRITICAL found** → fix, then 1 re-review round.\n- **CONCERNS (WARNING)** → fix or accept risk, then 1 more round.\n- **CLEAN on 2 consecutive rounds** → done.\n- **CLEAN on round 1 for a low-impact PR** → done (1 round is enough).\n\n## When to Use\n\n- You want deeper coverage than standard automated checks alone.\n- A self-authored PR needs pre-submit hardening.\n- `adversarial-reviewer` findings feel generic and you want sourced specificity.\n- Reviewing methodologies or docs (product personas excel here).\n- Auth, data, architecture, or public-API changes.\n\n## When NOT to Use\n\n- Low-impact PR (cosmetic only, no logic change) → use `adversarial-reviewer`.\n- No web access AND the persona isn't covered in `references\u002Fpersona_principles.md` → you can't ground it; don't fabricate.\n- Throwaway \u002F prototype code.\n\n## Anti-Patterns\n\nInherits all from `adversarial-reviewer`. Plus:\n\n| Anti-Pattern | Why wrong |\n|-------------|----------|\n| Inventing a verbatim quote to sound authoritative | Fabricated attribution to a real person. Cite the sourced principle + confidence, or drop it. |\n| \"As a senior engineer\" without grounding | Not a named, sourced lens. Ground first. |\n| Same 3 personas every time | Rotate per problem type — see Routing. |\n| Product person skipped | Product catches what engineers miss. |\n| Fabricating a finding to hit \"≥1 issue\" | The bar is honesty, not quota. Use the zero-finding burden instead. |\n| Skipping the integrity check | Verification without verification = rubber-stamp. |\n| 3 rounds for a trivial change | Low-impact PRs: 1 round is enough. |\n\n## Cross-References\n\n- **Extends:** [`engineering-team\u002Fadversarial-reviewer`](..\u002Fadversarial-reviewer\u002FSKILL.md) — abstract-role adversarial review (simpler, faster, no grounding needed)\n- **Related:** [`engineering-team\u002Fcode-reviewer`](..\u002Fcode-reviewer\u002FSKILL.md), [`engineering-team\u002Fsenior-security`](..\u002Fsenior-security\u002FSKILL.md)\n- **Sibling discipline:** [`productivity\u002Fandreessen`](..\u002F..\u002F..\u002Fproductivity\u002Fandreessen\u002Fskills\u002Fandreessen\u002FSKILL.md) — the confidence-level \u002F never-fabricate-a-citation pattern this skill adopts\n- **Sources & confidence per persona:** [`references\u002Fpersona_principles.md`](references\u002Fpersona_principles.md)\n- **Theory:** Edward de Bono, *Six Thinking Hats* (1985); Daniel Kahneman, *Thinking, Fast and Slow* (2011) — System-2 forcing via role switching\n\n---\n\n**Attribution:** Concept contributed by [@YuhaoLin2005](https:\u002F\u002Fgithub.com\u002FYuhaoLin2005) (PR #866). Hardened for this repo: consolidated to one location, anti-fabrication\u002Fconfidence discipline added, principles sourced in `references\u002F`.\n","# Named-Persona Adversarial Review\n\n> **TL;DR:** Abstract roles find abstract problems. Named engineers with *documented, sourced* philosophies find problems you would actually fix — as long as you cite the real principle and never invent the quote.\n\n**Triggers:** \"review this PR with real engineers\" | \"named persona review\" | \"philosophy-grounded review\"\n\n## Example Output\n\n```\nCRITICAL [Torvalds]: Special-case error handling at auth.ts:47 duplicates the\n  happy path. Torvalds' documented \"good taste\" principle: restructure so the\n  special case disappears rather than adding a branch. (confidence: high — TED 2016)\nWARNING  [Thompson]: parseConfig() does three unrelated things; the Unix\n  \"do one thing well\" principle argues to split it. (confidence: high)\nNOTE     [Jobs]: Error \"EACCES:13\" leaks an errno at the user surface; \"start\n  from the customer experience\" argues for a human message. (confidence: high — WWDC 1997)\nVerdict: CONCERNS — fix CRITICAL before merge.\n```\n\n## Problem\n\nAbstract adversarial review (\"act as a saboteur\") produces generic findings — the model imagines what a reviewer *might* say. This skill grounds each lens in a **real, sourced engineering philosophy** documented in [`references\u002Fpersona_principles.md`](references\u002Fpersona_principles.md): what Ken Thompson actually argued about trust, what Linus actually demonstrated about good taste — not what an AI imagines.\n\n**How it differs from `adversarial-reviewer`:** abstract roles → surface-level findings; named, sourced personas → findings anchored to a documented principle you can cite and defend.\n\n**Cost:** 1 round ≈ 8-12 min. Comparable to waiting for CI.\n\n## Attribution discipline (read this first — it is the load-bearing rule)\n\nThis skill puts named, real people's *principles* to work. That power is also its failure mode: **language models hallucinate quotes.** To stay honest:\n\n1. **Cite the principle, not a fabricated verbatim quote.** Prefer paraphrasing a documented position (\"Thompson's *Reflections on Trusting Trust* argues you can't trust code you didn't fully create\") over inventing quotation marks around words the person may never have said.\n2. **Attach a confidence level to every attribution** — `high` (documented, in `references\u002Fpersona_principles.md` with a source), `moderate` (widely attributed, source not pinned), `low`\u002F`unknown` (you're inferring). Mirrors `productivity\u002Fandreessen`'s citation discipline.\n3. **If you cannot ground a persona's lens in a real source, drop that persona.** A confidently-wrong quote attributed to a living engineer is worse than one fewer reviewer. Never fabricate a citation to hit the \"≥1 finding\" bar.\n4. **The finding must stand on its own technical merit.** The persona is a *lens that directs attention*, not the authority that makes the finding true. A real bug found \"through Carmack's lens\" is real because it's a bug, not because Carmack said so.\n\n## Rules\n\n- **Ground before role-play.** Anchor each persona in `references\u002Fpersona_principles.md` (or a verifiable search) first. Ungrounded = invalid.\n- **Findings stand on technical merit**, with the persona's principle as the lens — see the discipline above.\n- **Product persona mandatory every round.** Engineers miss UX. Always include one.\n- **Honesty over quantity.** Don't fabricate findings *or* citations. Clean dimensions get reported clean (with the zero-finding burden below).\n- **Zero-finding burden.** \"Looks fine\" is only valid if you name 3+ principles the code demonstrably satisfies, and how. Non-findings are as expensive as findings.\n\n## Persona Pools\n\nEach persona's documented principles + sources + confidence live in [`references\u002Fpersona_principles.md`](references\u002Fpersona_principles.md).\n\n**Product** (pick 1 per round — mandatory):\n\n| Persona | Documented principle | Best for |\n|---------|----------------------|----------|\n| Steve Jobs | Start from the customer experience, work back to the tech | UX, onboarding |\n| Marty Cagan | Fall in love with the problem, not the solution | PRDs, feature specs, scope creep |\n| Des Traynor (Intercom) | The first 30 seconds decide adoption | Docs, READMEs, quick starts |\n\n**Engineers** (pick 2 per round):\n\n| Persona | Documented principle | Best for | Blind spot |\n|---------|----------------------|----------|------------|\n| Ken Thompson | Trust boundaries; do one thing well | Architecture, supply chain, API | UX, docs |\n| Linus Torvalds | Eliminate the special case (\"good taste\"); never break userspace | Logic, data structures, compat | User empathy, DX |\n| John Carmack | Measure before you optimize; performance as craft | Algorithms, hot paths | Minimalism |\n| Kent Beck | Simple design; make it work → right → fast | Process, testability | Performance, security |\n| Fred Brooks | Essential vs. accidental complexity | System design, estimation | Low-level perf |\n\n**Routing (which personas when):**\n- Code correctness → Torvalds + Carmack + Jobs\n- Architecture \u002F design → Thompson + Brooks + Cagan\n- Documentation \u002F API → Thompson + Beck + Traynor\n- Performance → Carmack + Torvalds + Jobs\n- Security \u002F supply chain → Thompson + Torvalds + Cagan\n- 1st round on any PR → Torvalds + Thompson + Jobs (broadest coverage)\n\n## Severity Levels\n\n| Level | Definition | Action |\n|-------|-----------|--------|\n| BLOCKER | 2+ personas concur on a CRITICAL, or security \u002F data-loss risk | Fix before any further work |\n| CRITICAL | Wrong result, data loss, security hole, or violated core invariant | Fix before merge |\n| WARNING | Fragile, misleading, or likely to cause future bugs | Fix, or explain if deferred |\n| NOTE | Improvement that doesn't affect correctness | Optional; record for follow-up |\n\n**Promotion:** NOTE → WARNING → CRITICAL → BLOCKER. Two personas independently finding the same issue promotes it one level (concurrence is signal). BLOCKER is the ceiling.\n\n## The Process\n\n### Step 0: Read twice\n1. **Top-down** (comprehension): what changed, and why.\n2. **Bottom-up** (adversarial): read function by function, last to first. Ask what each function *actually* guarantees vs. what its name implies, where it can fail, and what it assumes about callers. Reading bottom-up breaks the author's mental model. Multi-file → trace one end-to-end path.\n\n### Step 1: Ground the principles first\nFor each persona, pull their documented principles from `references\u002Fpersona_principles.md` (or search `\"[Name] engineering philosophy principles\"` and extract only sourced positions) **before** looking at the code, so you apply the principle rather than retrofitting one to an opinion you already formed.\n\n### Step 2: Review (3 independent — 2 engineers + 1 product)\nEach persona gets: **Mindset** (one sentence from their principles), **Priorities** (3-5 criteria), **Findings** (each mapped to a documented principle + confidence level), or the **zero-finding burden** (3+ principles the code satisfies, with how).\n\n### Step 3: Synthesize & post\nMerge duplicates; count concurrences; promote per the rule; flag single-lens findings (often the most interesting). Post the report as a PR comment (default) or save to `.claude\u002Freview-[timestamp].md`.\n\n## Integrity Check (Feynman)\n\n> \"The first principle is that you must not fool yourself — and you are the easiest person to fool.\" — Richard Feynman, *Cargo Cult Science* (Caltech commencement, 1974)\n\nAfter each round, ask:\n1. Would this person's *documented* philosophy actually direct attention here — or am I projecting?\n2. Did I cite a real, sourced principle (confidence marked), or dress generic advice in a famous name?\n3. Are my findings true on technical merit independent of the name attached?\n4. All NOTE-level? Then I'm narrating one perspective in different voices. Switch ≥2 personas and re-review.\n\n## Exit Condition\n\n- **1 round minimum** for any PR.\n- **BLOCKER\u002FCRITICAL found** → fix, then 1 re-review round.\n- **CONCERNS (WARNING)** → fix or accept risk, then 1 more round.\n- **CLEAN on 2 consecutive rounds** → done.\n- **CLEAN on round 1 for a low-impact PR** → done (1 round is enough).\n\n## When to Use\n\n- You want deeper coverage than standard automated checks alone.\n- A self-authored PR needs pre-submit hardening.\n- `adversarial-reviewer` findings feel generic and you want sourced specificity.\n- Reviewing methodologies or docs (product personas excel here).\n- Auth, data, architecture, or public-API changes.\n\n## When NOT to Use\n\n- Low-impact PR (cosmetic only, no logic change) → use `adversarial-reviewer`.\n- No web access AND the persona isn't covered in `references\u002Fpersona_principles.md` → you can't ground it; don't fabricate.\n- Throwaway \u002F prototype code.\n\n## Anti-Patterns\n\nInherits all from `adversarial-reviewer`. Plus:\n\n| Anti-Pattern | Why wrong |\n|-------------|----------|\n| Inventing a verbatim quote to sound authoritative | Fabricated attribution to a real person. Cite the sourced principle + confidence, or drop it. |\n| \"As a senior engineer\" without grounding | Not a named, sourced lens. Ground first. |\n| Same 3 personas every time | Rotate per problem type — see Routing. |\n| Product person skipped | Product catches what engineers miss. |\n| Fabricating a finding to hit \"≥1 issue\" | The bar is honesty, not quota. Use the zero-finding burden instead. |\n| Skipping the integrity check | Verification without verification = rubber-stamp. |\n| 3 rounds for a trivial change | Low-impact PRs: 1 round is enough. |\n\n## Cross-References\n\n- **Extends:** [`engineering-team\u002Fadversarial-reviewer`](..\u002Fadversarial-reviewer\u002FSKILL.md) — abstract-role adversarial review (simpler, faster, no grounding needed)\n- **Related:** [`engineering-team\u002Fcode-reviewer`](..\u002Fcode-reviewer\u002FSKILL.md), [`engineering-team\u002Fsenior-security`](..\u002Fsenior-security\u002FSKILL.md)\n- **Sibling discipline:** [`productivity\u002Fandreessen`](..\u002F..\u002F..\u002Fproductivity\u002Fandreessen\u002Fskills\u002Fandreessen\u002FSKILL.md) — the confidence-level \u002F never-fabricate-a-citation pattern this skill adopts\n- **Sources & confidence per persona:** [`references\u002Fpersona_principles.md`](references\u002Fpersona_principles.md)\n- **Theory:** Edward de Bono, *Six Thinking Hats* (1985); Daniel Kahneman, *Thinking, Fast and Slow* (2011) — System-2 forcing via role switching\n\n---\n\n**Attribution:** Concept contributed by [@YuhaoLin2005](https:\u002F\u002Fgithub.com\u002FYuhaoLin2005) (PR #866). Hardened for this repo: consolidated to one location, anti-fabrication\u002Fconfidence discipline added, principles sourced in `references\u002F`.\n",{"name":5,"description":7},"main","57e7aa6b6e03bce1a7d7862ba9c2ec312f7f19b5","src\u002Fcyril_code\u002Fassets\u002F.skills_repo\u002Fengineering-team\u002Fskills\u002Fnamed-persona-adversarial-review",0,"https:\u002F\u002Fgithub.com\u002FCyrilthetecchieee\u002Fcyril-code-","https:\u002F\u002Fgithub.com\u002FCyrilthetecchieee","https:\u002F\u002Fwithcyril.me\u002F","Hi, I’m Julian Cyril D, a Computer Science and Business Systems student at PSNACET.\r\nI’m passionate about full-stack development, UI\u002FUX design, and building sma","2026-11-04 23:28:50",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add Cyrilthetecchieee\u002Fcyril-code- --skill named-persona-adversarial-review",{"tool":39,"command":40},"bunx","bunx skills add Cyrilthetecchieee\u002Fcyril-code- --skill named-persona-adversarial-review",{"tool":42,"command":43},"pnpm","pnpm dlx skills add Cyrilthetecchieee\u002Fcyril-code- --skill named-persona-adversarial-review","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FCyrilthetecchieee\u002Fcyril-code-\u002Fblob\u002Fmain\u002Fsrc\u002Fcyril_code\u002Fassets\u002F.skills_repo\u002Fengineering-team\u002Fskills\u002Fnamed-persona-adversarial-review\u002FSKILL.md",true,[47],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fpersona_principles.md","REFERENCE","参考文档",5479,"https:\u002F\u002Fgithub.com\u002FCyrilthetecchieee\u002Fcyril-code-\u002Fblob\u002Fmain\u002Fsrc\u002Fcyril_code\u002Fassets\u002F.skills_repo\u002Fengineering-team\u002Fskills\u002Fnamed-persona-adversarial-review\u002Freferences\u002Fpersona_principles.md",[54,63,70,78,85,92],{"skillNo":55,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":58,"licenseFileUrl":59,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":19},"01M7AQV6CYX8RMC78420V9WZ62","webapp-testing","Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FCyrilthetecchieee\u002Fcyril-code-\u002Fblob\u002Fmain\u002Fsrc\u002Fcyril_code\u002Fassets\u002F.skills_repo\u002Fwebapp-testing\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FCyrilthetecchieee\u002Fcyril-code-\u002Fblob\u002Fmain\u002Fsrc\u002Fcyril_code\u002Fassets\u002F.skills_repo\u002Fwebapp-testing\u002FSKILL.md",[],[],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":19},"01M7AQV2895N3S1MEX6K76G6G2","youtube-downloader","Download YouTube videos with customizable quality and format options. Use this skill when the user asks to download, save, or grab YouTube videos. Supports various quality settings (best, 1080p, 720p, 480p, 360p), multiple formats (mp4, webm, mkv), and audio-only downloads as MP3.","https:\u002F\u002Fgithub.com\u002FCyrilthetecchieee\u002Fcyril-code-\u002Fblob\u002Fmain\u002Fsrc\u002Fcyril_code\u002Fassets\u002F.skills_repo\u002Fvideo-downloader\u002FSKILL.md",[],[],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":58,"licenseFileUrl":74,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":19},"01M7AQTRNX62DNKVZ5GXEHRBKB","theme-factory","Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors\u002Ffonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.","https:\u002F\u002Fgithub.com\u002FCyrilthetecchieee\u002Fcyril-code-\u002Fblob\u002Fmain\u002Fsrc\u002Fcyril_code\u002Fassets\u002F.skills_repo\u002Ftheme-factory\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FCyrilthetecchieee\u002Fcyril-code-\u002Fblob\u002Fmain\u002Fsrc\u002Fcyril_code\u002Fassets\u002F.skills_repo\u002Ftheme-factory\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":19},"01M7AQTNNVHAAN9H6DA8T6ZVE0","template-skill","Replace with description of the skill and when Claude should use it.","https:\u002F\u002Fgithub.com\u002FCyrilthetecchieee\u002Fcyril-code-\u002Fblob\u002Fmain\u002Fsrc\u002Fcyril_code\u002Fassets\u002F.skills_repo\u002Ftemplate-skill\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":19},"01M7AQTJ3MQ6AKX152MEX2MYCC","tailored-resume-generator","Analyzes job descriptions and generates tailored resumes that highlight relevant experience, skills, and achievements to maximize interview chances","https:\u002F\u002Fgithub.com\u002FCyrilthetecchieee\u002Fcyril-code-\u002Fblob\u002Fmain\u002Fsrc\u002Fcyril_code\u002Fassets\u002F.skills_repo\u002Ftailored-resume-generator\u002FSKILL.md",[],[],{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":58,"licenseFileUrl":96,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":19},"01M7AQTD7D5MYET2YWG7HG9WM3","slack-gif-creator","Toolkit for creating animated GIFs optimized for Slack, with validators for size constraints and composable animation primitives. This skill applies when users request animated GIFs or emoji animations for Slack from descriptions like \"make me a GIF for Slack of X doing Y\".","https:\u002F\u002Fgithub.com\u002FCyrilthetecchieee\u002Fcyril-code-\u002Fblob\u002Fmain\u002Fsrc\u002Fcyril_code\u002Fassets\u002F.skills_repo\u002Fslack-gif-creator\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FCyrilthetecchieee\u002Fcyril-code-\u002Fblob\u002Fmain\u002Fsrc\u002Fcyril_code\u002Fassets\u002F.skills_repo\u002Fslack-gif-creator\u002FSKILL.md",[],[]]