[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7DDP9JGBTZMJHRVAYB8WWH4":3,"skill-same:01M7DDP9JGBTZMJHRVAYB8WWH4":49},{"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":25,"commitSha":26,"skillDirectory":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":30,"ownerHtmlUrl":31,"ownerBlogUrl":32,"ownerDescription":33,"updatedAt":34,"install":35,"resources":48},"01M7DDP9JGBTZMJHRVAYB8WWH4","summarize",null,"Produces a structured execution summary of the current session — every action taken, issues found with their root causes, the solutions implemented, verification evidence, and outstanding work. Use when the user types \u002Fsummarize, asks for a session recap, wants a handoff document, asks \"what did we do\", or needs a record of changes before ending a session.","Marvellbrazil\u002Fmy-agentic-skills","Marvellbrazil","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F184349613?v=4","01M7DCJPCRHP7SZS0T5H1GJZ8F","Marvello Faisal","01M7DCJPDCZDB94VG0QXGC6RC3",5,"MIT","https:\u002F\u002Fgithub.com\u002FMarvellbrazil\u002Fmy-agentic-skills\u002Fblob\u002Fmain\u002Fskills\u002Fsummarize\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: summarize\ndescription: Produces a structured execution summary of the current session — every action taken, issues found with their root causes, the solutions implemented, verification evidence, and outstanding work. Use when the user types \u002Fsummarize, asks for a session recap, wants a handoff document, asks \"what did we do\", or needs a record of changes before ending a session.\nallowed-tools: Read Grep Glob Bash\n---\n\n# Summarize\n\nProduce an accurate, scannable record of what happened in this session.\n\nThe summary serves two readers: the user, who wants to confirm what changed, and a future session or teammate, who wants to continue the work without re-deriving it. Write for both.\n\n## The Integrity Rule\n\n**Report only what actually happened in this session.**\n\n- Do not claim a file was changed if it was not.\n- Do not claim a test passed unless you saw it pass.\n- Do not present a plan as a completed action.\n- Do not omit a failure, a revert, or a dead end. A summary that hides the failed attempt makes the next session repeat it.\n- If you do not know whether something succeeded, say so.\n\nVerify claims against the session record rather than recalling them. Use the tools to confirm file state and repository state.\n\n```bash\ngit status --short\ngit diff --stat\ngit log --oneline -10\n```\n\nIf the session made no repository changes, say that plainly rather than padding the report.\n\n## Structure\n\nProduce these sections in this order. Omit a section only when it is genuinely empty — and when you omit one, say so, because a missing section reads as an oversight.\n\n### 1. Overview\n\nTwo to four sentences. What was the session about, what was the outcome, and what is the state now. A reader who stops here should know whether the work is done.\n\n### 2. Actions Taken\n\nEvery action, in the order it happened, with the evidence.\n\n| #   | Action | Target                   | Result                            |\n| --- | ------ | ------------------------ | --------------------------------- |\n| 1   | Read   | `src\u002Fauth\u002Fsession.ts`    | Located the token refresh path    |\n| 2   | Edit   | `src\u002Fauth\u002Fsession.ts:88` | Added expiry check before refresh |\n| 3   | Run    | `bun test src\u002Fauth`      | 12 passed, 0 failed               |\n| 4   | Run    | `bunx tsc --noEmit`      | 2 errors, both pre-existing       |\n\nGroup by type when the list is long: **Files created**, **Files modified**, **Files deleted**, **Commands executed**, **Dependencies changed**, **Configuration changed**. For each modified file, state what changed and why — not just that it changed.\n\n### 3. Issues and Root Causes\n\nFor each problem encountered — reported by the user or discovered during the work.\n\n```markdown\n#### Issue 1 — \u003Cone-line symptom>\n\n**Symptom** What was observed, with the exact error text if there was one.\n\n**Root cause** Why it happened. Not the surface location — the actual mechanism.\n\n**Evidence** The file, line, command output, or stack frame that proves the cause.\n\n**Fix** What was changed and why that addresses the cause rather than the symptom.\n\n**Verification** How it was confirmed fixed, with the result.\n```\n\nDistinguish clearly between:\n\n- **Reported by the user** — a bug or request they raised.\n- **Discovered during work** — something you found while doing something else.\n- **Pre-existing** — a defect you did not introduce and did not fix. **Always call these out separately.** Conflating a pre-existing problem with your own change makes the diff look worse than it is and hides real work the user still owes.\n\n### 4. Changes Made\n\nFor each change, the substance — not the diff.\n\n- What the code did before and what it does now.\n- The key logic or structural decision, and the constraint that drove it.\n- Edge cases handled, and edge cases deliberately not handled.\n- Anything a reviewer must know to read the diff correctly.\n\nFor an architectural change, describe the before and after shape in a sentence or a small diagram.\n\n### 5. Verification\n\nWhat was actually run, and what it returned. This section is where trust is earned or lost.\n\n| Check      | Command                              | Result                     |\n| ---------- | ------------------------------------ | -------------------------- |\n| Type check | `bunx tsc --noEmit`                  | Pass — 0 errors            |\n| Unit tests | `bun test`                           | Pass — 47 passed, 0 failed |\n| Lint       | `bun lint`                           | Pass                       |\n| Build      | `bun build`                          | Pass                       |\n| Manual     | Loaded `\u002Flogin`, submitted bad creds | Correct error shown        |\n\nIf a check was **not** run, list it under Not Verified with the reason. An unverified claim stated as verified is the single most damaging thing a summary can do.\n\n### 6. Not Verified \u002F Known Gaps\n\nBe specific and unflinching.\n\n- What was not tested and why (no test exists, no fixture, requires a live service).\n- Assumptions made that were not confirmed.\n- Behavior you changed that has no test coverage.\n- Anything you are uncertain about.\n\n### 7. Follow-Up\n\nConcrete, ordered next steps. Each names what to do and why it matters.\n\n1. **Add a regression test** for the expiry boundary at `src\u002Fauth\u002Fsession.ts:88` — the fix is untested, so it can silently regress.\n2. **Migrate the two callers** of the deprecated helper — they still use the old signature.\n3. **Pre-existing:** `tsc` reports 2 errors in `src\u002Flegacy\u002F*` — unrelated to this session, still open.\n\nSeparate **blocking** from **optional**. Do not pad this list with speculative work.\n\n## Output Rules\n\n- **Lead with the outcome.** The first line answers \"did it work\".\n- **Use tables for anything enumerable.** Actions, files, verification results.\n- **Cite locations.** `src\u002Fauth\u002Fsession.ts:88`, not \"the session file\".\n- **Quote exact errors and exact command output.** Paraphrasing an error loses the string the reader needs to search for.\n- **Distinguish done from planned from blocked.** Use explicit labels.\n- **Be concise but complete.** Cut adjectives, not facts. No \"successfully\", no \"carefully\", no \"it's worth noting\".\n- **Keep it readable.** A reader should be able to skim the headings and tables and get the shape in ten seconds, then read one section for detail.\n- **No emoji, no decorative formatting.** This is a record.\n\n## Handling an Empty or Trivial Session\n\nIf the session was a question, a review with no edits, or an exploration, do not manufacture sections. Report what happened in the honest shape:\n\n```markdown\n## Overview\n\nReviewed the proposed caching layer. No code changed — the design has a\ncorrectness problem that should be resolved first.\n\n## Findings\n\n| #   | Finding                                                 | Severity | Location             |\n| --- | ------------------------------------------------------- | -------- | -------------------- |\n| 1   | Cache key omits the tenant id, so tenants share entries | Critical | src\u002Fcache\u002Fkeys.ts:14 |\n\n## Actions Taken\n\nRead-only. No files modified, no commands run beyond search.\n\n## Recommendation\n\nFix the cache key before implementing. See finding 1.\n```\n\nA short accurate summary beats a long padded one.\n\n## Handoff Form\n\nWhen the user wants to hand off to another session or teammate, add a section that a fresh agent can act on without reading the transcript:\n\n```markdown\n## Handoff\n\n**State** Feature implemented and tested; not yet committed.\n**Branch** `feat\u002Fsession-expiry` — 3 commits ahead of `main`\n**Entry point** `src\u002Fauth\u002Fsession.ts` — `refreshSession()` is the changed function\n**How to verify** `bun test src\u002Fauth && bun run dev`, then load `\u002Flogin`\n**Open** Two callers still use the old signature — see Follow-Up 2.\n**Do not** Revert the `!` on the schema change; it is intentional.\n```\n\n## Common Mistakes\n\n| Mistake                                       | Why It Breaks                                                 | Correct Approach                               |\n| --------------------------------------------- | ------------------------------------------------------------- | ---------------------------------------------- |\n| Claiming tests passed without running them    | Destroys trust the moment it is checked                       | Run them, or list under Not Verified           |\n| Mixing pre-existing defects with your changes | Makes the diff look worse and hides the user's remaining work | Separate \"pre-existing\" explicitly             |\n| Listing files without saying what changed     | Unreadable; the user must open every file                     | One line per file describing the change        |\n| Paraphrasing an error message                 | The reader cannot search for it                               | Quote it exactly                               |\n| Reporting a plan as done                      | The next session builds on something that does not exist      | Label done \u002F planned \u002F blocked                 |\n| Omitting the failed attempt                   | The next session repeats it                                   | Record dead ends and why they failed           |\n| Padding with \"successfully\" and \"carefully\"   | Buries the facts                                              | Cut the adverbs                                |\n| No verification section                       | The reader cannot tell whether anything was checked           | Always state what was run and what it returned |\n| Writing prose where a table belongs           | Slow to scan                                                  | Tables for enumerables                         |\n| Burying the outcome at the end                | The reader must read everything to learn whether it worked    | Lead with the outcome                          |\n| Inventing follow-up work                      | Wastes the reader's attention                                 | Only real, actionable next steps               |\n| Manufacturing sections for a trivial session  | Signals padding and undermines the whole report               | Report the honest shape, however short         |\n","# Summarize\n\nProduce an accurate, scannable record of what happened in this session.\n\nThe summary serves two readers: the user, who wants to confirm what changed, and a future session or teammate, who wants to continue the work without re-deriving it. Write for both.\n\n## The Integrity Rule\n\n**Report only what actually happened in this session.**\n\n- Do not claim a file was changed if it was not.\n- Do not claim a test passed unless you saw it pass.\n- Do not present a plan as a completed action.\n- Do not omit a failure, a revert, or a dead end. A summary that hides the failed attempt makes the next session repeat it.\n- If you do not know whether something succeeded, say so.\n\nVerify claims against the session record rather than recalling them. Use the tools to confirm file state and repository state.\n\n```bash\ngit status --short\ngit diff --stat\ngit log --oneline -10\n```\n\nIf the session made no repository changes, say that plainly rather than padding the report.\n\n## Structure\n\nProduce these sections in this order. Omit a section only when it is genuinely empty — and when you omit one, say so, because a missing section reads as an oversight.\n\n### 1. Overview\n\nTwo to four sentences. What was the session about, what was the outcome, and what is the state now. A reader who stops here should know whether the work is done.\n\n### 2. Actions Taken\n\nEvery action, in the order it happened, with the evidence.\n\n| #   | Action | Target                   | Result                            |\n| --- | ------ | ------------------------ | --------------------------------- |\n| 1   | Read   | `src\u002Fauth\u002Fsession.ts`    | Located the token refresh path    |\n| 2   | Edit   | `src\u002Fauth\u002Fsession.ts:88` | Added expiry check before refresh |\n| 3   | Run    | `bun test src\u002Fauth`      | 12 passed, 0 failed               |\n| 4   | Run    | `bunx tsc --noEmit`      | 2 errors, both pre-existing       |\n\nGroup by type when the list is long: **Files created**, **Files modified**, **Files deleted**, **Commands executed**, **Dependencies changed**, **Configuration changed**. For each modified file, state what changed and why — not just that it changed.\n\n### 3. Issues and Root Causes\n\nFor each problem encountered — reported by the user or discovered during the work.\n\n```markdown\n#### Issue 1 — \u003Cone-line symptom>\n\n**Symptom** What was observed, with the exact error text if there was one.\n\n**Root cause** Why it happened. Not the surface location — the actual mechanism.\n\n**Evidence** The file, line, command output, or stack frame that proves the cause.\n\n**Fix** What was changed and why that addresses the cause rather than the symptom.\n\n**Verification** How it was confirmed fixed, with the result.\n```\n\nDistinguish clearly between:\n\n- **Reported by the user** — a bug or request they raised.\n- **Discovered during work** — something you found while doing something else.\n- **Pre-existing** — a defect you did not introduce and did not fix. **Always call these out separately.** Conflating a pre-existing problem with your own change makes the diff look worse than it is and hides real work the user still owes.\n\n### 4. Changes Made\n\nFor each change, the substance — not the diff.\n\n- What the code did before and what it does now.\n- The key logic or structural decision, and the constraint that drove it.\n- Edge cases handled, and edge cases deliberately not handled.\n- Anything a reviewer must know to read the diff correctly.\n\nFor an architectural change, describe the before and after shape in a sentence or a small diagram.\n\n### 5. Verification\n\nWhat was actually run, and what it returned. This section is where trust is earned or lost.\n\n| Check      | Command                              | Result                     |\n| ---------- | ------------------------------------ | -------------------------- |\n| Type check | `bunx tsc --noEmit`                  | Pass — 0 errors            |\n| Unit tests | `bun test`                           | Pass — 47 passed, 0 failed |\n| Lint       | `bun lint`                           | Pass                       |\n| Build      | `bun build`                          | Pass                       |\n| Manual     | Loaded `\u002Flogin`, submitted bad creds | Correct error shown        |\n\nIf a check was **not** run, list it under Not Verified with the reason. An unverified claim stated as verified is the single most damaging thing a summary can do.\n\n### 6. Not Verified \u002F Known Gaps\n\nBe specific and unflinching.\n\n- What was not tested and why (no test exists, no fixture, requires a live service).\n- Assumptions made that were not confirmed.\n- Behavior you changed that has no test coverage.\n- Anything you are uncertain about.\n\n### 7. Follow-Up\n\nConcrete, ordered next steps. Each names what to do and why it matters.\n\n1. **Add a regression test** for the expiry boundary at `src\u002Fauth\u002Fsession.ts:88` — the fix is untested, so it can silently regress.\n2. **Migrate the two callers** of the deprecated helper — they still use the old signature.\n3. **Pre-existing:** `tsc` reports 2 errors in `src\u002Flegacy\u002F*` — unrelated to this session, still open.\n\nSeparate **blocking** from **optional**. Do not pad this list with speculative work.\n\n## Output Rules\n\n- **Lead with the outcome.** The first line answers \"did it work\".\n- **Use tables for anything enumerable.** Actions, files, verification results.\n- **Cite locations.** `src\u002Fauth\u002Fsession.ts:88`, not \"the session file\".\n- **Quote exact errors and exact command output.** Paraphrasing an error loses the string the reader needs to search for.\n- **Distinguish done from planned from blocked.** Use explicit labels.\n- **Be concise but complete.** Cut adjectives, not facts. No \"successfully\", no \"carefully\", no \"it's worth noting\".\n- **Keep it readable.** A reader should be able to skim the headings and tables and get the shape in ten seconds, then read one section for detail.\n- **No emoji, no decorative formatting.** This is a record.\n\n## Handling an Empty or Trivial Session\n\nIf the session was a question, a review with no edits, or an exploration, do not manufacture sections. Report what happened in the honest shape:\n\n```markdown\n## Overview\n\nReviewed the proposed caching layer. No code changed — the design has a\ncorrectness problem that should be resolved first.\n\n## Findings\n\n| #   | Finding                                                 | Severity | Location             |\n| --- | ------------------------------------------------------- | -------- | -------------------- |\n| 1   | Cache key omits the tenant id, so tenants share entries | Critical | src\u002Fcache\u002Fkeys.ts:14 |\n\n## Actions Taken\n\nRead-only. No files modified, no commands run beyond search.\n\n## Recommendation\n\nFix the cache key before implementing. See finding 1.\n```\n\nA short accurate summary beats a long padded one.\n\n## Handoff Form\n\nWhen the user wants to hand off to another session or teammate, add a section that a fresh agent can act on without reading the transcript:\n\n```markdown\n## Handoff\n\n**State** Feature implemented and tested; not yet committed.\n**Branch** `feat\u002Fsession-expiry` — 3 commits ahead of `main`\n**Entry point** `src\u002Fauth\u002Fsession.ts` — `refreshSession()` is the changed function\n**How to verify** `bun test src\u002Fauth && bun run dev`, then load `\u002Flogin`\n**Open** Two callers still use the old signature — see Follow-Up 2.\n**Do not** Revert the `!` on the schema change; it is intentional.\n```\n\n## Common Mistakes\n\n| Mistake                                       | Why It Breaks                                                 | Correct Approach                               |\n| --------------------------------------------- | ------------------------------------------------------------- | ---------------------------------------------- |\n| Claiming tests passed without running them    | Destroys trust the moment it is checked                       | Run them, or list under Not Verified           |\n| Mixing pre-existing defects with your changes | Makes the diff look worse and hides the user's remaining work | Separate \"pre-existing\" explicitly             |\n| Listing files without saying what changed     | Unreadable; the user must open every file                     | One line per file describing the change        |\n| Paraphrasing an error message                 | The reader cannot search for it                               | Quote it exactly                               |\n| Reporting a plan as done                      | The next session builds on something that does not exist      | Label done \u002F planned \u002F blocked                 |\n| Omitting the failed attempt                   | The next session repeats it                                   | Record dead ends and why they failed           |\n| Padding with \"successfully\" and \"carefully\"   | Buries the facts                                              | Cut the adverbs                                |\n| No verification section                       | The reader cannot tell whether anything was checked           | Always state what was run and what it returned |\n| Writing prose where a table belongs           | Slow to scan                                                  | Tables for enumerables                         |\n| Burying the outcome at the end                | The reader must read everything to learn whether it worked    | Lead with the outcome                          |\n| Inventing follow-up work                      | Wastes the reader's attention                                 | Only real, actionable next steps               |\n| Manufacturing sections for a trivial session  | Signals padding and undermines the whole report               | Report the honest shape, however short         |\n",{"name":5,"description":7,"allowed-tools":24},"Read Grep Glob Bash","main","42203fde5eb692ba254e058168ee1af75855fcb4","skills\u002Fsummarize",0,"https:\u002F\u002Fgithub.com\u002FMarvellbrazil\u002Fmy-agentic-skills","skills.marvellofaisal.me","https:\u002F\u002Fgithub.com\u002FMarvellbrazil","marvellofaisal.me","Software Engineering Student | Backend & API Developer | Tech Enthusiast | Homelabber","2026-10-23 22:23:52",{"source":8,"skillName":5,"commands":36,"prompt":46,"zipAvailable":47},[37,40,43],{"tool":38,"command":39},"npx","npx skills add Marvellbrazil\u002Fmy-agentic-skills --skill summarize",{"tool":41,"command":42},"bunx","bunx skills add Marvellbrazil\u002Fmy-agentic-skills --skill summarize",{"tool":44,"command":45},"pnpm","pnpm dlx skills add Marvellbrazil\u002Fmy-agentic-skills --skill summarize","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FMarvellbrazil\u002Fmy-agentic-skills\u002Fblob\u002Fmain\u002Fskills\u002Fsummarize\u002FSKILL.md",true,[],[50,57,64,71,78,85],{"skillNo":51,"name":52,"nameZh":6,"description":53,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":54,"categories":55,"keywords":56,"publishedAt":19},"01M7DDQP2F4E42AMTGY0VCJ6G2","writing-guidelines","Review docs\u002Fprose for Writing Guidelines compliance. Use when asked to \"review my docs\", \"check writing style\", \"audit prose\", \"review docs voice and tone\", or \"check this page against the writing handbook\".","https:\u002F\u002Fgithub.com\u002FMarvellbrazil\u002Fmy-agentic-skills\u002Fblob\u002Fmain\u002Fskills\u002Fwriting-guidelines\u002FSKILL.md",[],[],{"skillNo":58,"name":59,"nameZh":6,"description":60,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":61,"categories":62,"keywords":63,"publishedAt":19},"01M7DDQM00XGSGT8V797C89R2E","writing-for-agents","Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.","https:\u002F\u002Fgithub.com\u002FMarvellbrazil\u002Fmy-agentic-skills\u002Fblob\u002Fmain\u002Fskills\u002Fwriting-for-agents\u002FSKILL.md",[],[],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":19},"01M7DDQEF1HP9CMH88HMN9MCBA","wrangler","Cloudflare Workers CLI for deploying, developing, and managing Workers, KV, R2, D1, Vectorize, Hyperdrive, Workers AI, Containers, Queues, Workflows, Pipelines, and Secrets Store. Load before running wrangler commands to ensure correct syntax and best practices. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.","https:\u002F\u002Fgithub.com\u002FMarvellbrazil\u002Fmy-agentic-skills\u002Fblob\u002Fmain\u002Fskills\u002Fwrangler\u002FSKILL.md",[],[],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":19},"01M7DDQA32ZAG7J4PMRXRSQ3NQ","workers-best-practices","Reviews and authors Cloudflare Workers code against production best practices. Load when writing new Workers, reviewing Worker code, configuring wrangler.jsonc, or checking for common Workers anti-patterns (streaming, floating promises, global state, secrets, bindings, observability). Biases towards retrieval from Cloudflare docs over pre-trained knowledge.","https:\u002F\u002Fgithub.com\u002FMarvellbrazil\u002Fmy-agentic-skills\u002Fblob\u002Fmain\u002Fskills\u002Fworkers-best-practices\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},"01M7DDQ5482QSC0FC4NX107FVY","web-perf","Analyzes web performance using Chrome DevTools MCP. Measures Core Web Vitals (LCP, INP, CLS) and supplementary metrics (FCP, TBT, Speed Index), identifies render-blocking resources, network dependency chains, layout shifts, caching issues, and accessibility gaps. Use when asked to audit, profile, debug, or optimize page load performance, Lighthouse scores, or site speed. Biases towards retrieval from current documentation over pre-trained knowledge.","https:\u002F\u002Fgithub.com\u002FMarvellbrazil\u002Fmy-agentic-skills\u002Fblob\u002Fmain\u002Fskills\u002Fweb-perf\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},"01M7DDQ1GZ7Z2Y67460SJJEMC0","using-agent-skills","Discovers and invokes agent skills. Use when starting a session, or when you need to decide which skill or workflow applies to the piece of work at hand. This is the meta-skill that governs how all other skills are discovered and invoked.","https:\u002F\u002Fgithub.com\u002FMarvellbrazil\u002Fmy-agentic-skills\u002Fblob\u002Fmain\u002Fskills\u002Fusing-agent-skills\u002FSKILL.md",[],[]]