[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77MK8HCWP92VTTM3BGZKX5X":3,"skill-same:01M77MK8HCWP92VTTM3BGZKX5X":48},{"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":29,"ownerHtmlUrl":30,"ownerBlogUrl":31,"ownerDescription":32,"updatedAt":33,"install":34,"resources":47},"01M77MK8HCWP92VTTM3BGZKX5X","effective-agent-skills",null,"Write, review, and debug agent skills. Use when creating or editing SKILL.md files, improving skill structure, or diagnosing invocation and execution problems.","davidondrej\u002Fskills","davidondrej","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F131768515?v=4","01M77MHARFKYVNT9FV22807T8F","David Ondrej","01M77MHASHNDV507F9NTVKR2CY",4310,"MIT","https:\u002F\u002Fgithub.com\u002Fdavidondrej\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Feffective-agent-skills\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: effective-agent-skills\ndescription: 'Write, review, and debug agent skills. Use when creating or editing SKILL.md files, improving skill structure, or diagnosing invocation and execution problems.'\n---\n\n# Effective Agent Skills\n\n---\n\n## 1. What agent skills are\n\nAn Agent Skill is a folder containing a `SKILL.md` file (YAML frontmatter + markdown instructions), plus optional subfolders for scripts, references, and assets that the agent loads on demand.\n\n```\nmy-skill\u002F\n├── SKILL.md          # Required: metadata + instructions\n├── scripts\u002F          # Optional: executable code (CLIs, validators, helpers)\n├── references\u002F       # Optional: detailed docs loaded only when needed\n└── assets\u002F           # Optional: templates, fonts, static files\n```\n\nAgent Skills (agentskills.io) is an open standard. The folder and `SKILL.md` format are portable; optional behavior such as invocation control can be client-specific.\n\n---\n\n## 2. Why use skills\n\nSkills package procedural knowledge and context for reuse:\n\n- **Context efficiency** — instructions load only when relevant\n- **Repeatability** — multi-step procedures become auditable workflows\n- **Composability** — multiple skills combine at runtime per task\n- **Portability** — same files work across vendors and surfaces\n\n---\n\n## 3. How they work — progressive disclosure\n\nThree levels of loading:\n\n**Level 1 — Discovery (~100 tokens per skill, always in context):**\nThe agent sees `name` + `description` first to decide whether the skill applies.\n\n**Level 2 — Activation (\u003C5,000 tokens, loaded on match):**\nWhen the request matches, the agent reads the full `SKILL.md` body.\n\n**Level 3 — Execution (unbounded, on demand):**\nThe agent reads references (`references\u002Ffoo.md`) or runs scripts (`scripts\u002Fvalidate.py`) as needed. Running a script need not load its source into context.\n\nBundled files consume context only when their contents are loaded.\n\n---\n\n## 4. SKILL.md anatomy\n\n```markdown\n---\nname: skill-name\ndescription: What this skill does AND when to use it. Include trigger phrases the user will say.\n---\n\n# Skill Name\n\n## Quick start\n[Minimal working example]\n\n## Workflow\n[Step-by-step procedure with checklists]\n\n## Output format\n[What the user\u002Fagent should expect back]\n\n## Advanced\n[Link to references\u002F for rarely-needed detail]\n```\n\nFrontmatter constraints:\n- `name` is lowercase, hyphens only, 1–64 chars, **exactly matches the parent folder name**\n- Avoid `\u003C` and `>` in frontmatter (they can inject into the system prompt)\n- Invalid YAML silently prevents loading\n- **Never put `: ` (colon + space) inside an unquoted `description`** — strict YAML parsers (e.g. Pi's) reject it as a nested mapping (\"Nested mappings are not allowed in compact mappings\"), even though lenient parsers (Claude Code) accept it. If the text needs a mid-sentence colon, single-quote the whole value and double any inner apostrophes: `description: 'Differentiator: finds gaps in David''s knowledge.'`\n\n### Manual-only invocation is client-specific\n\n`disable-model-invocation: true` is **not** part of the core Agent Skills specification. It is a client extension supported by Claude Code and VS Code\u002FCopilot. In those clients, put it in `SKILL.md` frontmatter to prevent automatic invocation while keeping explicit invocation available.\n\nOpenAI Codex uses a separate file at `agents\u002Fopenai.yaml` inside the skill:\n\n```yaml\npolicy:\n  allow_implicit_invocation: false\n```\n\nFor a manual-only skill shared across Claude Code, VS Code\u002FCopilot, and Codex, include both configurations. Never assume a client-specific frontmatter field works in every Agent Skills implementation; verify each target client's documentation and test implicit invocation in each runtime.\n\n---\n\n## 5. Two design philosophies\n\n### Pattern A — Capability primitives (tool wrappers)\nThe skill is a thin wrapper over a deterministic CLI or script. Logic lives in code. SKILL.md teaches the agent how to invoke it.\n\n- **Adds**: new capabilities (search, email, browser, API access)\n- **Reliability via**: shell tools, not prompts\n- **Typical length**: 30–80 lines, mostly command examples\n- **Use when**: the bottleneck is \"the agent can't do X\"\n\n### Pattern B — Process primitives (cognitive disciplines)\nThe skill encodes a methodology the agent should follow. Pure prompt engineering — no scripts needed.\n\n- **Adds**: structured workflows (TDD, code review, design alignment, debugging loops)\n- **Reliability via**: explicit procedure, checklists, validation loops\n- **Use when**: the bottleneck is \"the agent's output quality or process is bad\"\n\n---\n\n## 6. How to write effective skills — do this\n\n### Write descriptions for skill selection\nThe agent sees the name and description before loading the body. Describe **what the skill does + concrete tasks that should trigger it**.\n\n- Aim for one or two short sentences. The 1,024-character limit is a ceiling, not a target.\n- Put the main use case and important terms first; hosts may shorten descriptions.\n- Name tasks, inputs, or file types users actually mention. Match intent, not just keywords.\n- Add a boundary only when it prevents confusion with related skills.\n- Keep workflow steps in the body. Avoid vague claims, catchalls, and lists of synonyms.\n\nPattern: `\"[Capability]. Use when [specific tasks or situations].\"`\n\nSources: [Agent Skills](https:\u002F\u002Fagentskills.io\u002Fskill-creation\u002Foptimizing-descriptions) · [OpenAI](https:\u002F\u002Fdevelopers.openai.com\u002Fcodex\u002Fbuild-skills).\n\n### Keep SKILL.md lean\n- Beyond a certain length, you're usually encoding logic that should be in a script or referenced file\n\n### Bash-first, prose-second\nPrefer concrete command examples with inline comments to lengthy prose.\n\n### Push determinism into code\nAnything fragile, repetitive, or where variation is a bug → script. Use markdown only for tasks requiring judgment.\n\n### Match strictness to task fragility (degrees of freedom)\nScale instruction rigidity to how costly a wrong move is:\n- **Loose natural-language heuristics** when many approaches are valid (e.g. code review).\n- **Pseudocode or templates** when there's a preferred pattern but variation is acceptable (e.g. report format).\n- **Exact scripts and strict step lists** when the workflow is fragile, error-prone, or consistency-critical (e.g. migrations, document patching).\n\n### Build validation loops\nState a verify → fix → re-verify loop explicitly.\n\n- Document skills: visual QA pass before delivery\n- Code skills: tests pass + zero type errors before completion\n- Data skills: schema validation before output\n\n### State-check before action\nDon't assume setup is done. Instruct the agent to verify state, then branch:\n```\nFirst check if X is configured: [command]\nIf not, walk the user through setup: [steps]\n```\n\n### Just-in-time loading with explicit pointers\nTell the agent exactly when to read each referenced file:\n```\nFor standard cases, follow the steps below.\nFor [specific edge case], read references\u002Fedge-cases.md first.\n```\n\n### Keep references one level deep\nLink references directly from SKILL.md; nested chains risk partial reads and missed instructions. Add a table of contents to references longer than 100 lines.\n\n### Document output formats\nShow structured output examples so other tools can parse them reliably.\n\n### Defer to --help for completeness\nShow common operations in SKILL.md; use `tool --help` for the rest.\n\n### Compose primitives, don't bundle workflows\nKeep each skill to one capability or discipline; compose focused skills for larger workflows.\n\n### Cite established principles when applicable\nName the source of established methods such as TDD, DDD, or red-green-refactor so agents and users can verify the intended approach.\n\n### Persistent artifacts for cross-session memory\nSkills can keep durable context in repo files (CONTEXT.md, ADRs, decision logs) for future sessions.\n\n---\n\n## 7. What not to do — anti-patterns\n\n### Don't re-teach what the model already knows\nProvide context the model lacks. Skip basic Python or Git tutorials; make every paragraph earn its place.\n\n### Don't include human-facing docs\nNo README.md, no CHANGELOG.md, no INSTALLATION_GUIDE.md inside the skill folder. Skills are for agents.\n\n### Don't write vague descriptions\n- Bad: \"A helpful skill for documents\"\n- Good: \"Fill PDF form fields, extract form data, flatten completed PDFs. Use when the user mentions PDF forms, fillable forms, or programmatic field population.\"\n\n### Don't bundle library code\nIf you need a parsing library, install via npm\u002Fpip. Don't paste source into the skill.\n\n### Don't write monolithic mega-skills\nSplit skills that bundle design, planning, implementation, testing, and deployment.\n\n### Don't assume the agent will infer\nBe explicit about every step that matters.\n- Bad: \"Then deploy it.\"\n- Good: \"Run `npm run deploy:staging` and wait for HTTP 200 from \u002Fhealthz before reporting success.\"\n\n### Don't write style-only variants\nA skill that just changes tone or formatting belongs in user preferences or a system prompt, not a skill.\n\n### Don't ignore failure modes\nFor each fallible step, describe how to recognize failure and what to do.\n\n### Don't include time-sensitive information\n\"As of Q4 2024...\" rots fast. Fetch live data via script or omit.\n\n### Don't use absolute paths\nAlways relative. Forward slashes regardless of OS. Use runtime placeholders for skill-directory references.\n\n### Don't trust unfamiliar skills\nSkills can run code, steer behavior, and leak data. Audit scripts, references, names, and access scope before use; follow the security checklist below.\n\n---\n\n## 8. Authoring workflow\n\n1. **Identify the gap.** Run your agent on real tasks. Where does it consistently fail or need re-prompting? That's a skill candidate.\n2. **Decide the pattern.** Capability primitive (need new tools) or process primitive (need better methodology)?\n3. **Draft the description first.** What + when; add a boundary only if it prevents likely confusion.\n4. **Write the smallest body that works.** Add only when testing reveals gaps.\n5. **Move detail to references\u002F once SKILL.md grows too long.**\n6. **Test triggering.** Use realistic requests and near-misses without naming the skill. Verify that its body actually loads.\n7. **Test execution.** Invoke explicitly. If output is wrong, fix the body.\n8. **Adversarial test.** Have another LLM ask: \"What edge cases break this skill?\" Patch the gaps.\n9. **Version control.** Treat skills as code. Tag, branch, review.\n\n---\n\n## 9. Testing and debugging\n\n- **Verify actual activation.** Inspect whether the runtime loaded `SKILL.md`; valid YAML or an agent's self-report is not proof.\n- **Wrong or missed activation.** Check discovery and invocation settings, then adjust description scope and trigger wording.\n- **Execution fails → body problem.** Add explicit steps, examples, or validation.\n- **Use fresh sessions for trigger tests.** Some clients snapshot skills at startup.\n- **Test against the weakest model you'll deploy on.** Stronger models forgive vague skills; weaker models expose them.\n- **Test both directions.** Include realistic requests and near-misses sharing keywords that should not activate the skill. Repeat ambiguous cases and test new prompts to avoid overfitting.\n\n---\n\n## 10. Composition\n\nAgents can combine skills for one task:\n\n- **One skill = one concern.** Resist bundling.\n- **Define interfaces between skills.** If skill A produces artifacts that skill B consumes, document the shape.\n- **Share repo-level context.** Files such as AGENTS.md, CONTEXT.md, or settings.json can coordinate multiple skills without explicit handoffs.\n- **Connect skills into useful workflows** such as align → spec → build → verify → refactor.\n\n---\n\n## 11. Security checklist\n\nBefore installing any third-party skill:\n\n- Read every file in the folder\n- Audit `scripts\u002F` for outbound network calls, file access outside expected scope, command execution\n- Check references for prompt injection (\"ignore previous instructions...\")\n- Verify the skill name isn't typosquatting a popular one\n- Run in a sandboxed environment first\n- Pin to a specific version\u002Fcommit, not `latest`\n\n---\n\n## 12. Ship checklist\n\nBefore publishing a skill:\n\n- [ ] Frontmatter `name` matches folder name\n- [ ] Description is concise, with capability and concrete triggers first\n- [ ] Boundaries distinguish related skills where needed\n- [ ] No human-facing docs inside the skill folder\n- [ ] No time-sensitive information\n- [ ] Relative paths only\n- [ ] State-check before action where applicable\n- [ ] Validation loop documented\n- [ ] Output format documented if relevant\n- [ ] Tested with weak and strong models\n- [ ] Tested for both correct triggering and correct execution\n- [ ] Skill does one thing\n- [ ] Composes cleanly with related skills\n- [ ] Version controlled\n","# Effective Agent Skills\n\n---\n\n## 1. What agent skills are\n\nAn Agent Skill is a folder containing a `SKILL.md` file (YAML frontmatter + markdown instructions), plus optional subfolders for scripts, references, and assets that the agent loads on demand.\n\n```\nmy-skill\u002F\n├── SKILL.md          # Required: metadata + instructions\n├── scripts\u002F          # Optional: executable code (CLIs, validators, helpers)\n├── references\u002F       # Optional: detailed docs loaded only when needed\n└── assets\u002F           # Optional: templates, fonts, static files\n```\n\nAgent Skills (agentskills.io) is an open standard. The folder and `SKILL.md` format are portable; optional behavior such as invocation control can be client-specific.\n\n---\n\n## 2. Why use skills\n\nSkills package procedural knowledge and context for reuse:\n\n- **Context efficiency** — instructions load only when relevant\n- **Repeatability** — multi-step procedures become auditable workflows\n- **Composability** — multiple skills combine at runtime per task\n- **Portability** — same files work across vendors and surfaces\n\n---\n\n## 3. How they work — progressive disclosure\n\nThree levels of loading:\n\n**Level 1 — Discovery (~100 tokens per skill, always in context):**\nThe agent sees `name` + `description` first to decide whether the skill applies.\n\n**Level 2 — Activation (\u003C5,000 tokens, loaded on match):**\nWhen the request matches, the agent reads the full `SKILL.md` body.\n\n**Level 3 — Execution (unbounded, on demand):**\nThe agent reads references (`references\u002Ffoo.md`) or runs scripts (`scripts\u002Fvalidate.py`) as needed. Running a script need not load its source into context.\n\nBundled files consume context only when their contents are loaded.\n\n---\n\n## 4. SKILL.md anatomy\n\n```markdown\n---\nname: skill-name\ndescription: What this skill does AND when to use it. Include trigger phrases the user will say.\n---\n\n# Skill Name\n\n## Quick start\n[Minimal working example]\n\n## Workflow\n[Step-by-step procedure with checklists]\n\n## Output format\n[What the user\u002Fagent should expect back]\n\n## Advanced\n[Link to references\u002F for rarely-needed detail]\n```\n\nFrontmatter constraints:\n- `name` is lowercase, hyphens only, 1–64 chars, **exactly matches the parent folder name**\n- Avoid `\u003C` and `>` in frontmatter (they can inject into the system prompt)\n- Invalid YAML silently prevents loading\n- **Never put `: ` (colon + space) inside an unquoted `description`** — strict YAML parsers (e.g. Pi's) reject it as a nested mapping (\"Nested mappings are not allowed in compact mappings\"), even though lenient parsers (Claude Code) accept it. If the text needs a mid-sentence colon, single-quote the whole value and double any inner apostrophes: `description: 'Differentiator: finds gaps in David''s knowledge.'`\n\n### Manual-only invocation is client-specific\n\n`disable-model-invocation: true` is **not** part of the core Agent Skills specification. It is a client extension supported by Claude Code and VS Code\u002FCopilot. In those clients, put it in `SKILL.md` frontmatter to prevent automatic invocation while keeping explicit invocation available.\n\nOpenAI Codex uses a separate file at `agents\u002Fopenai.yaml` inside the skill:\n\n```yaml\npolicy:\n  allow_implicit_invocation: false\n```\n\nFor a manual-only skill shared across Claude Code, VS Code\u002FCopilot, and Codex, include both configurations. Never assume a client-specific frontmatter field works in every Agent Skills implementation; verify each target client's documentation and test implicit invocation in each runtime.\n\n---\n\n## 5. Two design philosophies\n\n### Pattern A — Capability primitives (tool wrappers)\nThe skill is a thin wrapper over a deterministic CLI or script. Logic lives in code. SKILL.md teaches the agent how to invoke it.\n\n- **Adds**: new capabilities (search, email, browser, API access)\n- **Reliability via**: shell tools, not prompts\n- **Typical length**: 30–80 lines, mostly command examples\n- **Use when**: the bottleneck is \"the agent can't do X\"\n\n### Pattern B — Process primitives (cognitive disciplines)\nThe skill encodes a methodology the agent should follow. Pure prompt engineering — no scripts needed.\n\n- **Adds**: structured workflows (TDD, code review, design alignment, debugging loops)\n- **Reliability via**: explicit procedure, checklists, validation loops\n- **Use when**: the bottleneck is \"the agent's output quality or process is bad\"\n\n---\n\n## 6. How to write effective skills — do this\n\n### Write descriptions for skill selection\nThe agent sees the name and description before loading the body. Describe **what the skill does + concrete tasks that should trigger it**.\n\n- Aim for one or two short sentences. The 1,024-character limit is a ceiling, not a target.\n- Put the main use case and important terms first; hosts may shorten descriptions.\n- Name tasks, inputs, or file types users actually mention. Match intent, not just keywords.\n- Add a boundary only when it prevents confusion with related skills.\n- Keep workflow steps in the body. Avoid vague claims, catchalls, and lists of synonyms.\n\nPattern: `\"[Capability]. Use when [specific tasks or situations].\"`\n\nSources: [Agent Skills](https:\u002F\u002Fagentskills.io\u002Fskill-creation\u002Foptimizing-descriptions) · [OpenAI](https:\u002F\u002Fdevelopers.openai.com\u002Fcodex\u002Fbuild-skills).\n\n### Keep SKILL.md lean\n- Beyond a certain length, you're usually encoding logic that should be in a script or referenced file\n\n### Bash-first, prose-second\nPrefer concrete command examples with inline comments to lengthy prose.\n\n### Push determinism into code\nAnything fragile, repetitive, or where variation is a bug → script. Use markdown only for tasks requiring judgment.\n\n### Match strictness to task fragility (degrees of freedom)\nScale instruction rigidity to how costly a wrong move is:\n- **Loose natural-language heuristics** when many approaches are valid (e.g. code review).\n- **Pseudocode or templates** when there's a preferred pattern but variation is acceptable (e.g. report format).\n- **Exact scripts and strict step lists** when the workflow is fragile, error-prone, or consistency-critical (e.g. migrations, document patching).\n\n### Build validation loops\nState a verify → fix → re-verify loop explicitly.\n\n- Document skills: visual QA pass before delivery\n- Code skills: tests pass + zero type errors before completion\n- Data skills: schema validation before output\n\n### State-check before action\nDon't assume setup is done. Instruct the agent to verify state, then branch:\n```\nFirst check if X is configured: [command]\nIf not, walk the user through setup: [steps]\n```\n\n### Just-in-time loading with explicit pointers\nTell the agent exactly when to read each referenced file:\n```\nFor standard cases, follow the steps below.\nFor [specific edge case], read references\u002Fedge-cases.md first.\n```\n\n### Keep references one level deep\nLink references directly from SKILL.md; nested chains risk partial reads and missed instructions. Add a table of contents to references longer than 100 lines.\n\n### Document output formats\nShow structured output examples so other tools can parse them reliably.\n\n### Defer to --help for completeness\nShow common operations in SKILL.md; use `tool --help` for the rest.\n\n### Compose primitives, don't bundle workflows\nKeep each skill to one capability or discipline; compose focused skills for larger workflows.\n\n### Cite established principles when applicable\nName the source of established methods such as TDD, DDD, or red-green-refactor so agents and users can verify the intended approach.\n\n### Persistent artifacts for cross-session memory\nSkills can keep durable context in repo files (CONTEXT.md, ADRs, decision logs) for future sessions.\n\n---\n\n## 7. What not to do — anti-patterns\n\n### Don't re-teach what the model already knows\nProvide context the model lacks. Skip basic Python or Git tutorials; make every paragraph earn its place.\n\n### Don't include human-facing docs\nNo README.md, no CHANGELOG.md, no INSTALLATION_GUIDE.md inside the skill folder. Skills are for agents.\n\n### Don't write vague descriptions\n- Bad: \"A helpful skill for documents\"\n- Good: \"Fill PDF form fields, extract form data, flatten completed PDFs. Use when the user mentions PDF forms, fillable forms, or programmatic field population.\"\n\n### Don't bundle library code\nIf you need a parsing library, install via npm\u002Fpip. Don't paste source into the skill.\n\n### Don't write monolithic mega-skills\nSplit skills that bundle design, planning, implementation, testing, and deployment.\n\n### Don't assume the agent will infer\nBe explicit about every step that matters.\n- Bad: \"Then deploy it.\"\n- Good: \"Run `npm run deploy:staging` and wait for HTTP 200 from \u002Fhealthz before reporting success.\"\n\n### Don't write style-only variants\nA skill that just changes tone or formatting belongs in user preferences or a system prompt, not a skill.\n\n### Don't ignore failure modes\nFor each fallible step, describe how to recognize failure and what to do.\n\n### Don't include time-sensitive information\n\"As of Q4 2024...\" rots fast. Fetch live data via script or omit.\n\n### Don't use absolute paths\nAlways relative. Forward slashes regardless of OS. Use runtime placeholders for skill-directory references.\n\n### Don't trust unfamiliar skills\nSkills can run code, steer behavior, and leak data. Audit scripts, references, names, and access scope before use; follow the security checklist below.\n\n---\n\n## 8. Authoring workflow\n\n1. **Identify the gap.** Run your agent on real tasks. Where does it consistently fail or need re-prompting? That's a skill candidate.\n2. **Decide the pattern.** Capability primitive (need new tools) or process primitive (need better methodology)?\n3. **Draft the description first.** What + when; add a boundary only if it prevents likely confusion.\n4. **Write the smallest body that works.** Add only when testing reveals gaps.\n5. **Move detail to references\u002F once SKILL.md grows too long.**\n6. **Test triggering.** Use realistic requests and near-misses without naming the skill. Verify that its body actually loads.\n7. **Test execution.** Invoke explicitly. If output is wrong, fix the body.\n8. **Adversarial test.** Have another LLM ask: \"What edge cases break this skill?\" Patch the gaps.\n9. **Version control.** Treat skills as code. Tag, branch, review.\n\n---\n\n## 9. Testing and debugging\n\n- **Verify actual activation.** Inspect whether the runtime loaded `SKILL.md`; valid YAML or an agent's self-report is not proof.\n- **Wrong or missed activation.** Check discovery and invocation settings, then adjust description scope and trigger wording.\n- **Execution fails → body problem.** Add explicit steps, examples, or validation.\n- **Use fresh sessions for trigger tests.** Some clients snapshot skills at startup.\n- **Test against the weakest model you'll deploy on.** Stronger models forgive vague skills; weaker models expose them.\n- **Test both directions.** Include realistic requests and near-misses sharing keywords that should not activate the skill. Repeat ambiguous cases and test new prompts to avoid overfitting.\n\n---\n\n## 10. Composition\n\nAgents can combine skills for one task:\n\n- **One skill = one concern.** Resist bundling.\n- **Define interfaces between skills.** If skill A produces artifacts that skill B consumes, document the shape.\n- **Share repo-level context.** Files such as AGENTS.md, CONTEXT.md, or settings.json can coordinate multiple skills without explicit handoffs.\n- **Connect skills into useful workflows** such as align → spec → build → verify → refactor.\n\n---\n\n## 11. Security checklist\n\nBefore installing any third-party skill:\n\n- Read every file in the folder\n- Audit `scripts\u002F` for outbound network calls, file access outside expected scope, command execution\n- Check references for prompt injection (\"ignore previous instructions...\")\n- Verify the skill name isn't typosquatting a popular one\n- Run in a sandboxed environment first\n- Pin to a specific version\u002Fcommit, not `latest`\n\n---\n\n## 12. Ship checklist\n\nBefore publishing a skill:\n\n- [ ] Frontmatter `name` matches folder name\n- [ ] Description is concise, with capability and concrete triggers first\n- [ ] Boundaries distinguish related skills where needed\n- [ ] No human-facing docs inside the skill folder\n- [ ] No time-sensitive information\n- [ ] Relative paths only\n- [ ] State-check before action where applicable\n- [ ] Validation loop documented\n- [ ] Output format documented if relevant\n- [ ] Tested with weak and strong models\n- [ ] Tested for both correct triggering and correct execution\n- [ ] Skill does one thing\n- [ ] Composes cleanly with related skills\n- [ ] Version controlled\n",{"name":5,"description":7},"main","a9d4ad810cf3c303fde23bdcd5fc86df7c57daf3","skills\u002Feffective-agent-skills",626,"https:\u002F\u002Fgithub.com\u002Fdavidondrej\u002Fskills","https:\u002F\u002Fwww.cloudroom.dev","https:\u002F\u002Fgithub.com\u002Fdavidondrej","https:\u002F\u002Fwww.cloudroom.dev\u002F","founder of Cloudroom","2026-11-14 10:00:36",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add davidondrej\u002Fskills --skill effective-agent-skills",{"tool":40,"command":41},"bunx","bunx skills add davidondrej\u002Fskills --skill effective-agent-skills",{"tool":43,"command":44},"pnpm","pnpm dlx skills add davidondrej\u002Fskills --skill effective-agent-skills","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fdavidondrej\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Feffective-agent-skills\u002FSKILL.md",true,[],[49,56,63,70,77,84],{"skillNo":50,"name":51,"nameZh":6,"description":52,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":53,"categories":54,"keywords":55,"publishedAt":19},"01M77MPMR6DE13EZFSMY76S6YB","varied-search","Research a topic across the web, GitHub, and X\u002FTwitter with DeepAPI and produce a concise Markdown report. Use for varied-search or requests to compare web coverage, relevant repositories, and social discussion.","https:\u002F\u002Fgithub.com\u002Fdavidondrej\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fvaried-search\u002FSKILL.md",[],[],{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":19},"01M77MPG5F9H2JBW4VFHBY1VSM","total-review","Run five independent max-effort reviews (Fable 5.1, Opus 5.5, GPT-6 Astra, GPT-6.1 Sol, Muse Wonder), merge their findings, and fix only what the user approves. Use for \u002Ftotal-review, or when the user or another agent asks for a total review.","https:\u002F\u002Fgithub.com\u002Fdavidondrej\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ftotal-review\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},"01M77MP8XZJ42ZJZQV8C76B353","stop-overthinking","Manually-invoked skill that stops overthinking and forces a short, practical decision. Use only when the user explicitly invokes stop-overthinking.","https:\u002F\u002Fgithub.com\u002Fdavidondrej\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fstop-overthinking\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":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":19},"01M77MP5EGQSNF1VS9SY8CK60Q","state","Manually-invoked skill that recaps what the current thread is doing and how far along it is. Use when the user says \"state\", \"where are we\", or \"what % are we done\".","https:\u002F\u002Fgithub.com\u002Fdavidondrej\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fstate\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M77MP2H479SWAP7687RAVG7T","setup-help","Guide setup one step at a time and show what remains. Use only when the user explicitly asks for it by name.","https:\u002F\u002Fgithub.com\u002Fdavidondrej\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fsetup-help\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"01M77MNZV9X8NPC9JZMWP8WAF8","self-archive","Archive the current Cloudroom thread and release its runtime. Use only when the user explicitly asks to self-archive, archive yourself, or archive this thread.","https:\u002F\u002Fgithub.com\u002Fdavidondrej\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fself-archive\u002FSKILL.md",[],[]]