Agent workflow
Context, delegation, and building your own skills and tools.
Refine agent workflow by task, stack and access
Skill creator
Creates, tests and tunes skills, including evals and trigger checks.
What it can touch: Writes docs · Runs commands · Subagents
Automated scan recorded · evidence and limits
- Automated scan: Checked 16 Nov 2026. Checks SKILL.md patterns and frontmatter; does not run the skill.
- Source revision: 1780c5e5a552 (opens in a new tab). The install command targets this commit. Only SKILL.md was scanned.
- Human reading: No full human-reading date recorded.
- Runtime evidence: No runtime-test evidence recorded here.
A review is not a security audit or a guarantee.
Commands target the repository commits recorded with the automated scans. Scans cover only SKILL.md, not referenced files or runtime behavior. What the review covers.
434Kinstalls+810 today
npx skills@latest add https://github.com/anthropics/skills/tree/1780c5e5a552fd4d1c9d6a7b0cab26b0c2bef064 --skill skill-creatorSubagent-driven development
Executes implementation plans with fresh agents, per-task reviews, and a durable progress ledger.
What it can touch: Edits code · Writes docs · Runs commands · Uses git · Subagents
Automated scan recorded · evidence and limits
- Automated scan: Checked 16 Nov 2026. Checks SKILL.md patterns and frontmatter; does not run the skill.
- Source revision: 22f0b463e7a5 (opens in a new tab). The install command targets this commit. Only SKILL.md was scanned.
- Human reading: No full human-reading date recorded.
- Runtime evidence: No runtime-test evidence recorded here.
A review is not a security audit or a guarantee.
Commands target the repository commits recorded with the automated scans. Scans cover only SKILL.md, not referenced files or runtime behavior. What the review covers.
258Kinstalls+1.3K today
npx skills@latest add https://github.com/obra/superpowers/tree/22f0b463e7a5e579904dd6211a520321035526f7 --skill subagent-driven-developmentDispatching parallel agents
Splits independent problems across parallel subagents and merges the results.
What it can touch: Subagents
Automated scan recorded · evidence and limits
- Automated scan: Checked 16 Nov 2026. Checks SKILL.md patterns and frontmatter; does not run the skill.
- Source revision: 22f0b463e7a5 (opens in a new tab). The install command targets this commit. Only SKILL.md was scanned.
- Human reading: No full human-reading date recorded.
- Runtime evidence: No runtime-test evidence recorded here.
A review is not a security audit or a guarantee.
Commands target the repository commits recorded with the automated scans. Scans cover only SKILL.md, not referenced files or runtime behavior. What the review covers.
237Kinstalls+1.1K today
npx skills@latest add https://github.com/obra/superpowers/tree/22f0b463e7a5e579904dd6211a520321035526f7 --skill dispatching-parallel-agentsMCP builder
A phased guide to building good MCP servers in Python or TypeScript, with evaluations.
What it can touch: Edits code · Runs commands · Network
Automated scan recorded · evidence and limits
- Automated scan: Checked 16 Nov 2026. Checks SKILL.md patterns and frontmatter; does not run the skill.
- Source revision: 1780c5e5a552 (opens in a new tab). The install command targets this commit. Only SKILL.md was scanned.
- Human reading: No full human-reading date recorded.
- Runtime evidence: No runtime-test evidence recorded here.
A review is not a security audit or a guarantee.
Commands target the repository commits recorded with the automated scans. Scans cover only SKILL.md, not referenced files or runtime behavior. What the review covers.
143Kinstalls+602 today
npx skills@latest add https://github.com/anthropics/skills/tree/1780c5e5a552fd4d1c9d6a7b0cab26b0c2bef064 --skill mcp-builderClaude API
Builds Claude API and Managed Agent integrations with current SDK and tool-use patterns.
What it can touch: Edits code · Writes docs · Runs commands · Subagents · Browser · Needs MCP · Network
Automated scan recorded · evidence and limits
- Automated scan: Checked 16 Nov 2026. Checks SKILL.md patterns and frontmatter; does not run the skill.
- Source revision: 1780c5e5a552 (opens in a new tab). The install command targets this commit. Only SKILL.md was scanned.
- Human reading: No full human-reading date recorded.
- Runtime evidence: No runtime-test evidence recorded here.
A review is not a security audit or a guarantee.
Commands target the repository commits recorded with the automated scans. Scans cover only SKILL.md, not referenced files or runtime behavior. What the review covers.
81Kinstalls+326 today
npx skills@latest add https://github.com/anthropics/skills/tree/1780c5e5a552fd4d1c9d6a7b0cab26b0c2bef064 --skill claude-apiContext engineering
Sets up rules files and project context so agent quality holds across sessions.
What it can touch: Writes docs
Automated scan recorded · evidence and limits
- Automated scan: Checked 16 Nov 2026. Checks SKILL.md patterns and frontmatter; does not run the skill.
- Source revision: 39b723ceebf8 (opens in a new tab). The install command targets this commit. Only SKILL.md was scanned.
- Human reading: No full human-reading date recorded.
- Runtime evidence: No runtime-test evidence recorded here.
A review is not a security audit or a guarantee.
Commands target the repository commits recorded with the automated scans. Scans cover only SKILL.md, not referenced files or runtime behavior. What the review covers.
75Kinstalls+553 today
npx skills@latest add https://github.com/addyosmani/agent-skills/tree/39b723ceebf81474d0557c1fecd01eddab585563 --skill context-engineeringTask Coordination Strategies
Coordinates multiple agents through task decomposition, ownership, and communication patterns.
What it can touch: Subagents
Automated scan recorded · evidence and limits
- Automated scan: Checked 16 Nov 2026. Checks SKILL.md patterns and frontmatter; does not run the skill.
- Source revision: 9c61ab243def (opens in a new tab). The install command targets this commit. Only SKILL.md was scanned.
- Human reading: No full human-reading date recorded.
- Runtime evidence: No runtime-test evidence recorded here.
A review is not a security audit or a guarantee.
Commands target the repository commits recorded with the automated scans. Scans cover only SKILL.md, not referenced files or runtime behavior. What the review covers.
10Kinstalls+15 today
npx skills@latest add https://github.com/wshobson/agents/tree/9c61ab243def98f72da12abd41cfcf5bcd91af9d --skill task-coordination-strategiesMCP Developer
Builds Model Context Protocol servers with tool, resource, and transport design guidance.
What it can touch: Edits code · Runs commands · Writes docs · Network
Automated scan recorded · evidence and limits
- Automated scan: Checked 16 Nov 2026. Checks SKILL.md patterns and frontmatter; does not run the skill.
- Source revision: 078a25cc5bfd (opens in a new tab). The install command targets this commit. Only SKILL.md was scanned.
- Human reading: No full human-reading date recorded.
- Runtime evidence: No runtime-test evidence recorded here.
A review is not a security audit or a guarantee.
Commands target the repository commits recorded with the automated scans. Scans cover only SKILL.md, not referenced files or runtime behavior. What the review covers.
4.5Kinstalls+8 today
npx skills@latest add https://github.com/jeffallan/claude-skills/tree/078a25cc5bfd8011459be7b91d004e900c1d02d3 --skill mcp-developerEfficiency Skill
Keep the main model in charge. Delegate bounded work when the handoff is worth it.
What it can touch: Subagents
Automated scan recorded · evidence and limits
- Automated scan: Checked 16 Nov 2026. Checks SKILL.md patterns and frontmatter; does not run the skill.
- Source revision: f32c6aba18d4 (opens in a new tab). The install command targets this commit. Only SKILL.md was scanned.
- Human reading: Full reading recorded 25 Sept 2026; not bound to the current source revision.
- Runtime evidence: Published evaluation notes (opens in a new tab). Evaluation date not recorded here; see the notes for dates, scope and limitations. Not a test of every upstream revision.
A review is not a security audit or a guarantee.
Commands target the repository commits recorded with the automated scans. Scans cover only SKILL.md, not referenced files or runtime behavior. What the review covers.
—not counted yet
npx skills@latest add https://github.com/AaravKashyap12/efficiency-skill/tree/f32c6aba18d42ae6f2f757f6515cb5e32f61ae80 --skill efficiency-skillMCP Server Patterns
Applies reusable design patterns for robust, secure MCP server implementations.
What it can touch: Edits code · Runs commands · Writes docs
Last good scan retained · evidence and limits
- Automated scan: Latest fetch failed. Last successful scan: 8 Nov 2026. Current upstream content is unverified.
- Source revision: No repository commit recorded. Install command is unpinned.
- Human reading: No full human-reading date recorded.
- Runtime evidence: No runtime-test evidence recorded here.
A review is not a security audit or a guarantee.
Installs the upstream repository’s current version, not a pinned reviewed revision. The source may have changed since the check. What the review covers.
—not counted yet
npx skills@latest add affaan-m/everything-claude-code --skill mcp-server-patterns
No skill matches these filters and “”. Remove a filter, or submit a skill that fits.