latestaiagents/agent-skills

1

graphrag-patterns Implement GraphRAG combining knowledge graphs with RAG for multi-hop reasoning. Use this skill when building knowledg…

latestaiagents/agent-skills

202

2

agentic-rag Build agentic RAG systems with autonomous planning, reflection, and tool use. Use this skill when implementing agent-…

latestaiagents/agent-skills

78

3

rag-evaluation Test and benchmark RAG systems with proper metrics and evaluation frameworks. Use this skill when evaluating RAG qual…

latestaiagents/agent-skills

62

4

chunking-strategies Optimize document chunking for RAG performance and retrieval quality. Use this skill when splitting documents, choosi…

latestaiagents/agent-skills

61

5

production-rag-checklist Deploy RAG systems to production with proper architecture, monitoring, and operations. Use this skill when deploying …

latestaiagents/agent-skills

55

6

hybrid-retrieval Implement hybrid search combining vector and keyword retrieval for RAG systems. Use this skill when building RAG retr…

latestaiagents/agent-skills

51

7

corrective-rag Implement Corrective RAG (CRAG) and Self-RAG for reliable, self-healing retrieval systems. Use this skill when buildi…

latestaiagents/agent-skills

45

8

mcp-transport-stdio-http Choose between MCP transports — stdio for local processes, Streamable HTTP for remote servers, SSE for legacy — and i…

latestaiagents/agent-skills

31

9

computer-use Build browser/desktop automation agents using Claude's Computer Use capability — screen-taking, clicking, typing. Cov…

latestaiagents/agent-skills

22

10

code-execution Use Claude's Code Execution tool to run Python in a sandboxed environment as part of a response — for calculation, da…

latestaiagents/agent-skills

21

11

mcp-resource-patterns Use MCP Resources correctly — the read-only, URI-addressable data primitive — and know when to pick resources, tools,…

latestaiagents/agent-skills

21

12

session-lifecycle Manage Claude Agent SDK / Managed Agents sessions — creation, resumption, compaction, forking, and termination. Cover…

latestaiagents/agent-skills

21

13

agent-sdk-quickstart Build your first Claude Agent SDK agent — TypeScript or Python. Covers installation, minimal agent loop, tool definit…

latestaiagents/agent-skills

20

14

eval-dataset-design Design eval datasets that actually measure model quality — coverage, difficulty distribution, labeling consistency, a…

latestaiagents/agent-skills

20

15

long-context-1m Use Claude's 1M-token context window effectively — when to use it, how to structure inputs for recall, how to price i…

latestaiagents/agent-skills

20

16

managed-agents-api Use Anthropic's Managed Agents API (/v1/agents, /v1/sessions) — server-side agent runtime that handles the tool loop,…

latestaiagents/agent-skills

20

17

mcp-tool-design Design MCP tool schemas, names, and descriptions that AI agents actually pick correctly and use without hand-holding.…

latestaiagents/agent-skills

20

18

regression-evals Set up continuous regression evals so model/prompt/tool changes don't silently break existing behavior. Covers gating…

latestaiagents/agent-skills

20

19

skill-activation-patterns Design skills that fire at the right moment — neither over-eager (noise) nor under-eager (silent). Covers activation …

latestaiagents/agent-skills

20

20

sub-agent-delegation Delegate work to sub-agents via the Task/Agent tool — parallel research, isolated context windows, specialized expert…

latestaiagents/agent-skills

20

21

agent-sdk-streaming Stream agent output correctly — text deltas, tool-use events, thinking deltas, progress indicators — without dropping…

latestaiagents/agent-skills

19

22

cost-quality-tradeoff Measure and optimize the cost/quality curve — which model, prompt, and settings give the best quality per dollar. Cov…

latestaiagents/agent-skills

19

23

extended-thinking Use Claude's extended thinking (reasoning) mode effectively — budget tokens, interleaved thinking with tool use, when…

latestaiagents/agent-skills

19

24

golden-set-maintenance Curate and maintain "golden set" eval items — the small, high-signal cases that must never regress. Covers selection …

latestaiagents/agent-skills

19

25

llm-as-judge Use an LLM as an evaluator for open-ended outputs — rubrics, pairwise comparison, calibration with human labels, bias…

latestaiagents/agent-skills

19

26

mcp-auth-oauth Implement OAuth 2.1 + PKCE authentication for remote MCP servers, including dynamic client registration, token refres…

latestaiagents/agent-skills

19

27

mcp-client-integration Connect MCP servers to AI clients — Claude Desktop, Claude Code, Cursor, the Claude Agent SDK, and custom apps — incl…

latestaiagents/agent-skills

19

28

mcp-security-sandboxing Secure MCP servers against prompt injection, tool abuse, excessive permission, and data exfiltration. Covers per-tool…

latestaiagents/agent-skills

19

29

mcp-server-authoring Build production-quality MCP (Model Context Protocol) servers that expose tools, resources, and prompts to AI clients…

latestaiagents/agent-skills

19

30

memory-tool Use Claude's Memory tool to give agents persistent cross-session memory stored in a client-side file directory. Cover…

latestaiagents/agent-skills

19

31

progressive-disclosure Structure SKILL.md content so the model reads just enough — concise summary up front, progressively deeper detail, ex…

latestaiagents/agent-skills

19

32

prompt-caching-ttl Use Claude's prompt caching with 5-minute and 1-hour TTLs to slash costs on repeated context — codebases, system prom…

latestaiagents/agent-skills

19

33

skill-frontmatter Write the YAML frontmatter for a SKILL.md file so it activates reliably — name, description, and activation keywords …

latestaiagents/agent-skills

19

34

skill-testing Test skills for correct activation, content quality, and regression — both automated checks (frontmatter validity, li…

latestaiagents/agent-skills

19

35

branch-strategy-advisor Use this skill when discussing Git branching strategies. Activate when the user asks about branch naming, GitFlow, tr…

latestaiagents/agent-skills

14

36

code-explanation-generator Use this skill when generating explanations for code. Activate when the user needs to understand complex code, wants …

latestaiagents/agent-skills

14

37

codebase-context-builder Use this skill when preparing context for AI coding assistants. Activate when the user wants to help AI understand th…

latestaiagents/agent-skills

14

38

git-undo-wizard Use this skill when the user needs to undo, revert, or recover from Git mistakes. Activate when they mention: undo co…

latestaiagents/agent-skills

14

39

reproduction-builder Use this skill when creating bug reproductions. Activate when the user needs to create a minimal reproduction case, r…

latestaiagents/agent-skills

14

40

stack-trace-decoder Use this skill when analyzing stack traces. Activate when the user has a stack trace to understand, needs to decode e…

latestaiagents/agent-skills

14

41

ai-code-reviewer Use this skill when reviewing AI-generated code. Activate when the user has code generated by an AI assistant and wan…

latestaiagents/agent-skills

13

42

commit-message-crafter Use this skill when writing Git commit messages. Activate when the user asks about commit message format, conventiona…

latestaiagents/agent-skills

13

43

debug-with-ai Use this skill when debugging code with AI assistance. Activate when the user has a bug, error, unexpected behavior, …

latestaiagents/agent-skills

13

44

dependency-conflict-resolver Use this skill when resolving dependency conflicts. Activate when the user has package version conflicts, npm/yarn/pn…

latestaiagents/agent-skills

13

45

doc-sync-automation Use this skill when keeping documentation synchronized with code. Activate when the user needs to update docs after c…

latestaiagents/agent-skills

13

46

error-pattern-analyzer Use this skill when analyzing error patterns in applications. Activate when the user has recurring errors, wants to f…

latestaiagents/agent-skills

13

47

git-history-detective Use this skill when investigating Git history. Activate when the user wants to find when a bug was introduced, who ch…

latestaiagents/agent-skills

13

48

log-forensics Use this skill when investigating issues through logs. Activate when the user needs to analyze log files, search for …

latestaiagents/agent-skills

13

49

merge-conflict-surgeon Use this skill when resolving Git merge conflicts. Activate when the user mentions merge conflicts, conflicting chang…

latestaiagents/agent-skills

13

50

performance-profiler Use this skill when investigating performance issues. Activate when the user has slow code, needs to find performance…

latestaiagents/agent-skills

13