agent-sh/agentsys

1

enhance-claude-memory Use when improving CLAUDE.md or AGENTS.md project memory files.

agent-sh/agentsys

125

2

debate Structured AI debate templates and synthesis. Use when orchestrating multi-round debates between AI tools, 'debate to…

agent-sh/agentsys

115

3

learn Research any topic online and create learning guides. Use when user asks to 'learn about', 'research topic', 'create …

agent-sh/agentsys

106

4

consult Cross-tool AI consultation. Use when user asks to 'consult gemini', 'ask codex', 'get second opinion', 'cross-check w…

agent-sh/agentsys

97

5

sync-docs Sync documentation with code. Use when user asks to update docs, check docs, fix stale documentation, update changelo…

agent-sh/agentsys

92

6

enhance-prompts Use when improving general prompts for structure, examples, and constraints.

agent-sh/agentsys

90

7

deslop Use when user wants to clean AI slop from code. Use for cleanup, remove debug statements, find ghost code, repo hygie…

agent-sh/agentsys

87

8

enhance-agent-prompts Use when improving agent prompts, frontmatter, and tool restrictions.

agent-sh/agentsys

87

9

perf-profiler Use when profiling CPU/memory hot paths, generating flame graphs, or capturing JFR/perf evidence.

agent-sh/agentsys

87

10

perf-benchmarker Use when running performance benchmarks, establishing baselines, or validating regressions with sequential runs. Enfo…

agent-sh/agentsys

86

11

validate-delivery Use when user asks to "validate delivery", "check readiness", or "verify completion". Runs tests, build, and requirem…

agent-sh/agentsys

86

12

enhance-skills Use when reviewing SKILL.md files for structure and trigger quality.

agent-sh/agentsys

85

13

perf-analyzer Use when synthesizing perf findings into evidence-backed recommendations and decisions.

agent-sh/agentsys

85

14

enhance-docs Use when improving documentation structure, accuracy, and RAG readiness.

agent-sh/agentsys

84

15

orchestrate-review Use when user asks to "deep review the code", "thorough code review", "multi-pass review", or when orchestrating the …

agent-sh/agentsys

84

16

perf-investigation-logger Use when appending structured perf investigation notes and evidence.

agent-sh/agentsys

84

17

discover-tasks Use when user asks to "discover tasks", "find next task", "prioritize issues", "what should I work on", or "list open…

agent-sh/agentsys

83

18

enhance-cross-file Use when checking cross-file consistency: tools vs frontmatter, agent references, duplicate rules, contradictions.

agent-sh/agentsys

83

19

perf-theory-gatherer Use when generating performance hypotheses backed by git history and code evidence.

agent-sh/agentsys

83

20

perf-theory-tester Use when running controlled perf experiments to validate hypotheses.

agent-sh/agentsys

83

21

drift-analysis Use when the user asks about plan drift, reality check, comparing docs to code, project state analysis, roadmap align…

agent-sh/agentsys

82

22

perf-baseline-manager Use when managing perf baselines, consolidating results, or comparing versions. Ensures one baseline JSON per version.

agent-sh/agentsys

82

23

perf-code-paths Use when mapping code paths, entrypoints, and likely hot files before profiling.

agent-sh/agentsys

82

24

enhance-orchestrator Use when coordinating multiple enhancers for /enhance command. Runs analyzers in parallel and produces unified report.

agent-sh/agentsys

81

25

enhance-hooks Use when reviewing hooks for safety, timeouts, and correct frontmatter.

agent-sh/agentsys

80

26

enhance-plugins Use when analyzing plugin structures, MCP tools, and plugin security patterns.

agent-sh/agentsys

80

27

web-browse Browse and interact with web pages headlessly. Use when agent needs to navigate websites, click elements, fill forms,…

agent-sh/agentsys

66

28

repo-intel Use when user asks to "run repo intel", "generate repo map", "analyze repo", "query hotspots", "check ownership", or …

agent-sh/agentsys

62

29

web-auth Authenticate to websites with human-in-the-loop browser handoff. Use when user needs to log into a website, complete …

agent-sh/agentsys

62

30

repo-mapping Use when user asks to "create repo map", "generate repo map", "update repo map", "repo map status", or "map symbols/i…

agent-sh/agentsys

25

31

agnix Use when user asks to 'lint agent configs', 'validate skills', 'check CLAUDE.md', 'validate hooks', 'lint MCP'. Valid…

agent-sh/agentsys

5