agent-sh
71 verified skills24,159 total stars
perf-investigation-logger
Use when appending structured perf investigation notes and evidence.
tools656
perf-theory-tester
Use when running controlled perf experiments to validate hypotheses.
testing656
sync-docs
Sync documentation with code. Use when user asks to update docs, check docs, fix stale documentation, update changelog, or after code changes.
development656
validate-delivery
Use when user asks to "validate delivery", "check readiness", or "verify completion". Runs tests, build, and requirement checks with pass/fail instructions.
development656
web-browse
Browse and interact with web pages headlessly. Use when agent needs to navigate websites, click elements, fill forms, read content, or take screenshots.
tools656
maintain-cross-platform
Use when preparing releases, validating cross-platform compatibility, or updating installation infrastructure. Meta-skill for maintaining AgentSys's 3-platform architecture.
devops656
learn
Research any topic online and create learning guides. Use when user asks to 'learn about', 'research topic', 'create learning guide', 'build knowledge base', or 'study subject'.
development656
enhance-skills
Use when reviewing SKILL.md files for structure and trigger quality.
testing656
deslop
Use when user wants to clean AI slop from code. Use for cleanup, remove debug statements, find ghost code, repo hygiene.
development656
enhance-agent-prompts
Use when improving agent prompts, frontmatter, and tool restrictions.
tools656
perf-code-paths
Use when mapping code paths, entrypoints, and likely hot files before profiling.
development656
perf-profiler
Use when profiling CPU/memory hot paths, generating flame graphs, or capturing JFR/perf evidence.
tools656
repo-intel
Use when user asks to "run repo intel", "generate repo map", "analyze repo", "query hotspots", "check ownership", or "bus factor". Unified static analysis - git history, AST symbols, project metadata.
testing656
enhance-cross-file
Use when checking cross-file consistency: tools vs frontmatter, agent references, duplicate rules, contradictions.
tools656
enhance-hooks
Use when reviewing hooks for safety, timeouts, and correct frontmatter.
tools656
enhance-plugins
Use when analyzing plugin structures, MCP tools, and plugin security patterns.
tools656
web-auth
Authenticate to websites with human-in-the-loop browser handoff. Use when user needs to log into a website, complete 2FA, or solve CAPTCHAs for agent access.
development656
orchestrate-review
Use when user asks to "deep review the code", "thorough code review", "multi-pass review", or when orchestrating the Phase 9 review loop. Provides review pass definitions (code quality, security, performance, test coverage), signal detection patterns, and iteration algorithms.
development656
discover-tasks
Use when user asks to "discover tasks", "find next task", "prioritize issues", "what should I work on", or "list open issues". Discovers and ranks tasks from GitHub, GitLab, local files, and custom sources.
tools656
perf-benchmarker
Use when running performance benchmarks, establishing baselines, or validating regressions with sequential runs. Enforces 60s minimum runs (30s only for binary search) and no parallel benchmarks.
tools656
perf-theory-gatherer
Use when generating performance hypotheses backed by git history and code evidence.
development656
consult
Cross-tool AI consultation. Use when user asks to 'consult gemini', 'ask codex', 'get second opinion', 'cross-check with claude', 'consult another AI', 'ask opencode', 'copilot opinion', or wants a second opinion from a different AI tool.
tools656
debate
Structured AI debate templates and synthesis. Use when orchestrating multi-round debates between AI tools, 'debate topic', 'argue about', 'stress test idea', 'devil advocate'.
tools656
drift-analysis
Use when the user asks about plan drift, reality check, comparing docs to code, project state analysis, roadmap alignment, implementation gaps, or needs guidance on identifying discrepancies between documented plans and actual implementation state.
development656
enhance-claude-memory
Use when improving CLAUDE.md or AGENTS.md project memory files.
data-ai656
enhance-docs
Use when improving documentation structure, accuracy, and RAG readiness.
documentation656
enhance-orchestrator
Use when coordinating multiple enhancers for /enhance command. Runs analyzers in parallel and produces unified report.
business656
enhance-prompts
Use when improving general prompts for structure, examples, and constraints.
data-ai656
perf-analyzer
Use when synthesizing perf findings into evidence-backed recommendations and decisions.
testing656
perf-baseline-manager
Use when managing perf baselines, consolidating results, or comparing versions. Ensures one baseline JSON per version.
tools656
agnix
Use when user asks to 'lint agent configs', 'validate skills', 'check CLAUDE.md', 'validate hooks', 'lint MCP'. Validates agent configuration files against 385 rules.
tools114
agnix
Use when user asks to 'lint agent configs', 'validate skills', 'check CLAUDE.md', 'validate hooks', 'lint MCP'. Validates agent configuration files against 385 rules across 10+ AI tools.
tools114
fork-with-instructions
Use when analyzing code quality
development109
invalid-model-skill
Use when testing invalid model validation
testing109
unreachable-skill
Use when testing unreachable skills
testing109
unknown-frontmatter-field
Use when validating frontmatter keys
tools109
hint-skill
Use when testing argument hints
testing109
test-skill
Use when testing per-client skill rules
tools109
first-person-description
Use when you need pull-request review help
tools109
with-custom-agent
Use when testing custom agent validation
testing109
hooks-skill
Use when testing hooks validation
testing109
test-skill
Use when testing per-client skill rules
tools109
agent-without-context-skill
Use when testing agent without context validation
testing109
deploy-prod
Deploys to production
devops109
deploy-prod
Use when deploying to production environment
devops109
indexed-arguments-no-hint
Use when validating indexed arguments
tools109
invalid-agent-skill
Use when testing invalid agent validation
testing109
invalid-context-skill
Use when testing invalid context validation
testing109
tests/fixtures/skills/missing-frontmatter
No frontmatter here.
testing109
directory-helper
Use when validating name-directory matching
tools109
bad-invocable-skill
Use when testing boolean type validation
testing109
test-skill
Use when testing per-client skill rules
tools109
test-skill
Use when testing per-client skill rules
tools109
test-skill
Use when testing per-client skill rules
tools109
too-many-injections-skill
Use when testing injection limit validation
testing109
helper
Use when validating vague skill names
tools109
test-skill
Use when testing per-client skill rules
tools109
with-hooks
Use when testing valid hooks
testing109
with-context-agent
Use when testing valid context and agent configuration
testing109
windows-path
Use when validating windows paths
tools109
test-skill
Use when testing per-client skill rules
tools109
test-skill
Use when testing per-client skill rules
tools109
invalid_name
Use when user wants to review code
development109
bad-bool-skill
Use when testing boolean type validation
testing109
context-without-agent-skill
Use when testing context without agent validation
testing109
with-model
Use when testing valid model configuration
testing109
deep-reference
Use when validating deep references
tools109
code-review
Use when user asks to review code for quality and security issues.
development109
with-argument-hint
Use when greeting users
tools109
unknown-tool-skill
Use when testing unknown tool validation
tools109
reference-skill
Use when looking up documentation
documentation109