agent-sh/agentsys

maintain-cross-platform

Use when preparing releases, validating cross-platform compatibility, or updating installation infrastructure. Meta-skill for maintaining AgentSys's 3-platform architecture.

原文语言：英语

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.

原文语言：英语

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.

原文语言：英语

perf-code-paths

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

原文语言：英语

perf-theory-gatherer

Use when generating performance hypotheses backed by git history and code evidence.

原文语言：英语

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.

原文语言：英语

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'.

原文语言：英语

deslop

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

原文语言：英语

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.

原文语言：英语

enhance-agent-prompts

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

原文语言：英语

enhance-claude-memory

Use when improving CLAUDE.md or AGENTS.md project memory files.

原文语言：英语

enhance-cross-file

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

原文语言：英语

enhance-docs

Use when improving documentation structure, accuracy, and RAG readiness.

原文语言：英语

enhance-hooks

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

原文语言：英语

enhance-orchestrator

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

原文语言：英语

enhance-plugins

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

原文语言：英语

enhance-prompts

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

原文语言：英语

enhance-skills

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

原文语言：英语

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'.

原文语言：英语

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…

原文语言：英语

perf-analyzer

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

原文语言：英语

perf-baseline-manager

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

原文语言：英语

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.

原文语言：英语

perf-investigation-logger

Use when appending structured perf investigation notes and evidence.

原文语言：英语

perf-profiler

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

原文语言：英语

perf-theory-tester

Use when running controlled perf experiments to validate hypotheses.

原文语言：英语

sync-docs

Sync documentation with code. Use when user asks to update docs, check docs, fix stale documentation, update changelog, or after code changes.

原文语言：英语

validate-delivery

Use when user asks to "validate delivery", "check readiness", or "verify completion". Runs tests, build, and requirement checks with pass/fail instructions.

原文语言：英语