Skill collection

agent-sh/agentsys

28 agent skills across 7 categories, read straight from the repository tree.

agent-sh404★ across the radarProfile →
28
Skills published
7
Categories
923
Stars on the repo
Tracked on the radar · 923★Repository facts and velocity →
AI & Agents · 6
All in category →
consultCross-tool AI consultation. Use when user asks to 'consult gemini', 'ask codex', 'get second opinion'…enhance-agent-promptsUse when improving agent prompts, frontmatter, and tool restrictions.enhance-claude-memoryUse when improving CLAUDE.md or AGENTS.md project memory files.enhance-cross-fileUse when checking cross-file consistency: tools vs frontmatter, agent references, duplicate rules…perf-profilerUse when profiling CPU/memory hot paths, generating flame graphs, or capturing JFR/perf evidence.maintain-cross-platformUse when preparing releases, validating cross-platform compatibility, or updating installation…
Code Review & Quality · 2
All in category →
deslopUse when user wants to clean AI slop from code. Use for cleanup, remove debug statements, find ghost code…enhance-skillsUse when reviewing SKILL.md files for structure and trigger quality.
Workflow & Productivity · 2
All in category →
discover-tasksUse when user asks to \"discover tasks\", \"find next task\", \"prioritize issues\", \"what should I work…drift-analysisUse when the user asks about plan drift, reality check, comparing docs to code, project state analysis…
Documentation · 2
All in category →
enhance-docsUse when improving documentation structure, accuracy, and RAG readiness.sync-docsSync documentation with code. Use when user asks to update docs, check docs, fix stale documentation, update…
Security · 2
All in category →
enhance-pluginsUse when analyzing plugin structures, MCP tools, and plugin security patterns.orchestrate-reviewUse when user asks to \"deep review the code\", \"thorough code review\", \"multi-pass review\", or when…
Testing & QA · 1
All in category →
debateStructured AI debate templates and synthesis. Use when orchestrating multi-round debates between AI tools…
Other · 13
learnResearch any topic online and create learning guides. Use when user asks to 'learn about', 'research topic'…enhance-promptsUse when improving general prompts for structure, examples, and constraints.enhance-hooksUse when reviewing hooks for safety, timeouts, and correct frontmatter.enhance-orchestratorUse when coordinating multiple enhancers for /enhance command. Runs analyzers in parallel and produces…perf-analyzerUse when synthesizing perf findings into evidence-backed recommendations and decisions.perf-baseline-managerUse when managing perf baselines, consolidating results, or comparing versions. Ensures one baseline JSON per…perf-benchmarkerUse when running performance benchmarks, establishing baselines, or validating regressions with sequential…perf-code-pathsUse when mapping code paths, entrypoints, and likely hot files before profiling.perf-investigation-loggerUse when appending structured perf investigation notes and evidence.
perf-theory-gathererperf-theory-testerrepo-intelvalidate-delivery
About this collection
How many skills does agent-sh/agentsys publish?

28 that pass our gate — each has a real description and a SKILL.md we could read.

How do I install one?

Every skill page carries its own command — `npx skills add agent-sh/agentsys --skill <name> --agent claude-code`. Swap the agent for codex, cursor or copilot.

Keep going
All skills →
The full catalog, by category and by tool.
Open Source Radar →
The repositories these collections come from.
More from agent-sh →
Everything this maker publishes.