how
49Skill Claude Code
Explains how a subsystem works: architecture, runtime flow, onboarding mental models. Use for how does X work or code walkthroughs. Not for motivation.
not rated 38
changed 9d ago A 33 tokens
interrogate
50Skill Claude Code
Runs several independent adversarial reviewers over a diff and synthesizes one verdict without auto-applying fixes. Use to challenge a change or find blind spots.
not rated 38
changed 9d ago A 33 tokens
Skill Claude Code
Keeps a project's verification skill and feature map accurate using parallel source readers and one live session, ending in at most one PR of proven corrections.
not rated 38
changed 9d ago A 36 tokens
no-comments
52Skill Claude Code
Reviews comments on a diff, deletes narration, fixes accepted findings, and offers encodings for claimed constraints. Use before review or when asked to strip comments.
not rated 38
changed 9d ago A 34 tokens
recall
53Skill Claude Code
Rebuilds recent working context from chat history, live state, and the shared record into a tight current-state brief. Use to resume or catch up on past work.
not rated 38
changed 9d ago A 37 tokens
setup-pstack
54Skill Claude Code
Configures canonical Shipshit Pstack adapters for selected harnesses while preserving existing role choices. Use when setting up Pstack, migrating duplicate installations, or enabling a supported optional adapter.
not rated 38
changed 9d ago A 40 tokens
Skill Claude Code
Keeps a TSV decision log (what, why, evidence, result) for long or unattended work. Use for autonomous or multi-phase runs a human reviews afterward.
not rated 38
changed 9d ago A 38 tokens
swarm
56Skill Claude Code
Fans out N parallel workers, drains them, and returns one aggregated report. Use for swarm this, parallel coverage, races, gauntlets and exploration partitions.
not rated 38 6d ago A 35 tokens
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: