skills plugins

by Jongwon Choi

Detect application-context mismatch after execution — /contextualize (ἐφαρμογή: an application)

by Jongwon Choi

Utility skills layered on top of the core protocols. /catalog browses the protocol handbook; each utility skill's own SKILL.md carries its contract.

by Jongwon Choi

Resolve via Extended-Mind reverse induction — /elicit (εὐπορία: way through)

by Jongwon Choi

Widen an underexpanded candidate field through frame-parallel divergent generation — /ideate (εὕρεσις: finding/invention)

by Jongwon Choi

Define epistemic boundaries per decision — /bound (ὁρισμός: a bounding)

by Jongwon Choi

Conduct the method of a session's epistemic work before object-level cognition — /conduct (ὑφήγησις: a leading-the-way)

by Jongwon Choi

Verify understanding of a result or artifact through intent-scented entry points — /grasp (κατάληψις: a grasping firmly)

by Jongwon Choi

Apportion an autonomous goal into coarse execution units and derive each unit's completion conditions — /apportion (μερισμός: an apportionment)

by Jongwon Choi

Align concrete cases first, then name what they share — /induce (περιαγωγή: turning-around)

by Jongwon Choi

Expose direction unknowns through divergent-discard instantiation before commitment — /preview (πρόπλασμα: a preliminary clay model)

by Jongwon Choi

Multi-perspective framing — /frame (πρόθεσις: a placing before)

by Jongwon Choi

Route the accumulated session context to the core protocol whose deficit it shows — /route (a per-prompt hook directive triggers it)

by arbiterForge

Governance kernel for OpenAI Codex CLI: the generated codeArbiter governance surface plus enforcement hooks (persona injection, blocking pre-exec and pre-write gates, append-only audit trail), sharing one .codearbiter/ store with the Claude Code sibling plugin. Standalone: opt a repo in with ca-init; enforcement stays dormant until .codearbiter/CONTEXT.md carries 'arbiter: enabled'. Requires Python 3 and Codex >= 0.143.0. CI continuously verifies, through a real Codex host at 0.143.0 and 0.145.0, that the plugin installs, reads back enabled, and ships every hook script it declares; an advisory lane tracks npm latest for upstream drift. Hook FIRING - live persona injection and live blocks inside a turn - is verified by hand per release against docs/codex-parity-testing.md, because a turn needs a model and a provider credential cannot gate fork pull requests.

by Jesse Vincent

Skills and resources for developing Claude Code plugins, skills, MCP servers, and extensions. Includes comprehensive official documentation and self-update mechanism.

by lynxlangya

A curated skills plugin for practical AI-era craft, judgment, and delivery.

by forsonny

100-question deep discovery process: a structured self-interrogation framework for thoroughly exploring a topic, architecture, strategy, or problem space before committing to a design.

by godot-devtool contributors

Claude Code skills and an IDE-style Agent for Godot Engine development through the godot-devtool MCP server.

by DevBrother

DevBrother agent skills for clarifying requirements, generating AGENTS.md governance systems, verifying-then-applying PR review feedback, consulting a stronger advisor model at decision points, and designing polished self-contained HTML deliverables.

by akiojin

Workflow-oriented Codex skills for Unity Editor automation via the Rust unity-cli.

by Katie Parrott

A focused kit of feedback-first writing review skills for stress-testing drafts, arguments, pacing, clarity, and line-level prose.

by Devil

AI memory system with semantic understanding - provides persistent memory, decision trees, and outcome tracking

by Jacob Magar

Core homelab agents, commands, and setup and health skills for self-hosted service management.

A copyable reference package and migration guide for Agent Plugins v1.0.0.

by GadaaLabs

24 elite skills across 5 layers: discipline, domain expertise, intelligence, coordination, and execution. Turn Claude Code into a proactive engineering partner.