Plugins

Tools for building and evaluating Claude skills, hooks, agents, commands, and plugins — modular patterns, quality checks, and plugin validation

from pproenca/dot-claude-old

Skills about skills -- writing, auditing, and managing the lifecycle of skills.

Marketplace maintenance skills — scaffold, garden, update, review, and release the skills and plugins in this repository while keeping the registry, versions, and conventions free of drift. Also bundles the skill-creator engine for authoring and eval-optimizing skills from scratch.

Plugin from naffis/loadout

from computomatic/claude-plugin

Skills + 2 hooks + CLI mb materializando Camada 3 entre sessões Claude Code e graph Logseq. /journal-note pra captura cross-domain em hashtag-buckets; /journal-close pra síntese de sessão como DONE tasks agrupados por repo; /journal-load pra carregar conteúdo de journals na working memory do CC (read-only); /init-logseq-project pra sync repo→Project Page; /journal-review pra review detective-first de janela configurável via 4 heurísticas estruturais + wizard GTD opt-in (sucessor de /weekly-review); hook suggest_journal_close (Stop) reagindo ao marker de fim de /run-plan do pragmatic-dev-toolkit; hook suggest_session_start_tip (SessionStart) sugerindo /journal-load quando cwd casa com repo owned/active da constelação. Substância de write vive em meta_bridge (Python CLI via Click); skills viram thin orchestrators preservando substância editorial-semântica.

Readable functional patterns — orchestrators, pure functions, named abstractions

Scaffold a scheduled 'doctor' agent that audits app health, opens PRs for code-fixable findings, and files deduped tickets for the rest

GitHub harness authoring: agent tooling setup and repository conventions (issue forms, labels, PR, commit, and release rules, automation).

GitLab harness authoring: agent tooling setup and project conventions (description templates, scoped labels, MR, commit, and release rules, CI validation).

Investigation flow (Glob -> Grep -> Read), evidence-based research with file:line references, structured output format for AI consumption. Use for pattern discovery, implementation research, and codebase investigation.

Inspect recent Claude Code activity and promote repeated patterns into the smallest useful Skill, subagent, or hook. Read-only investigation; creation gated by user approval.

Legal document metadata extraction, verification, and curation command with agents for Claude.

from jtsylve/claude-experiments

Compositional prompt engineering for Claude Code. Five commands, four operators (→ || ⊗ >=>), seventeen skills. Inspired by category theory.

CLI code review patterns. Use when reviewing CLI applications built with Commander.js, @clack/prompts, picocolors. Covers exit codes, signal handling, error messages, user experience, testing adequacy.

Code review patterns, feedback principles. Use when reviewing PRs, implementations, or making approval/rejection decisions. Covers self-correction, progress tracking, feedback principles, severity levels.

from adbutterfield/coding-agent-plugins

Nine task-agnostic meta-skills that emit the reusable structure solving a whole category of work, not a single instance.

from Agentient/vibekit

from postsharp/PostSharp.Engineering.AISkills

Skills and agents to help implement a customizable agent driven SDLC

Internal review harness, adversarial gates, and post-merge learning for coding agents

from liskl/claude-marketplace

from stbenjam/metrics-temp

mindfunnel: project-agnostic Claude Code session management. /mf:dump consolidates session state into auto-memory; /mf:spinup reads it back; /mf:setup and /mf:prime handle first-time and per-project scaffolding.

from lacrioque/mfinit

from galligan/claude-plugin

from jason-hchsieh/marketplace