auto-improve
01Plugin Claude Code
Bundles 1 skill, 1 hook · 76 tokens together
Background review hook that learns from each session. Forks a headless Claude after every Stop to update memory and skills.
Plugin Claude Code
Bundles 1 skill, 1 hook · 76 tokens together
Background review hook that learns from each session. Forks a headless Claude after every Stop to update memory and skills.
Plugin Claude Code
Bundles 4 commands · 48 tokens together
Git commit workflow commands: commit, push and PR, branch cleanup.
Plugin Claude Code
Bundles 1 skill · 79 tokens together
Multi-model AI consultation using cursor-agent. Supports consultation, research, and deliberation modes.
Plugin Claude Code
Bundles 3 commands · 39 tokens together
Background skill-library maintenance. Weekly idle-gated pass that consolidates near-duplicate skills into umbrellas with references/templates/scripts, with pre-run snapshots and rollback. Ported from Hermes.
Plugin Claude Code
Bundles 1 skill · 15 tokens together
Syncs Claude Code plugins to Cursor skills and commands directories with launchd watcher.
Plugin Claude Code
Bundles 1 skill · 68 tokens together
Analyse Claude Code conversation history for search and summaries.
Plugin Claude Code
Bundles 1 skill · 72 tokens together
Logo design generation pipeline using Gemini image generation. Generates prompt variations, calls API, evaluates results, and iterates.
Plugin Claude Code
Bundles 1 skill, 3 commands · 130 tokens together
Persistent session memory: auto-checkpoints sessions (PreCompact/SessionEnd), /note-session writes daily logs, /rollup-day distills them, /recall searches the curated layer.
Plugin Claude Code
Bundles 2 skills, 1 agent · 312 tokens together
PEP (Project Enhancement Proposal) workflow: markdown-driven planning, investigation, and execution with wave shapes, adversarial review, and gate evidence. Audit hook records what actually ran. No engine, no state.db. Folds in the spike (investigation) flow. Includes the grill skill (alignment interview + domain…
Plugin Claude Code
Bundles 1 skill · 158 tokens together
QA spine. qa-scenarios generates user-impact test scenarios from a code change, reading a layered repo-local QA.md failure-mode corpus discovered at runtime. Product-agnostic; grows the corpus as the user reacts to scenarios.
Plugin Claude Code
Bundles 1 skill · 69 tokens together
Utilities for creating and validating Claude Code skills.
Plugin Claude Code
Bundles 8 skills, 1 command, 1 agent · 687 tokens together
Code review, cleanup, comment deslopping, refactoring, debugging discipline, browser testing agent, and gate-keeper evaluation agent. PEP workflow moved to its own marketplace at the pep repo.
Plugin Claude Code
Bundles 1 skill · 130 tokens together
Turn spoken or typed descriptions into editable .excalidraw diagrams. Claude writes a small graph JSON, a bundled script lays it out with ELK and writes the Excalidraw file, canvas edits sync back into the graph, and positions are kept between renders.
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: