claudecodex

self-improve-skill

Analyzes session transcripts and improves project documentation (CLAUDE.md, README, memory) based on learnings

10 on GitHubby Yorrick Jansenv2.0.0MITupdated 1 month ago
/

Plugin self-improve-skill from marketplace yorrick in yorrick/agent-skills. Commands read from the repo's manifest — 1 month ago.

This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.

What it installs

Skills (1)

  • reflect

    Analyze the current session transcript and improve project documentation based on what was learned. Triggered automatically via SessionEnd hook, or manually with /reflect. Use when the user says "reflect", "what did we learn", "improve docs from this session", or "capture learnings". Also runs autom

Hooks (2)

  • SessionEnd

    uv run ${CLAUDE_PLUGIN_ROOT}/scripts/session_end_hook.py

  • SessionStart

    uv run ${CLAUDE_PLUGIN_ROOT}/scripts/session_start_hook.py

View source on GitHub

More from yorrick/agent-skills

All 9 plugins →

jev-router

claudecodex

Asks Jev (via OpenRouter) how long each job will run and, in Claude Code, whether a fresh subagent would do it cheaper. Starts in shadow mode. Off until you turn it on with /jev on.

1 skill · 4 agents · hooks

10

dev-loop

claudecodex

Automated development loop and ad-hoc workflow generation for orchestrating AI coding agents

3 commands

10

agent-session-monitor

claudecodex

Monitor and steer Claude Code, Codex, and other terminal coding agents through tmux panes.

1 skill

10

flowchart

claudecodex

Create clear process flowcharts and interactive walkthroughs, with evidence-based layout guidance and keyboard checks for the actual delivery surface.

1 skill

10

pr-review

claudecodex

Multi-provider interactive PR code review. Runs Claude Code, Gemini CLI, and Codex CLI in parallel, merges findings, then lets you vet each issue before posting to GitHub.

1 skill

10

supabase-security

claudecodex

Access-control rules for Supabase projects exposed directly to a browser via PostgREST. Covers the three enforcement layers (GRANT, RLS, triggers), the traps that cause privilege escalation, and how anon keys, JWTs and service_role actually differ.

1 skill

10

Maintain self-improve-skill?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins9 plugins