Stats
Actions
Tags
Help us improve
Share bugs, ideas, or general feedback.
From subagent-system
Reads improvement proposals from .claude/improvement-proposals.md and applies HIGH/MEDIUM priority changes to plugin files, with safety checks for destructive or multi-file edits.
npx claudepluginhub minhthang1009/dotclaude --plugin subagent-systemHow this skill is triggered — by the user, by Claude, or both
Slash command
/subagent-system:apply-improvementsThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Read `.claude/improvement-proposals.md` from the project at $ARGUMENTS (or current directory if not specified).
Creates p5.js generative art with seeded randomness, noise fields, and interactive parameter exploration. Use for algorithmic art, flow fields, or particle systems.
Share bugs, ideas, or general feedback.
Read .claude/improvement-proposals.md from the project at $ARGUMENTS (or current directory if not specified).
For each proposal in the file:
Parse the proposal — extract Target (plugin file path), Problem, and Proposed change.
Locate the target file in the plugin directory. The plugin is at the path shown by:
`echo ${CLAUDE_PLUGIN_ROOT}`
Apply only HIGH and MEDIUM priority proposals automatically. For LOW priority proposals: show them to the user and ask for confirmation before applying.
For each change applied:
Do NOT apply proposals that:
After all changes, output:
IMPROVEMENTS_APPLIED:
Applied: N proposals
Skipped (LOW priority, awaiting confirmation): M proposals
Skipped (requires manual review): K proposals
Files modified:
- [plugin file]: [what changed]
Re-run the pipeline on the same project to verify improvements took effect.
Safety rule: Never apply a proposal that modifies the pipeline-retrospective skill itself, the apply-improvements command itself, or the mandatory pipeline shape — these require manual review.