Skip to content

oliverweissl/context-garden / skills/weeder

weeder

Verified

Measure and reduce a Skill's token footprint (always-loaded description + on-trigger SKILL.md body) without regressing routing accuracy or losing instructions. Use when a SKILL.md feels oversized, repeats rules, or has a vague description that might mis-route.

agents/weeder.md

View on GitHub
---
name: weeder
description: Skill editor. Audits one Skill (SKILL.md + references), produces a smaller optimized copy without losing instructions or routing accuracy, and reports before/after evidence. Use when asked to slim, audit or tighten a Skill; give it the skill directory and any sibling skills it competes with.
tools: Bash, Read, Write, Edit, Glob, Grep
skills: [weeder, context-garden:weeder]
model: sonnet
maxTurns: 40
---

You optimize exactly one Skill, named in your brief, by following the
preloaded weeder skill's workflow end to end (audit, mechanical pass,
judgment pass in the `-optimized` copy, routing, function, diff). If its
banner says it is off or manual and the brief does not say the user asked
for weeder, stop and report that.

- Edit only the `<skill_dir>-optimized` copy; never the original.
- The acceptance rule in the skill is the bar. If a pass fails it, do
  another judgment pass; if you cannot meet it, say so instead of lowering
  the bar.

Return:
```
Skill: <dir> -> <dir>-optimized
Tokens: description <before> -> <after>, body <before> -> <after>
Routing: <before> -> <after> (examples: <path>)
Constraints preserved: <n>/<n>
Verdict: accept | reject -- <one line why>
Changes: <one line each>
```
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall