Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Yrzhe/claude-skills --skill skill-improvegit clone --depth 1 https://github.com/Yrzhe/claude-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/yrzhe/claude-skills/skill-improve)<a href="https://agentmods.dev/skills/yrzhe/claude-skills/skill-improve"><img src="https://agentmods.dev/badge/skills/yrzhe/claude-skills/skill-improve/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/yrzhe/claude-skills/skill-improve"><img src="https://agentmods.dev/badge/skills/yrzhe/claude-skills/skill-improve.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00074 | $0.00828 |
| Opus 5 | $0.00037 | $0.00414 |
| Sonnet 5 | $0.00015 | $0.00166 |
| Haiku 4.5 | $0.00007 | $0.00083 |
Grade A, and why
skill-improve scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Improve — Post-Use Skill Maintenance
Improve existing skills based on real usage experience. Always finish the current task first.
Trigger Rules
- After task completion: If a skill was used and had issues, suggest: "The
<skill-name>skill had some gaps — want me to/skill-improveit?" - Manual:
/skill-improve <skill-name>or/skill-improve(defaults to most recently used skill in session) - NEVER interrupt the current task to improve a skill. Finish first, improve after.
Improvement Flow
1. Identify Target
Determine which skill to improve:
- If
<skill-name>provided, use that - If no argument, use the most recently invoked skill in this session
- If no skill was used, ask the user which skill to improve
2. Read Current Skill
Read the target skill's SKILL.md and any bundled resources (scripts/, references/, assets/).
3. Diagnose Issues
Compare the skill's instructions against actual execution experience. Categorize problems:
| Category | Example |
|---|---|
| Outdated | Tool/API changed, deprecated method |
| Missing | Edge case encountered that skill didn't cover |
| Redundant | Steps Claude already knows, wasting context |
| Unclear | Ambiguous instruction that caused wrong action |
| Wrong | Incorrect assumption or factual error |
4. Generate Diff Preview
Show the user exactly what will change:
- Quote the original text
- Show the proposed replacement
- Explain why for each change
Do NOT modify the file until user confirms.
5. Apply Changes
After confirmation:
- Edit the SKILL.md (and bundled resources if needed)
- Preserve the skill's name and description structure unless the issue is there
- Keep changes minimal — fix what's broken, don't rewrite what works
6. Log the Improvement
Update or create ~/.claude/skills/learn/learned/<skill-name>.md:
If the file exists, append to the improvement record section:
### <YYYY-MM-DD>
- **Problem**: <what was wrong>
- **Fix**: <what was changed>
- **Source**: <task context that revealed the issue>
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 103 lines · 74 tokens per session scan A cd045037de5c
skill-improve is a skill published in the GitHub repository Yrzhe/claude-skills (33 stars, last pushed 3mo ago), licensed MIT. It adds 74 tokens to every session and 828 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…