skill-improve

skill-improve is a skill for Claude Code from cenconq25/claude-code-app-studio. It costs 49 tokens per session (1,540 once invoked), scanned A, original, MIT.

A maintenance tool for improving SKILL.md files, the instruction files that define coding-agent skills. It checks their structure, suggests focused changes, tests the result, and keeps or reverses the changes based on the outcome.

In plain words
What is it for?
Use it to lint one skill or the whole skill library, propose and apply targeted fixes, and re-test the files. It can also run in a check-only mode.
Why use it?
It helps when a skill produces poor results, no longer follows current conventions, or needs checking after a template change. The test-and-compare loop reduces guesswork about whether a rewrite helped.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; reads .claude/ paths; names the AskUserQuestion tool.

Good fit Use it to lint one skill or the whole skill library, propose and apply targeted fixes, and re-test the files. It can also run in a check-only mode.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/cenconq25/claude-code-app-studio/skill-improve
Install

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.

Any agent
npx skills add cenconq25/claude-code-app-studio --skill skill-improve
Clone the repo
git clone --depth 1 https://github.com/cenconq25/claude-code-app-studio

Made for: Claude Code.

Wrote 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.

agentmods badge for skill-improve

README.md
[![agentmods](https://agentmods.dev/badge/skills/cenconq25/claude-code-app-studio/skill-improve/github.svg)](https://agentmods.dev/skills/cenconq25/claude-code-app-studio/skill-improve)
Your own site
<a href="https://agentmods.dev/skills/cenconq25/claude-code-app-studio/skill-improve"><img src="https://agentmods.dev/badge/skills/cenconq25/claude-code-app-studio/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.

agentmods 80×15 button for skill-improve

Your own site · 80×15
<a href="https://agentmods.dev/skills/cenconq25/claude-code-app-studio/skill-improve"><img src="https://agentmods.dev/badge/skills/cenconq25/claude-code-app-studio/skill-improve.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,540 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00049 $0.01540
Opus 5 $0.00024 $0.00770
Sonnet 5 $0.00010 $0.00308
Haiku 4.5 $0.00005 $0.00154

Measured 6d ago against content hash f156c6700672, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

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 6d 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.

.claude/skills/skill-improve/SKILL.md · 241 lines

How it starts

The opening of the file, as written. The whole thing — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill Improve

A maintenance skill for the skill library itself. Combines static linting (frontmatter compliance, structure rules) with a fix-test-keep loop. Use when an existing skill is producing poor results, when template structure changes and skills need to follow, or when a skill has decayed against new conventions.


Phase 1: Pick the Target

Parse the argument:

  • <skill-id> — work on that skill at .claude/skills/<id>/SKILL.md.
  • --all — iterate through every skill in the directory.
  • --static-only — run only the linter, no rewrites.

If no argument is provided, list every skill and ask the user.

Read in parallel:

  • The target SKILL.md.
  • A reference set of skills already known to be in good shape (3-4 of the simplest, like /help and /sprint-status).
  • Any local skill-conventions.md if present.

Phase 2: Static Lint

Delegate the structural checks to /skill-test --mode static <skill-id>. That skill is the canonical lint runner for the library — it owns the frontmatter rules, body rules, and severity scoring. This skill consumes its report and decides what to fix.

Run:

/skill-test --mode static <skill-id>

Read the resulting verdict and the per-rule findings. Capture: rule id, severity (BLOCKER, WARNING, NIT), short description, suggested fix hint.

If /skill-test is unavailable for any reason, fall back to inlining the checklist (see /skill-test SKILL.md for the canonical rule set): frontmatter compliance (name, description, argument-hint, user-invocable, allowed-tools, model, agent), body compliance (H1, purpose paragraph, numbered phases, Quality Gates, Examples, Next Steps, line count 150-450, no emoji).


Phase 3: Convention Lint

Cross-check against the rest of the library:

  • Does the skill claim agents/tools that exist?
  • Does it reference paths that match the project's directory structure?
  • Does it use the project's standard verdict tiers (PASS/CONCERNS/FAIL or APPROVED/etc.)?
  • Does it use AskUserQuestion at decision points where the reference skills do?

Read the full file on GitHub · 241 lines

Changes

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.

  1. 6d ago First seen · 241 lines · 49 tokens per session scan A f156c6700672

Subscribe to this mod's changes

skill-improve is a skill published in the GitHub repository cenconq25/claude-code-app-studio (40 stars, last pushed 4mo ago), licensed MIT. It adds 49 tokens to every session and 1,540 once invoked, about $0.0002 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 2026-09-03.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

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…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens