improve-skill

improve-skill is a skill for Claude Code from ANcpLua/ancplua-claude-plugins. It costs 61 tokens per session (746 once invoked), scanned A, original, MIT.

A planning tool that turns an evaluation of a local Claude Code skill into a rewrite brief. A skill is a folder containing instructions that guide an agent's work.

In plain words
What is it for?
Use it after evaluating a skill to group required fixes and prepare the instructions for a later editing pass.
Why use it?
It organizes evaluation findings into a concrete fix plan, so the author knows what to change first.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: mentions subagents.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the cc-plugin-eval plugin — 5 skills shipped together

Good fit Use it after evaluating a skill to group required fixes and prepare the instructions for a later editing pass.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add ANcpLua/ancplua-claude-plugins
Claude Code
/plugin install cc-plugin-eval

Made for: Claude Code.

Or install cc-plugin-eval, the plugin that ships this one along with the rest of its 5 skills.

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 improve-skill

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/ancplua/ancplua-claude-plugins/improve-skill"><img src="https://agentmods.dev/badge/skills/ancplua/ancplua-claude-plugins/improve-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 746 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 $0.00061 $0.00746
Opus 5 $0.00030 $0.00373
Sonnet 5 $0.00012 $0.00149
Haiku 4.5 $0.00006 $0.00075

Measured 9d ago against content hash d8cd647b495a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

improve-skill 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 9d 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.

plugins/cc-plugin-eval/skills/improve-skill/SKILL.md · 50 lines

How it starts

The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Improve Skill

Use this skill after cc-plugin-eval has already produced findings for a local skill.

The runnable commands below invoke the shipped script through the plugin root, which works in any checkout: node "${CLAUDE_PLUGIN_ROOT}/scripts/cc-plugin-eval.js" <command> <args>. Inline mentions of cc-plugin-eval <command> are shorthand for that same invocation; the bare cc-plugin-eval alias only exists if you ran npm link in the plugin directory.

What This Skill Does NOT Do

This skill does not perform LLM-driven rewrites. That is the job of the skill-creator skill (Anthropic's skill-creator@claude-plugins-official). cc-plugin-eval produces structured findings and a rewrite brief; skill-creator turns the brief into edits with subagent-driven evals and grading. Keep the two boundaries clear.

Workflow

  1. Run cc-plugin-eval analyze <skill-path> --brief-out ./skill-brief.json. The same payload is also produced by cc-plugin-eval improve <skill-path> --brief-out ./skill-brief.json, which writes the improvement brief as the top-level payload.
  2. Read the improvement brief. Group work into required fixes (severity error or fail) versus recommended fixes (severity warn or info).
  3. Hand the brief to skill-creator. That skill specializes in skill rewrites with subagent-driven evals.
  4. Re-run cc-plugin-eval analyze <skill-path> --output ./after.json and use cc-plugin-eval compare ./before.json ./after.json --format markdown to measure the delta.

Focus Areas

  • reduce trigger and invoke token costs (move bulky details into references, scripts, or helper files)
  • keep SKILL.md compact (target under 500 lines; hard limit at 800; reference threshold is 350)
  • improve trigger descriptions so Claude reliably routes to the skill (CC203, CC204)
  • fix broken relative links (CC211), oversized descriptions (CC202), and frontmatter issues (CC213)
  • normalize allowed-tools syntax (CC215) and add disable-model-invocation to task-style skills where appropriate (CC216)

Read the full file on GitHub · 50 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. 9d ago First seen · 50 lines · 61 tokens per session scan A d8cd647b495a

Subscribe to this mod's changes

improve-skill is a skill published in the GitHub repository ANcpLua/ancplua-claude-plugins (6 stars, last pushed 22d ago), licensed MIT. It adds 61 tokens to every session and 746 once invoked, about $0.0003 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 2026-08-31.

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