improve-skill

improve-skill is a skill for Claude Code from mgiovani/cc-arsenal. It costs 178 tokens per session (2,299 once invoked), scanned A, original, MIT.

A workflow for improving an existing coding-agent skill against a defined authoring standard, while keeping an unchanged copy of the original for comparison.

In plain words
What is it for?
Use it to revise a skill’s instructions and references, add or upgrade its evaluations, run comparisons, and check whether the revised version actually improves.
Why use it?
It replaces subjective rewrite claims with before-and-after evidence and prevents evaluations from being altered just to make results look better.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions subagents; names the AskUserQuestion tool.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is uv run skills/create-skill/scripts/quick_validate.py skills/<name>.

Part of the cc-arsenal plugin — 53 skills shipped together

Good fit Use it to revise a skill’s instructions and references, add or upgrade its evaluations, run comparisons, and check whether the revised version actually improves.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/mgiovani/cc-arsenal
agentmods
npx agentmods add skills/mgiovani/cc-arsenal/improve-skill

Made for: Claude Code.

Or install cc-arsenal, the plugin that ships this one along with the rest of its 53 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/mgiovani/cc-arsenal/improve-skill.svg)](https://agentmods.dev/skills/mgiovani/cc-arsenal/improve-skill)
Your own site
<a href="https://agentmods.dev/skills/mgiovani/cc-arsenal/improve-skill"><img src="https://agentmods.dev/badge/skills/mgiovani/cc-arsenal/improve-skill.svg" alt="Measured on agentmods" height="20"></a>
Per session 178 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,299 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Rogue Agent · line 47
    Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.
    Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
How audits are shown
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 $0.00178 $0.02299
Opus 5 $0.00089 $0.01149
Sonnet 5 $0.00036 $0.00460
Haiku 4.5 $0.00018 $0.00230

Measured 7d ago against content hash 5e86866cbb68, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, 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 7d 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.

skills/improve-skill/SKILL.md · 103 lines

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.

Improve Skill

Take a skill that already exists and bring it up to the current authoring standard: with a frozen baseline and a measured comparison, not just a confident rewrite. Every claim of "better" in your final report must trace to a validator run or a grading result you actually produced this session.

Ground rules

  • Snapshot before you touch anything, and never touch the snapshot again. Once skill-snapshot/ exists for a skill, it is read-only for the rest of the run: every later step (rewrite, iteration, feedback pass) reads it for comparison and never writes to it. If a later step wants to "fix" the baseline to make a comparison look better, that is overfitting to the eval, not improving the skill: refuse and explain why.
  • Never edit an eval's prompt or assertions to make a failing run pass. If a rewritten skill fails an assertion, fix the skill (SKILL.md, references, description) or, if the assertion itself was wrong when it was written, say so explicitly and get the user's sign-off before changing it: silently loosening an assertion after seeing it fail is the one move that makes every later benchmark meaningless.
  • Judgment, not rewrite-for-rewrite's-sake. A skill that's already close to the rubric gets a small diff, not a fresh draft. Read it fully before deciding what's actually deficient: most of the value here is in the delta, not the word count changed.
  • This skill never commits, pushes, or force-updates anything. Its output is a modified skill directory plus a benchmark report. When the user is ready to save the change, they invoke git-commit or ship separately: do not run git commit yourself even if the user says "looks good, ship it," because that phrase in this context is about the skill quality, not a request to commit.

Workflow

1. Scope

Identify which skill(s) to improve: a name the user gave, a path, or "audit all skills" (if a repo-wide audit workflow already exists here, e.g. .claude/workflows/arsenal-audit.js, its per-skill findings are a good prioritized starting list; don't re-derive that scoring yourself, just read its output). For each target, confirm skills/<name>/SKILL.md exists: if it doesn't, stop and say so; this skill only improves skills that already exist (a brand-new skill is create-skill's job).

Read the full file on GitHub · 103 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 7d ago First seen · 103 lines · 178 tokens per session scan A 5e86866cbb68

Subscribe to this mod's changes

improve-skill is a skill published in the GitHub repository mgiovani/cc-arsenal (7 stars, last pushed 7d ago), licensed MIT. It adds 178 tokens to every session and 2,299 once invoked, about $0.0009 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

dataforseo

Agent-callable DataForSEO tools — Google SERP results, keyword and domain analytics, backlinks, Google Maps business data, on-page audits, and AI-search visibility (LLM answers + brand mentions). Use when the user wants SEO or AI-search data, even if they don't name DataForSEO.

zapier/connectors · 65 tokens

gitlab

Agent-callable GitLab tools — manage issues and merge requests, review diffs, commit files, run pipelines, and search. Use when the user mentions GitLab or wants to review or merge an MR, commit code, run CI, or manage issues — even if they don't name GitLab explicitly.

zapier/connectors · 64 tokens

algolia

Agent-callable Algolia tools — index records, search and browse them, manage index settings, synonyms, and query rules, and read AI recommendations.

zapier/connectors · 33 tokens

alpaca

Agent-callable Alpaca trading tools — place and manage stock, crypto, and options orders, read account balances, positions, and portfolio history, look up assets and market hours, and read watchlists. Use when the user mentions Alpaca or wants to trade or inspect a brokerage account, even if they don't name Alpaca…

zapier/connectors · 70 tokens

discord

Agent-callable Discord tools — send and manage messages, start threads and forum posts, manage channels, members, and roles, and post via webhooks. Use when the user mentions Discord or wants to post, read, or manage Discord servers, channels, or members, even if they don't name Discord explicitly.

zapier/connectors · 64 tokens

dropbox

Agent-callable Dropbox tools — upload, organize, find, and share files and folders. Use when the user wants to manage Dropbox content (save, move, search, share, list, or read files), including requests that don't name Dropbox explicitly, e.g. "save this report to my cloud storage" or "share that folder with Sam".

zapier/connectors · 73 tokens