skill-improver

skill-improver is a skill for Claude Code from LiozShor/claude-code-skills. It costs 157 tokens per session (2,879 once invoked), scanned A, original, MIT.

A reviewer for one existing agent skill, which is a set of instructions that guides an AI coding agent. It checks the skill's structure, wording, permissions, files, size, and tests.

In plain words
What is it for?
Use it to audit a skill or make safe improvements to its documentation and routing. Permission-expanding, destructive, or major behavioural changes require user approval.
Why use it?
It helps find unclear instructions, unsafe permissions, unused files, missing sections, and weak evaluation coverage before they cause unreliable agent behaviour.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

Good fit Use it to audit a skill or make safe improvements to its documentation and routing. Permission-expanding, destructive, or major behavioural changes require user approval.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/liozshor/claude-code-skills/skill-improver
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 LiozShor/claude-code-skills --skill skill-improver
Clone the repo
git clone --depth 1 https://github.com/LiozShor/claude-code-skills

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-improver

README.md
[![agentmods](https://agentmods.dev/badge/skills/liozshor/claude-code-skills/skill-improver.svg)](https://agentmods.dev/skills/liozshor/claude-code-skills/skill-improver)
Your own site
<a href="https://agentmods.dev/skills/liozshor/claude-code-skills/skill-improver"><img src="https://agentmods.dev/badge/skills/liozshor/claude-code-skills/skill-improver.svg" alt="Measured on agentmods" height="20"></a>
Per session 157 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,879 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 $0.00157 $0.02879
Opus 5 $0.00078 $0.01439
Sonnet 5 $0.00031 $0.00576
Haiku 4.5 $0.00016 $0.00288

Measured 7d ago against content hash 5c97ba61e5a5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

skill-improver 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.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/list-skill-evals.sh, scripts/review-skill-structure.sh, scripts/survey-skill-fleet.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skill-improver/SKILL.md · 182 lines

How it starts

The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill Improver

Inspect an existing agent skill and improve it safely. The goal is to make it more reliable, safer, clearer, easier to trigger correctly, and easier to evaluate. Preserve what works. Fix what is vague, risky, missing, or bloated. Do not rewrite aggressively just because you can.

Safety modes

Classify the requested work into one of four modes before touching anything:

  1. Review-only — read the skill and produce findings. No edits.
  2. Safe-edit — apply low-risk improvements that preserve intent: clearer wording, sharper trigger description, missing sections, formatting, stronger gotchas, more explicit output format.
  3. Permission-changing or destructive — ask the user before any change that expands allowed-tools, deletes files, removes major sections, alters core behavior, renames the skill, moves files, modifies scripts, or splits the skill.
  4. Structural-defect repair — adding missing required frontmatter fields (name, description, allowed-tools) is not a permission change; it is documentation of behavior the skill already exhibits. Infer the minimum tools the visible workflow uses (shell snippets ⇒ Bash; file creates ⇒ Write; file edits ⇒ Edit). Apply the fix and flag the inference in the diagnosis. Do not block on user approval for adding a missing field — only for expanding a field that is already present.

If the user's request is ambiguous, start in review-only mode and ask before editing.

When this triggers

Reviewing or improving EXISTING skills only. For greenfield skill creation, use skills-build.

Use this skill when the user asks to:

  • Check, audit, or review an existing skill or SKILL.md.
  • Improve triggers, descriptions, gotchas, gates, output format, or evaluation checklist.
  • Review or tighten allowed-tools permissions.
  • Validate folder structure (references/, assets/, scripts/).
  • Split an over-broad skill into focused ones.
  • Diagnose why a skill is not triggering or is triggering too often.
  • Refactor a skill without changing its purpose.
  • Audit the whole skill fleet at once ("which skills need work") — run scripts/survey-skill-fleet.sh first, then improve the worst offenders.

Read the full file on GitHub · 182 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. 7d ago First seen · 182 lines · 157 tokens per session scan A 5c97ba61e5a5

Subscribe to this mod's changes

skill-improver is a skill published in the GitHub repository LiozShor/claude-code-skills (2 stars, last pushed 19d ago), licensed MIT. It adds 157 tokens to every session and 2,879 once invoked, about $0.0008 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.