What is skill-evolution?

A system that records development context, failures, and session summaries, then suggests small improvements to the skills library. It proposes patches for human review instead of editing skills automatically.

Use it to capture run history, generate skill-improvement candidates, review suggested patches after major tasks, and prioritize areas where skills should improve.

It turns experience from completed tasks into concrete improvement suggestions while keeping a person in control of changes. Hooks are automated triggers that collect these development signals.

skill-evolution — Skill for Claude Code by Heyvhuang

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 Heyvhuang/ship-faster --skill skill-evolution

Clone the repo

git clone --depth 1 https://github.com/Heyvhuang/ship-faster

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/heyvhuang/ship-faster/skill-evolution.svg)](https://agentmods.dev/skills/heyvhuang/ship-faster/skill-evolution)

Your own site

<a href="https://agentmods.dev/skills/heyvhuang/ship-faster/skill-evolution"><img src="https://agentmods.dev/badge/skills/heyvhuang/ship-faster/skill-evolution.svg" alt="Measured on agentmods" height="20"></a>

Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,646 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 1 finding. 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.

Model	Per session	Once invoked
Fable 5.1	$0.00054	$0.01646
Opus 5	$0.00027	$0.00823
Sonnet 5	$0.00011	$0.00329
Haiku 4.5	$0.00005	$0.00165

Measured 7d ago against content hash 1b8fc3558b7d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade B, and why

skill-evolution scanned grade B with 1 finding 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 4 executable files (hooks/post-bash.sh, hooks/post-tool.sh, hooks/pre-tool.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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

Example (merge into `~/.claude/settings.json` or `<project>/.claude/settings.json`):

skills/skill-evolution/SKILL.md · 194 lines

How it starts

The opening of the file, as written. The whole thing — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Evolution

This skill makes the skills library evolve based on real development signals without auto-editing skills. The default output is a patch suggestion only.

Why it exists (solving "too passive")

Default hooks can only "log events" without automatically consolidating experience into skills.

The goal of this skill is to turn retrospectives into a fixed closing action:

At the end of each "big task", spend 60 seconds on Q&A confirmation: whether to optimize skills and which areas to prioritize
When user chooses "yes to optimize", use skill-improver to generate minimal patch suggestions based on real run artifacts (still no auto-editing of skill library)

Default strategy

Capture context and failures into run artifacts
Generate evolution candidates
Use skill-improver to propose a minimal patch
Human reviews and applies the patch

Global hooks (recommended)

Hooks live in: ~/.claude/skills/skill-evolution/hooks/

Add to your global settings (or project settings) so hooks run automatically.

Example (merge into ~/.claude/settings.json or <project>/.claude/settings.json):

Evolution settings

Configure behavior via ~/.claude/skills/skill-evolution/hooks/settings.json:

{
  "min_fail_count": 2,
  "ignore_tool_errors": true,
  "noise_filters": {
    "ignore_patterns": [
      "typescript: type.*already exists",
      "eslint:.*no-unused-vars.*react",
      "prettier:.*prettier-ignore"
    ],
    "max_failures_per_run": 20,
    "recent_only": true,
    "recent_window_minutes": 60
  },
  "output_format": {
    "summary_only": false,
    "include_context": true,
    "include_recent_failures": 20,
    "sort_by": "frequency"
  }
}

Settings explanation:

min_fail_count: Minimum occurrences of a single error type before generating a candidate
ignore_tool_errors: Whether to ignore tool-level errors (vs user code errors)
noise_filters.ignore_patterns: List of regex patterns to ignore
max_failures_per_run: Maximum failures to record per session (prevent explosion)
recent_only: Only look at failures within recent time window
recent_window_minutes: Only count failures within the last N minutes
output_format: Controls evolution-candidates.md output format

Read the full file on GitHub · 194 lines

Files

What ships with it

6 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.

7d ago First seen · 194 lines · 54 tokens per session scan B 1b8fc3558b7d

Subscribe to this mod's changes

skill-evolution is a skill published in the GitHub repository Heyvhuang/ship-faster (339 stars, last pushed 22d ago), licensed MIT. It adds 54 tokens to every session and 1,646 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Building agents

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

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.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 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

skill-evolution