skill-evolve

skill-evolve is a skill for Claude Code from XRenSiu/claude-code-forge. It costs 240 tokens per session (4,250 once invoked), scanned A, original, MIT.

A skill improvement process for structured instructions used by coding agents. It scores a SKILL.md file against nine criteria, compares agent results with and without the skill, then keeps or rolls back revisions based on the results.

In plain words
What is it for?
Use it to improve an existing agent skill, test its instructions against example prompts, record weak areas, and retain only revisions that improve the evaluation.
Why use it?
It replaces ad hoc prompt editing with repeated evaluation and guards against changes that make an agent perform worse.

Skill for Claude Code

Written for Claude Code: when-to-use in frontmatter. Also seen: mentions subagents.

Part of the skill-evolve plugin — 1 skill shipped together

Good fit Use it to improve an existing agent skill, test its instructions against example prompts, record weak areas, and retain only revisions that improve the evaluation.

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

Made for: Claude Code.

Or install skill-evolve, the plugin that ships this one along with the rest of its 1 skill.

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-evolve

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/xrensiu/claude-code-forge/skill-evolve"><img src="https://agentmods.dev/badge/skills/xrensiu/claude-code-forge/skill-evolve.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 240 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,250 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 $0.00240 $0.04250
Opus 5.5 $0.00096 $0.01700
Sonnet 5.5 $0.00048 $0.00850
Haiku 4.5 $0.00024 $0.00425

Measured 1mo ago against content hash a7e17a413f6a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

skill-evolve 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 1mo 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/skill-evolve/skills/skill-evolve/SKILL.md · 219 lines

How it starts

The opening of the file, as written. The whole thing — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.

skill-evolve

让一个 skill 从 1 分变 100 分,不靠灵感,靠循环。

Announce at start: "I'm using the skill-evolve skill to run the 9-dimension rubric (with no-skill baseline comparison) + ratchet hill-climbing loop on the target SKILL.md."

Skill(结构化 Prompt)和 ML 超参数一样,是可以被自动化搜索优化的参数空间。

Skills are searchable parameter spaces — same as ML hyperparameters.

它解决什么问题

写完一个 SKILL.md 之后,绝大多数人停在「能跑就行」。但「能跑」和「好用」之间有一条 30 分的鸿沟:触发不准、步骤含糊、边界没定义、激活了不知道先干啥。

人工反复打磨成本极高,且改一处不知道是不是变差了。本 skill 把这个过程自动化 + 防退化:

  • 自动化:9 维 rubric 直接告诉你哪里弱、改哪里
  • 防退化:每次改完独立打分,不升反降立刻回滚,分数只能涨不能跌(棘轮)
  • 防自欺:rubric 的三个高信号维(失败机制 / 可执行性 / 高风险黑名单)来自 SkillLens 实测,且每轮强制跑「带 skill vs 不带 skill」基线对比——刷分但实际拖累 agent(负迁移)会被当场抓出并回滚

灵感来自 Karpathy autoresearch(修改→训练→保留/回滚)、alchaincyf/darwin-skill(把范式迁移到 Skill 优化),以及微软 SkillLens(arXiv 2605.23899,46.4%→73.8% 的三维药方 + 负迁移发现)/ SkillOpt(arXiv 2605.23904,拒绝缓冲 + 慢更新记忆 + 文本学习率三个稳定性控制)。

输入与输出

输入:

  • 目标 skill 路径(必须包含 SKILL.md),例如 plugins/foo/skills/bar/
  • (可选)3 个已知测试 prompt + 期望输出方向(无则自动从 SKILL.md 推断)
  • (可选)目标分数(默认 90)/ 最大轮次(默认 15)/ 收敛阈值(默认连续 3 轮无提升)

输出:

  • .skill-evolve/<skill>/experiments.tsv —— 每轮:{round, dim_scores(9), total, negative_transfer, change_summary, kept_or_reverted, flags(dry_run/single_judge), commit_hash}
  • .skill-evolve/<skill>/baseline.md —— 初评全维度分数 + 最弱维度诊断 + 确认过的测试集
  • .skill-evolve/<skill>/learnings.md / dead-ends.md —— 滚动正/负反馈记忆
  • .skill-evolve/<skill>/final-report.md —— 终评 + 改进清单 + 前后对比 + 负迁移确认
  • 每轮 experiment: <desc> 前缀的 git commit(棘轮历史)

触发后立即做什么

1. 确认目标 skill 路径存在且包含 SKILL.md
2. 检查 git working tree 是否干净(脏树先暂存或提示用户处理)
3. 创建工作目录 .skill-evolve/<skill-name>/ 存放日志和报告
4. 初始化滚动记忆(移植自 SkillOpt):
   : > .skill-evolve/<skill-name>/learnings.md   # 已验证规律(正反馈)
   : > .skill-evolve/<skill-name>/dead-ends.md   # 已证伪改法(负反馈,禁重试)
5. 检查 Agent/subagent 工具是否可用;不可用 → 走 dry_run 降级模式(见 test-protocol)
6. 进入 Phase 0

Phase 0.5:测试 prompt 设计与确认(先于评估的门)

测试 prompt 的质量直接决定优化方向对不对(SkillLens:测试太弱会导致「分数虚高、实战还烂」)。所以在任何评估之前:

  1. 按 test-protocol「测试 prompt 自动生成」规则备出 3 个测试 prompt(happy path)+ 1 个边缘 prompt(相邻领域、超范围)
  2. 写入 baseline.md 的「测试集」区,展示给用户确认
  3. 用户可替换/补充更刁钻的 case。用户确认后才进入 Phase 0——这一步不许跳过

Read the full file on GitHub · 219 lines

Files

What ships with it

7 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. 1mo ago First seen · 219 lines · 240 tokens per session scan A a7e17a413f6a

Subscribe to this mod's changes

skill-evolve is a skill published in the GitHub repository XRenSiu/claude-code-forge (2 stars, last pushed 29d ago), licensed MIT. It adds 240 tokens to every session and 4,250 once invoked, about $0.0010 per session on Opus 5.5. 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 2026-09-05.

Related

Other skills, from other repositories

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

tika-eval-compare

Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".

apache/tika · 50 tokens

cua-driver

Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.

davidondrej/skills · 68 tokens

jetson-validate-image

Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.

NVIDIA/skills · 50 tokens

atmos-validation

Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.

cloudposse/atmos · 31 tokens

skill-benchmark

Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.

HoangNguyen0403/agent-skills-standard · 16 tokens