skill-gen

A tool for creating one new skill in an existing collection of coding-agent instructions. A skill is a reusable set of instructions for handling a particular task.

In plain words
What is it for?
Use it to turn a request, issue, or idea into a new SKILL.md file and add it to the collection's skill map.
Why use it?
It prevents a new skill from duplicating existing ones or being added without understanding how the collection is organised. It also checks whether the proposed skill is independent and well designed.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/fagemx/prismstack/skill-gen
Any agent
npx skills add fagemx/prismstack --skill skill-gen
Clone the repo
git clone --depth 1 https://github.com/fagemx/prismstack

Made for: Claude Code, Codex.

Per session 133 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,329 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00133 $0.02329
Opus 5 $0.00067 $0.01164
Sonnet 5 $0.00027 $0.00466
Haiku 4.5 $0.00013 $0.00233

Measured 2d ago against content hash e26381499f7a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skill-gen 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 2d 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/skill-gen/SKILL.md · 213 lines

How it starts

The opening of the file, as written. The whole thing — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill Craftsman

你是一個 skill 工匠。一次只建一個 skill,精確地建。 你建出的每個 skill 都必須通過 3 項獨立性測試和 7 問設計檢查。 不要急著生成 — 先理解、再定位、再動手。

Mode Routing

解析參數:

  • /skill-gen {name} → 建造名為 {name} 的新 skill
  • /skill-gen → AskUserQuestion 詢問要建什麼
  • /skill-gen from-issue {url} → 從 issue 描述推導 skill 需求

Phase 0: Context Discovery

State

  • Reads: ~/.prismstack/projects/{slug}/.prismstack/skill-map.json (what's planned), domain-config.json (context)
  • Updates: skill-map.json (add new skill entry)

方法論(生成時必讀)

  • Read {PRISM_DIR}/shared/methodology/skill-craft-guide.md — skill 寫作原則、pattern、模板、實戰範例(含 review / bridge / control 各類型)

{PRISM_DIR} = ~/.claude/skills/prismstack 或 .claude/skills/prismstack

在做任何事之前,先搞清楚現有 domain 長什麼樣。

_SLUG=$(basename "$(git rev-parse --show-toplevel 2>/dev/null || pwd)")
_PROJECTS_DIR="${HOME}/.prismstack/projects/${_SLUG}"

# Search for existing skill map + routing table
ls "${_PROJECTS_DIR}"/skill-map-*.md 2>/dev/null
ls skills/*/SKILL.md 2>/dev/null

# Check for gaps in skill map vs actual skills
# (skill map may list skills not yet built)
  1. ls skills/ — 列出所有現有 skill
  2. 讀 routing skill(通常是 skills/{domain}-routing/SKILL.md
  3. skill-map.md(如果存在)— 比對已建 skill vs 計畫中的 skill,標出缺口
  4. 記錄:現有 skill 名稱、各自的觸發條件、artifact 命名
  5. 如果 skill map 中有尚未建立的 skill → 告知用戶,建議是否要建其中之一

STOP gate: 確認已理解現有 domain context。如果找不到 routing skill 或 skill map,告知用戶但繼續。


Phase 1: Intent + Independence Check

  1. 用 AskUserQuestion(四段格式)問清楚:

    • 這個 skill 要做什麼?
    • 誰會用它?什麼時候用?
    • 它產出什麼?
  2. 跑 3 項獨立性測試(見 references/generation-workflow.md):

    • 姿勢獨立?(跟現有 skill 的工作模式不同)
    • 產出獨立?(artifact 不重疊)
    • 觸發獨立?(trigger phrases 不重疊)
  3. 判定:

    • 3/3 PASS → 繼續建新 skill
    • < 3 → 建議合併到現有 skill,讓用戶決定

STOP gate: 用戶確認要建新 skill。


Phase 2: Generate

Input Quality Detection

判斷用戶對這個 skill 提供了多少資訊:

  • 只有名稱和用途 → Level 1
  • 有描述 + 上下游 → Level 2
  • 有案例、判斷標準、或參考材料 → Level 3-4

shared/methodology/skill-craft-guide.md How-To 10,按品質等級生成。 生成後在 completion 裡標記品質等級和提升建議。

Read the full file on GitHub · 213 lines

Files

What ships with it

2 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. 2d ago First seen · 213 lines · 133 tokens per session scan A e26381499f7a

Subscribe to this mod's changes

skill-gen is a skill published in the GitHub repository fagemx/prismstack (2 stars, last pushed 4mo ago), licensed MIT. It adds 133 tokens to every session and 2,329 once invoked, about $0.0007 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

ebay-sold-listings-search

All process output to user (progress updates, process notifications) follows the user's language.

browser-act/skills · 221 tokens

youtube-channel-business-email

YouTube channel business email and contact extractor: accepts a channel id (UCxxx), handle (@name), or URL; navigates the channel About view; extracts the business email from the description text plus full channel metadata (name, id, country, subscriber count, view count, video count, joined date, external links…

browser-act/skills · 324 tokens

webcrawler-deep-crawl

Deep-crawl any website from start URLs, return per-page LLM-ready text/markdown/HTML plus metadata (title, description, author, language, canonical URL, OG) and in-scope outbound links. Use when user mentions deep crawl website, recursive crawl, crawl a whole site, scrape entire website, scrape docs site, scrape…

browser-act/skills · 215 tokens

1688-product-detail

Extracts comprehensive wholesale product data from 1688.com product detail pages: title, tiered pricing, SKU variants with dimensions/weight, product images, seller info, shop scores, buyer protection, cross-border flags, product attributes, coupon/promotion data, and review stats. Use when user mentions 1688…

browser-act/skills · 212 tokens

amazon-listing-competitor-analysis-skill

This skill helps users analyze Amazon competitor listings by ASIN and produce structured competitive intelligence plus strategic opportunity points for their own go-to-market. The Agent should proactively apply this skill when users want to analyze a competitor Amazon listing by ASIN, understand what a top-ranked…

browser-act/skills · 172 tokens

amazon-product-detail

Amazon product detail page scraper: extract full product data from any open Amazon product detail URL (any /dp/{asin} or /gp/product/{asin} page across all Amazon regional TLDs) — returns asin, url, title, brand, price, listPrice, stars, reviewsCount, starsBreakdown (5/4/3/2/1 star percentages), answeredQuestions…

browser-act/skills · 472 tokens