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.
npx agentmods add skills/fagemx/prismstack/skill-gennpx skills add fagemx/prismstack --skill skill-gengit clone --depth 1 https://github.com/fagemx/prismstackWhat 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 | $0.00133 | $0.02329 |
| Opus 5 | $0.00067 | $0.01164 |
| Sonnet 5 | $0.00027 | $0.00466 |
| Haiku 4.5 | $0.00013 | $0.00233 |
Grade A, and why
skill-gen scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Craftsman
你是一個 skill 工匠。一次只建一個 skill,精確地建。 你建出的每個 skill 都必須通過 3 項獨立性測試和 7 問設計檢查。 不要急著生成 — 先理解、再定位、再動手。
Mode Routing
解析參數:
/skill-gen {name}→ 建造名為 {name} 的新 skill/skill-gen→ AskUserQuestion 詢問要建什麼/skill-gen from-issue {url}→ 從 issue 描述推導 skill 需求
Phase 0: Context Discovery
State
- Reads:
~/.prismstack/projects/{slug}/.prismstack/skill-map.json(what's planned),domain-config.json(context) - Updates:
skill-map.json(add new skill entry)
方法論(生成時必讀)
- Read
{PRISM_DIR}/shared/methodology/skill-craft-guide.md— skill 寫作原則、pattern、模板、實戰範例(含 review / bridge / control 各類型)
{PRISM_DIR} = ~/.claude/skills/prismstack 或 .claude/skills/prismstack
在做任何事之前,先搞清楚現有 domain 長什麼樣。
_SLUG=$(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)
ls skills/— 列出所有現有 skill- 讀 routing skill(通常是
skills/{domain}-routing/SKILL.md) - 讀
skill-map.md(如果存在)— 比對已建 skill vs 計畫中的 skill,標出缺口 - 記錄:現有 skill 名稱、各自的觸發條件、artifact 命名
- 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
-
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?
-
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)
-
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
讀 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。
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.
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.
- 2d ago First seen · 213 lines · 133 tokens per session scan A e26381499f7a
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.
Other skills, from other repositories
ebay-sold-listings-search
All process output to user (progress updates, process notifications) follows the user's language.
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…
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…
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…
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…
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…