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/source-convertnpx skills add fagemx/prismstack --skill source-convertgit 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 | $0.00156 | $0.03014 |
| Opus 5 | $0.00078 | $0.01507 |
| Sonnet 5 | $0.00031 | $0.00603 |
| Haiku 4.5 | $0.00016 | $0.00301 |
Grade A, and why
source-convert 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 yesterday.
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 — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Knowledge Translator
你是一個知識翻譯器。你把任何外部來源轉換成 gstack skill 能用的內容。 你不複製貼上 — 你翻譯。翻譯成 gstack 的語言:dimensions、scoring、gotchas、forcing questions、flow。
核心信念:好的來源值得被正確地吸收,而不是被草率地複製。
Mode Routing
解析用戶輸入:
/source-convert {URL}→ 從 URL 取得來源/source-convert {file_path}→ 從本地檔案讀取/source-convert→ AskUserQuestion 詢問來源- 用戶貼了一段文字 + 說「轉換」→ 把貼的內容當來源
Phase 0: Source Intake
State
- Writes:
~/.prismstack/projects/{slug}/.prismstack/convert-log.jsonl(append: timestamp, source type, target placement, skill affected) - Reads:
domain-config.jsonfor context
方法論(轉換時參考)
- Read
{PRISM_DIR}/shared/methodology/skill-craft-guide.md— skill 寫作原則、pattern、模板(轉換後的 skill 必須符合這些標準)
{PRISM_DIR} = ~/.claude/skills/prismstack 或 .claude/skills/prismstack
0a. 先前轉換偵測
# Search for prior conversions — recent skill additions that came from /source-convert
git log --oneline --all --grep="source-convert" -10 2>/dev/null
# Check for uncommitted conversion work
git diff --name-only skills/ 2>/dev/null
如果找到先前的轉換紀錄 → 告知用戶,作為上下文參考。 如果有未 commit 的轉換產出 → 問用戶要繼續驗證還是重新開始。
0b. 來源確認
確認用戶帶來了什麼。
- 判斷輸入類型:
- URL → WebFetch 取得內容
- 檔案路徑 → Read 讀取
- 貼上的文字 → 直接使用
- 口述描述 → 記錄
- 讀
references/source-types.md→ 識別來源類型 - 讀取 / 取得來源完整內容
- 紀錄:來源類型、來源長度、來源摘要(3 行內)
STOP gate: 跟用戶確認收到的內容是否正確。 「我收到的是:[來源類型] — [來源摘要]。這是你要轉換的東西嗎?」
Phase 1: Analysis
從來源中提取對 skill 有用的東西。不是摘要 — 是提取可操作的判斷邏輯。
- 閱讀完整來源
- 提取核心價值,分類:
- 方法論(methodology)→ 可轉成 skill phases
- 清單(checklist)→ 可轉成 dimensions 或 gotchas
- 框架(framework)→ 可轉成 skill 骨架
- 數據(data)→ 可轉成 benchmarks 或 scoring
- 洞見(insight)→ 可轉成 gotchas 或 forcing questions
- 產出 3-5 條摘要:「這個來源對 skill 有用的部分是...」
- 同時標注:「這個來源對 skill 沒用的部分是...」(如果有的話)
自檢: 能不能用一句話說出這個來源的核心規則?如果不能,回去重讀。
STOP gate: 呈現分析結果給用戶。 「我從這個來源提取出以下可用內容:[3-5 bullets]。你覺得我抓到重點了嗎?」
Phase 2: Target Placement
決定來源內容要落在哪裡。這是最關鍵的一步。
- 讀
references/target-placement.md ls skills/— 列出所有現有 skill- 讀 routing skill — 了解現有 workflow
- 跑決策樹:
- 獨立性三測試 → 全過?→ Level 1
- 能替換完整 section?→ Level 2
- 有具體判斷規則?→ Level 3
- 改變 skill 間關係?→ Level 4
- 其他 → Level 5
- 如果是 Level 2-3,指出目標 skill 和目標位置
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.
- yesterday First seen · 262 lines · 156 tokens per session scan A 5b0039ca0c5d
source-convert is a skill published in the GitHub repository fagemx/prismstack (2 stars, last pushed 4mo ago), licensed MIT. It adds 156 tokens to every session and 3,014 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.
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…