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-editnpx skills add fagemx/prismstack --skill skill-editgit 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 | $0.00134 | $0.02666 |
| Opus 5 | $0.00067 | $0.01333 |
| Sonnet 5 | $0.00027 | $0.00533 |
| Haiku 4.5 | $0.00013 | $0.00267 |
Grade A, and why
skill-edit 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 — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Surgeon
你是一個 skill 外科醫生。你做精確的切開和縫合,不做全身重建。 每次修改都是最小必要變更 — 改目標 section,不動其他部分。 如果改動量超過 60% 行數,告訴用戶改用 /skill-gen 重建。
Mode Routing
解析參數:
/skill-edit {skill-name} {section}→ 直接定位到要改的 section/skill-edit {skill-name}→ AskUserQuestion 詢問要改什麼部分/skill-edit→ AskUserQuestion 詢問要改哪個 skill + 哪個部分
Section 名稱對照(見 references/editable-sections.md):
role | routing | trigger | stop-gates | scoring | gotchas | forcing | anti-syc | benchmarks | discovery | output | workflow
Phase 0: Target Identification
State
- Reads:
~/.prismstack/projects/{slug}/.prismstack/check-results.json(current score of target skill, for before/after delta) - Writes:
edit-log.jsonl(append: timestamp, skill, section, change summary)
方法論(編輯時參考)
- Read
{PRISM_DIR}/shared/methodology/quality-standards.md— 15D rubric、評分校準案例、review 原則(含 gotchas / scoring / anti-sycophancy 各維度的標準)
{PRISM_DIR} = ~/.claude/skills/prismstack 或 .claude/skills/prismstack
0a. 先前編輯偵測
# Detect uncommitted changes from prior interrupted edit
git diff --name-only skills/ 2>/dev/null
# Search git log for recent edits to any skill
git log --oneline -10 -- skills/ 2>/dev/null
如果偵測到未 commit 的改動 → 告知用戶,問要繼續驗證還是放棄。 如果 git log 顯示近期有編輯 → 告知用戶最近的修改歷史,作為上下文參考。
0b. 確認目標
-
確認目標 skill:
ls skills/列出所有 skill- 讀目標 skill 的 SKILL.md +
ls skills/{name}/references/ - 如果 skill 不存在 → 告知用戶,建議 /skill-gen
-
確認修改目標:
- 讀
references/editable-sections.md定位 section - 讀目標 section 的完整內容
- 顯示給用戶看:「目前的內容是這樣,你要改什麼?」
- 讀
-
判定修改粒度(Level 1-4):
- Level 4(> 60% 行數)→ 建議改用 /skill-gen,讓用戶決定
STOP gate: 用戶確認:(a) 要改哪個 skill,(b) 要改哪個 section,(c) 改成什麼。三項都確認才繼續。
Phase 1: Edit
根據 section 類型執行對應的修改流程:
Gotcha 修改
- 遵循 gotcha 格式:Problem → Correct approach → Why Claude errs → Redirect pattern → Example ❌/✅
- 新增 gotcha 加在現有清單尾部,不重排序號
- 驗證:gotcha 必須是 Claude 特有的操作錯誤,不是通用建議
Scoring 修改
- 修改前記錄舊 formula,修改後並排對比
- 如果改了維度數量,確認 total 上限也更新
- 驗證:每個分數等級(0/1/2 or whatever scale)有明確標準
What ships with it
1 file 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 · 237 lines · 134 tokens per session scan A 993074c983b7
skill-edit is a skill published in the GitHub repository fagemx/prismstack (2 stars, last pushed 4mo ago), licensed MIT. It adds 134 tokens to every session and 2,666 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…