Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Doc Status Sweep Method

ASecurity

要宣稱「docs 與狀態 X 一致」之前載入——特別是 milestone 收官記錄、契約政策翻轉(如 auto-merge 從關到開)之後的全庫狀態句清理。方法論來自同一軸線被 owner 連抓三輪漏網的實案(starledger PR #217→#218→#219)。

2 stars
0 votes
0 copies
0 views
Added 9/4/2026
ai-agentsdocumentation

Security Analysis

A100/100

Scanned 9/4/2026

$npx -y skills add F-e-u-e-r/opus-pack --skill doc-status-sweep-method --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Doc Status Sweep Method?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Doc Status Sweep Method
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/f-e-u-e-r-doc-status-sweep-method/badge)](https://www.skillsdirectory.com/skills/f-e-u-e-r-doc-status-sweep-method)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: doc-status-sweep-method
description: 要宣稱「docs 與狀態 X 一致」之前載入——特別是 milestone 收官記錄、契約政策翻轉(如 auto-merge 從關到開)之後的全庫狀態句清理。方法論來自同一軸線被 owner 連抓三輪漏網的實案(starledger PR #217→#218→#219)。
---

# 文件狀態掃蕩方法(class → stem → wrap-aware)

(驗證日 2026-07-30。這是**方法 skill**:三輪真實漏網的失敗模式各對應一條規則。)

## 三輪漏網的實案(starledger,2026-07-30 同日)

| 輪 | 掃法 | 漏掉的真實句子 | 為什麼漏 |
|---|---|---|---|
| #217 | 關鍵詞 `pending\|not yet` | 「Continue bounded, **manual backfill**…」「**Auto-merge stays disabled** in v1」 | 矛盾句不含你選的關鍵詞——狀態宣稱是**語意類**,不是詞表 |
| #218 | 語意類,但詞形只列 `human review`、`reviews and merges` | 「…publish through a **reviewed merge**」 | 同類**詞形變化**沒窮舉 |
| #219 | 補 `reviewed merge` 片語 | 同一句 | 片語**跨行折行**(`a reviewed\nmerge`)——單行 regex 連正確片語都抓不到 |

當時的不安全合理化(真實、勿重演):「掃過 `pending` 都乾淨了,documentation consistency
✅」——關鍵詞零命中被當成類別零殘留,連錯兩輪。

## 方法(宣稱一致性前的必經四步)

1. **定義類,不是詞表**:先用一句話寫下「什麼樣的句子與新狀態矛盾」(例:pre-auto-merge 時代
   的 present-tense 契約句),再從類推導檢索詞。
2. **掃詞幹**:`rg -in "review"` 而不是 `"reviewed merge"`——詞形變化(review/reviews/
   reviewed/reviewer)一網打盡,然後**逐一裁決每個命中**。
3. **keep-ledger**:合法保留的命中(機制語如 retry「pending」、歷史敘述、一次性程序)逐條
   列出+理由,引進 PR body——「保留」是裁決結果,不是漏掃。
4. **把零命中當可疑訊號**:片語 grep 零命中 ≠ 不存在——markdown 折行會拆散片語;改用單一
   有辨識度的**單詞**重掃一次再下結論。

**完成定義**:PR body 內含(a)可重跑的詞幹掃蕩指令、(b)修正清單 before/after、
(c)keep-ledger 全列附理由;re-run 該指令的命中恰好等於 keep-ledger。

## 正例(#219 最終形)

`rg -in "review" docs/P3-ai-spec.md docs/P3.2-executor-runbook.md` → 恰 3 命中,逐條裁決為
keep(bootstrap PR ×2、meta-rebase operator 覆核)=掃蕩收斂的可驗證定義。

## 再驗證

方法 skill 無 repo 狀態可驗;每次套用時,「再驗證」=把你自己的最終掃蕩指令與 keep-ledger
貼進 PR body,讓下一個人能一鍵重跑。

Attribution

F-e-u-e-rF-e-u-e-r
View sourceSee grades on GitHubMore from F-e-u-e-r →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698621 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →