跳到正文
cccskills
免费在 GitHub 公开中文介绍

doc-maintenance

将近期git历史与README、规格和产品文档对照,查找遗漏功能及过时说明,以最少的事实性修改修正偏差,保留原有文风和结构,并整理为供审核的PR。

原文查看原文说明

Audit README, SPEC, and PRODUCT docs against recent git history for drift and make minimal PR-ready edits. Use when asked to review docs for accuracy, after major feature merges, or on a schedule.

AI 评分80分/ 100查看安装方法

适用场景

  • 发布后检查文档
  • 合并重要功能后更新说明
  • 修正路线图和支持状态
  • 定期核查文档准确性

中文介绍

功能

对照近期git历史与README.md、doc/SPEC.md、doc/PRODUCT.md,查找并修正文档与实现的偏差。检查新增功能是否遗漏、已实现功能是否仍标为“不支持”或“计划中”,同时核查安装使用步骤及集成说明,将必要修改整理为PR,即供审核的拉取请求。

适用场景

适合发布后、合并重要功能后或每周检查文档时使用。会记录上次审核的提交,便于持续复查;首次运行从过去60天的历史开始。

使用示例

  • “将近期变更与README对照,修正过时说明。”
  • “检查哪些已实现功能仍留在路线图中。”

注意事项

目标仓库须有git历史,创建PR使用gh。修改仅限事实准确性,并保留现有文风和结构。不新增章节,也不全面重写;大幅补充内容会作为后续工作报告。开发者文档、发布说明和技能文件等不在检查范围内。

本介绍由 AI(OpenAI Codex)根据公开的 SKILL.md 撰写。准确的规格请查看下方原文。

客观评估

AI 仅根据 SKILL.md 的内容,从 4 个方面进行了评估。星标数和热度不计入评估。

指令清晰度能否看出何时使用、做什么
A良好明确用于定期检查或功能合并后,修正三个指定文档与实现的偏差。
步骤具体性步骤、输入输出和示例是否具体
A良好提供历史获取、变更分类、最小编辑、gh pr create及结果报告步骤。
安全性发送数据、删除文件、执行命令等是否有说明
B部分不足限制了编辑范围,但git push及当前分支的游标提交没有确认步骤。
安装难易度所需工具和 API 密钥是否少且有说明
B部分不足提供使用git和gh的命令,但未说明gh的安装与认证。

总分按每项 A=25 分、B=15 分、C=5 分相加。 由 AI(OpenAI Codex)于 2026年10月20日 评估。仅供参考,安装前请同时查看原文。

如果您认为评估有误,请申请复核

请写明哪一项有误以及原因。无需登录。我们会对照 SKILL.md 重新评估,并在此处更新结果。

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

包含的文件(3)

  • SKILL.md6.5 KB
  • references/audit-checklist.md2.7 KB
  • references/section-map.md1.4 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Doc Maintenance Skill

Detect documentation drift and fix it via PR — no rewrites, no churn.

When to Use

  • Periodic doc review (e.g. weekly or after releases)
  • After major feature merges
  • When asked "are our docs up to date?"
  • When asked to audit README / SPEC / PRODUCT accuracy

Target Documents

DocumentPathWhat matters
READMEREADME.mdFeatures table, roadmap, quickstart, "what is" accuracy, "works with" table
SPECdoc/SPEC.mdNo false "not supported" claims, major model/schema accuracy
PRODUCTdoc/PRODUCT.mdCore concepts, feature list, principles accuracy

Out of scope: DEVELOPING.md, DATABASE.md, CLI.md, doc/plans/, skill files, release notes. These are dev-facing or ephemeral — lower risk of user-facing confusion.

Workflow

Step 1 — Detect what changed

Find the last review cursor:

# Read the last-reviewed commit SHA
CURSOR_FILE=".doc-review-cursor"
if [ -f "$CURSOR_FILE" ]; then
  LAST_SHA=$(cat "$CURSOR_FILE" | head -1)
else
  # First run: look back 60 days
  LAST_SHA=$(git log --format="%H" --after="60 days ago" --reverse | head -1)
fi

Then gather commits since the cursor:

git log "$LAST_SHA"..HEAD --oneline --no-merges

Step 2 — Classify changes

Scan commit messages and changed files. Categorize into:

  • Feature — new capabilities (keywords: feat, add, implement, support)
  • Breaking — removed/renamed things (keywords: remove, breaking, drop, rename)
  • Structural — new directories, config changes, new adapters, new CLI commands

Ignore: refactors, test-only changes, CI config, dependency bumps, doc-only changes, style/formatting commits. These don't affect doc accuracy.

For borderline cases, check the actual diff — a commit titled "refactor: X" that adds a new public API is a feature.

Step 3 — Build a change summary

Produce a concise list like:

Since last review (<sha>, <date>):
- FEATURE: Plugin system merged (runtime, SDK, CLI, slots, event bridge)
- FEATURE: Project archiving added
- BREAKING: Removed legacy webhook adapter
- STRUCTURAL: New .agents/skills/ directory convention

If there are no notable changes, skip to Step 7 (update cursor and exit).

Step 4 — Audit each target doc

For each target document, read it fully and cross-reference against the change summary. Check for:

  1. False negatives — major shipped features not mentioned at all
  2. False positives — features listed as "coming soon" / "roadmap" / "planned" / "not supported" / "TBD" that already shipped
  3. Quickstart accuracy — install commands, prereqs, and startup instructions still correct (README only)
  4. Feature table accuracy — does the features section reflect current capabilities? (README only)
  5. Works-with accuracy — are supported adapters/integrations listed correctly?

Use references/audit-checklist.md as the structured checklist. Use references/section-map.md to know where to look for each feature area.

Step 5 — Create branch and apply minimal edits

# Create a branch for the doc updates
BRANCH="docs/maintenance-$(date +%Y%m%d)"
git checkout -b "$BRANCH"

Apply only the edits needed to fix drift. Rules:

  • Minimal patches only. Fix inaccuracies, don't rewrite sections.
  • Preserve voice and style. Match the existing tone of each document.
  • No cosmetic changes. Don't fix typos, reformat tables, or reorganize sections unless they're part of a factual fix.
  • No new sections. If a feature needs a whole new section, note it in the PR description as a follow-up — don't add it in a maintenance pass.
  • Roadmap items: Move shipped features out of Roadmap. Add a brief mention in the appropriate existing section if there isn't one already. Don't add long descriptions.

Step 6 — Open a PR

Commit the changes and open a PR:

git add README.md doc/SPEC.md doc/PRODUCT.md .doc-review-cursor
git commit -m "docs: update documentation for accuracy

- [list each fix briefly]

Co-Authored-By: Paperclip <noreply@paperclip.ing>"

git push -u origin "$BRANCH"

gh pr create \
  --title "docs: periodic documentation accuracy update" \
  --body "$(cat <<'EOF'
## Summary
Automated doc maintenance pass. Fixes documentation drift detected since
last review.

### Changes
- [list each fix]

### Change summary (since last review)
- [list notable code changes that triggered doc updates]

## Review notes
- Only factual accuracy fixes — no style/cosmetic changes
- Preserves existing voice and structure
- Larger doc additions (new sections, tutorials) noted as follow-ups

🤖 Generated by doc-maintenance skill
EOF
)"

Step 7 — Update the cursor

After a successful audit (whether or not edits were needed), update the cursor:

git rev-parse HEAD > .doc-review-cursor

If edits were made, this is already committed in the PR branch. If no edits were needed, commit the cursor update to the current branch.

Change Classification Rules

SignalCategoryDoc update needed?
feat:, add, implement, support in messageFeatureYes if user-facing
remove, drop, breaking, !: in messageBreakingYes
New top-level directory or config fileStructuralMaybe
fix:, bugfixFixNo (unless it changes behavior described in docs)
refactor:, chore:, ci:, test:MaintenanceNo
docs:Doc changeNo (already handled)
Dependency bumps onlyMaintenanceNo

Patch Style Guide

  • Fix the fact, not the prose
  • If removing a roadmap item, don't leave a gap — remove the bullet cleanly
  • If adding a feature mention, match the format of surrounding entries (e.g. if features are in a table, add a table row)
  • Keep README changes especially minimal — it shouldn't churn often
  • For SPEC/PRODUCT, prefer updating existing statements over adding new ones (e.g. change "not supported in V1" to "supported via X" rather than adding a new section)

Output

When the skill completes, report:

  • How many commits were scanned
  • How many notable changes were found
  • How many doc edits were made (and to which files)
  • PR link (if edits were made)
  • Any follow-up items that need larger doc work

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

add-product-e2e-eval

免费有简介AI 评分 90分

为Paperclip新增或扩展贯穿真实浏览器、服务器、数据库和runner的端到端评估,整理测试数据、判定条件与证据,并在现有报告中查看操作结果。

  • 新增完整用户操作流程的评估
  • 更新测试数据与判定条件
  • 在评估报告中加入截图和产物
paperclipai/paperclip10.6万2026年10月22日 更新

add-runner-eval

免费有简介AI 评分 90分

为Paperclip Runner添加或扩展行为评估,定义判定条件、执行目标和报告验证数据,利用正常及异常证据验证结果,并保留执行记录与费用。

  • 添加Runner行为评估
  • 用有效与无效证据检验判定
  • 更新执行列表和持续评估
paperclipai/paperclip10.6万2026年10月22日 更新

agent-browser

免费有简介AI 评分 90分

通过实际浏览器操作网页和应用,检查界面显示与运行情况。结合截图、简单表单填写、错误及网络请求记录,帮助复现问题并确认操作结果。

  • 检查界面修改后的显示效果
  • 读取由JavaScript渲染的内容
  • 复现界面问题并记录错误
paperclipai/paperclip10.6万2026年10月22日 更新

agentmail

免费有简介AI 评分 100分

通过 Paperclip 分配的 AgentMail 收件箱,查看任务关联邮件、发送新邮件或回复,并核查投递结果;重试时保留相同标识,避免重复发送。

  • 查看所负责任务关联的邮件
  • 从分配的收件箱发送新邮件
  • 回复会话中的指定邮件
paperclipai/paperclip10.6万2026年10月22日 更新

check-pr

免费有简介AI 评分 80分

检查GitHub、GitLab和Perforce变更中的评审意见、自动检查失败及说明缺漏,整理待办事项,并按请求协助修改和解决已处理的讨论。

  • 提交变更前进行检查
  • 确认失败的检查和待修改项
  • 整理人工及机器人评审意见
paperclipai/paperclip10.6万2026年10月22日 更新

company-creator

免费有简介AI 评分 100分

根据构想或现有代码仓库,梳理AI智能体的职责、汇报关系与工作交接,生成符合规范的公司或团队文件包,供组织协作和导入Paperclip使用。

  • 从构想建立智能体公司
  • 将代码仓库整理为团队
  • 设计职责分工与工作交接
paperclipai/paperclip10.6万2026年10月22日 更新

查看 paperclipai 的全部技能

报告此技能的问题