← 返回 Skills 市场
iliaal

ia-document-review

作者 Ilia Alshanetsky · GitHub ↗ · v3.0.3 · MIT-0
cross-platform ✓ 安全检测通过
265
总下载
0
收藏
0
当前安装
10
版本数
在 OpenClaw 中安装
/install compound-eng-document-review
功能描述
Structural review of documents for gaps, clarity, completeness, and organization. Use when a brainstorm, plan, spec, ADR, or any doc needs polish before the...
使用说明 (SKILL.md)

Document Review

Improve brainstorm or plan documents through structured review.

Step 1: Get the Document

If a document path is provided: Read it, then proceed to Step 2.

If no document is specified: Ask which document to review, or look for the most recent brainstorm/plan in docs/brainstorms/ or docs/plans/.

Step 2: Assess

Read through the document and ask:

  • What is unclear?
  • What is unnecessary?
  • What decision is being avoided?
  • What assumptions are unstated?
  • Where could scope accidentally expand?
  • Is this technically feasible with the current architecture?
  • Are there security implications in what's proposed?

These questions surface issues. Don't fix yet--just note what you find.

Step 3: Activate Review Lenses

Based on the document's content, activate specialized review perspectives. Scan for signals and apply matching lenses:

Lens Signals What it checks
Product User-facing features, customer language, market claims, scope decisions Problem framing, value proposition clarity, whether scope matches stated goals
Design UI/UX references, user flows, wireframes, interaction descriptions Flow completeness, interaction gaps, accessibility considerations
Security Auth/authorization, API endpoints, PII, payments, tokens, encryption Auth model gaps, data exposure risks, missing threat considerations
Scope guardian Multiple priority tiers (P0/P1/P2), large requirement count (>8), stretch goals Scope creep, premature abstractions, features disguised as requirements
Adversarial >5 distinct requirements, explicit architectural decisions, high-stakes domains Unstated assumptions, optimistic estimates, single points of failure, missing failure modes

Activate a lens when ANY of its signals match. Most documents trigger 1-2 lenses; brainstorm notes may trigger none. When a lens is active, weave its checks into the assessment and evaluation steps rather than running it as a separate pass.

Step 4: Evaluate

Score the document against these criteria:

Criterion What to Check
Clarity Problem statement is clear, no vague language ("probably," "consider," "try to")
Completeness Required sections present, constraints stated, open questions flagged
Specificity Concrete enough for next step (brainstorm → can plan, plan → can implement)
YAGNI No hypothetical features, simplest approach chosen

If invoked within a workflow (after /ia-brainstorm or /ia-plan), also check:

  • User intent fidelity -- Document reflects what was discussed, assumptions validated

Step 5: Identify the Critical Improvement

Among everything found in Steps 2-4, does one issue stand out? If something would significantly improve the document's quality, this is the "must address" item. Highlight it prominently.

Step 6: Make Changes

Present your findings, then:

  1. Auto-fix minor issues (vague language, formatting) without asking
  2. Ask approval before substantive changes (restructuring, removing sections, changing meaning)
  3. Update the document inline--no separate files, no metadata sections

Simplification Guidance

Simplification is purposeful removal of unnecessary complexity, not shortening for its own sake.

Simplify when:

  • Content serves hypothetical future needs, not current ones
  • Sections repeat information already covered elsewhere
  • Detail exceeds what's needed to take the next step
  • Abstractions or structure add overhead without clarity

Don't simplify:

  • Constraints or edge cases that affect implementation
  • Rationale that explains why alternatives were rejected
  • Open questions that need resolution

Step 7: Reader Test (Optional)

For standalone documents that must be self-contained (onboarding guides, ADRs, external-facing docs), dispatch a zero-context sub-agent to simulate a first-time reader. The sub-agent has no conversation history — it sees only what a future reader would see.

How to run the test:

  1. Predict 5-10 reader questions from the document's stated goals — one per major section or decision. Mix three kinds:
    • Concrete retrieval: "What command sets up the dev environment?"
    • Decision rationale: "Why did we pick X over Y?"
    • Ambiguity probe: "Could a reader interpret \x3Cspecific phrase> in more than one way?"
  2. Dispatch a fresh sub-agent with the document attached and the questions. No prior context, no session history.
  3. Compare the sub-agent's answers against author intent. Also ask the sub-agent directly: "What feels ambiguous? What prior knowledge does this assume? Are there internal contradictions?"

Interpret results:

  • Correct, confident answers → document is self-contained for that question.
  • Wrong answer with high confidence → document actively misleads. Highest-priority fix.
  • Hedged or "insufficient information" → the document has a gap the author didn't notice. Fill it.
  • Sub-agent flags ambiguity the author didn't intend → reword for precision.

Skip for context-dependent docs (brainstorm notes, plan files, internal working docs) where the reader will always have prior context. The sub-agent test only adds value when the real reader has no other channel.

Step 8: Offer Next Action

After changes are complete, ask:

  1. Refine again - Another review pass
  2. Review complete - Document is ready

Iteration Guidance

After 2 refinement passes, recommend completion--diminishing returns are likely. If the user wants to continue, allow up to 4 passes total. After 4, stop and report "review converged -- further changes require new direction." Do not continue past 4 even on user request without a fresh framing.

Return control to the caller (workflow or user) after selection.

Constraints

  • Fix targeted sections, don't rewrite the whole document. If the structure is fundamentally broken, surface the structural problem and ask for permission to restructure.
  • Flag missing sections in your review, but don't add them. The user decides what to include.
  • Keep changes minimal. If a paragraph needs tightening, tighten it. Don't expand scope.
  • Review inline. No separate review files or metadata sections.

Success Criteria

  • Document read and scored on all four quality criteria
  • Relevant review lenses activated and checks applied
  • Critical improvements identified with specific suggestions
  • User presented with clear next-action choice (refine or complete)
  • Revised document saved if changes were approved
安全使用建议
This skill appears to do what it says (review and edit documents), but it can read repo paths and apply edits inline automatically and can spawn a fresh sub-agent to run reader tests. Before installing or invoking it: (1) confirm which directories/files it may access and restrict it to a safe project scope, (2) require explicit approval for any non-trivial edits (change 'auto-fix' behavior to always ask first if you want protection), (3) ensure your repo or files are backed up / under version control so you can revert edits, and (4) if you have sensitive data in docs, verify the sub-agent behavior and that no external endpoints will be used to transmit document contents. If you want stricter safety, request that auto-editing be disabled and that the skill only produce proposed edits rather than writing files.
功能分析
Type: OpenClaw Skill Name: compound-eng-document-review Version: 3.0.3 The skill bundle is a document review tool designed to analyze and improve the clarity, completeness, and structure of brainstorms and plans. It operates locally on files within the `docs/` directory and uses structured analytical 'lenses' to evaluate content, including a security lens to identify potential risks in the reviewed document. There are no indicators of data exfiltration, unauthorized command execution, or malicious prompt injection in SKILL.md or _meta.json.
能力标签
cryptocan-make-purchases
能力评估
Purpose & Capability
Name/description (document structural review) align with the instructions: read a document, apply review lenses, run a reader test, and suggest/perform edits. There are no unrelated environment variables, installs, or external services requested.
Instruction Scope
The SKILL.md explicitly directs the agent to read documents from provided paths or repo-like locations (docs/brainstorms/, docs/plans/) and to 'update the document inline' with auto-fixes for minor issues. While reading and editing files fits a review skill, automatic in-place edits and broad file-path search are powerfully scoped and can lead to unintended changes if not limited (no explicit safeguards or require-confirmation rules are in the instructions). The skill also instructs creating a zero-context 'sub-agent' to simulate a reader — that implies spawning additional agent runs which may increase blast radius if not controlled.
Install Mechanism
Instruction-only skill with no install spec and no code files; nothing will be downloaded or written to disk by an installer step. This is the lowest-risk install posture.
Credentials
No environment variables, credentials, or config paths are required. The skill does not request external secrets or unrelated system access in its manifest.
Persistence & Privilege
always:false and normal autonomous invocation. The skill does request persistent changes to documents ('update the document inline') and auto-fix behavior without asking for approval for minor edits — that is a level of write privilege to user files rather than persistent platform privileges. It's not requesting system-wide or cross-skill configuration changes.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install compound-eng-document-review
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /compound-eng-document-review 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v3.0.4
v3.0.4
v3.0.3
v3.0.3
v3.0.2
v3.0.2
v3.0.1
v3.0.1
v3.0.0
v3.0.0
v2.56.1
v2.56.1
v2.56.0
v2.56.0
v2.55.1
v2.55.1
v2.55.0
v2.55.0
v2.53.2
v2.53.2
v2.53.0
v2.53.0
元数据
Slug compound-eng-document-review
版本 3.0.3
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 10
常见问题

ia-document-review 是什么?

Structural review of documents for gaps, clarity, completeness, and organization. Use when a brainstorm, plan, spec, ADR, or any doc needs polish before the... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 265 次。

如何安装 ia-document-review?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install compound-eng-document-review」即可一键安装,无需额外配置。

ia-document-review 是免费的吗?

是的,ia-document-review 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

ia-document-review 支持哪些平台?

ia-document-review 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 ia-document-review?

由 Ilia Alshanetsky(@iliaal)开发并维护,当前版本 v3.0.3。

💬 留言讨论