documentation-lens
npx machina-cli add skill JoaoVyttorFelix/lightweight-ai-development-agent-skills/documentation-lens --openclawDocumentation Lens
Overview
Provide brief, neutral signals when documentation may be duplicated, misplaced, or over-explained. Prefer links over restatement. When new knowledge is intentionally recorded, expect a single canonical location with references linking to it rather than duplicating content.
Workflow
-
Discovery first
- Inspect the repository for existing documentation conventions (README structure, docs/ directories, architecture or decision docs, inline patterns).
- If conventions exist, align to them.
- If none exist, propose a minimal documentation convention as a suggestion only, and ask for confirmation before creating anything.
-
Identify knowledge intent
- Is the input new system knowledge, a restatement, or a mix?
-
Check for canonical placement
- Ask whether a canonical home exists (README, architecture, ADR).
- If unsure, state uncertainty explicitly.
-
Mode and persistence
- Ephemeral mode (default): review drafts, diffs, or proposed text and provide advisory signals only; write no files.
- Persistent mode (opt-in): write or edit documentation files only with explicit human instruction, aligned with discovered or agreed conventions.
-
Surface advisory signals
- Use phrasing like:
- “This looks similar to…”
- “You might consider linking to…”
- “This may fit better in…”
- Focus on conceptual duplication, misplaced background, or explanatory but non-authoritative docs.
- Avoid flagging minor repetition, enforcing style preferences, or large-scale semantic analysis.
- Do not prescribe exact edits.
- Use phrasing like:
-
Stop cleanly
- Present advisory signals (if any) and suggested canonical locations or links.
- If the human explicitly defers documentation changes, acknowledge and stop without revisiting.
- Do not rewrite or move content.
- Return control immediately.
Output format
Return a brief advisory assessment with one or more signals:
- Looks canonical (introduces genuinely new knowledge).
- Possible duplication detected (what is duplicated, where the canonical source may live).
- Verbosity / placement signal (content may be overly narrative or belong elsewhere). Optionally include suggested canonical locations or links.
Refusals
Politely refuse requests to:
- Rewrite or merge documentation.
- Enforce doc structure or templates.
- Block commits or PRs.
- Perform large-scale semantic analysis.
Tone
Calm, collegial, neutral. Advisory only. Prefer false negatives to false positives.
Source
git clone https://github.com/JoaoVyttorFelix/lightweight-ai-development-agent-skills/blob/main/documentation-lens/SKILL.mdView on GitHub Overview
Documentation Lens provides brief, neutral signals when documentation may be duplicated, misplaced, or over-explained. It favors linking to canonical sources over restatement. When new knowledge is recorded, expect a single canonical location with references.
How This Skill Works
It follows a discovery-first workflow to assess existing conventions, identify knowledge intent, and check for a canonical home (e.g., README, ADR, architecture docs). By default it runs in ephemeral mode, offering advisory signals without writing files; in persistent mode, changes are written only with explicit human instruction.
When to Use It
- Drafting or reviewing documentation to avoid duplication and misplacement
- Reviewing backlog items, ADRs, or explanatory text for single-source truth
- Evaluating whether a canonical location exists for new knowledge
- Addressing verbose or redundant background in docs
- Preparing documentation changes with clear references to canonical sources
Quick Start
- Step 1: Run a quick discovery to map docs conventions
- Step 2: Identify knowledge intent and check for a canonical home
- Step 3: Surface advisory signals and suggested canonical locations
Best Practices
- Scan for existing documentation conventions before proposing changes
- Favor linking to the canonical source rather than restating content
- Explicitly identify whether content is new knowledge or a restatement
- Check for a canonical home (README, ADR, architecture doc) and reference it
- Provide advisory signals only in ephemeral mode and avoid rewriting content
Example Use Cases
- PR includes a duplicate README section that mirrors an official doc
- ADRs and high-level docs cover the same decision in parallel
- Explainer text restates API docs without adding new intent
- Feature docs repeat information from an existing canonical wiki
- Drafts that add background narrative without a clear canonical destination