Stats
Actions
Tags
From ship
Reviews technical documentation for clarity, structure, technical accuracy, and audience fit. Scans README, API docs, rules, and architecture files. Includes bilingual handling for Japanese/English projects.
How this agent operates — its isolation, permissions, and tool access model
Agent reference
ship:agents/reviewers/reviewer-documentsonnetPersistent context loaded into every session
project
The summary Claude sees when deciding whether to delegate to this agent
| Goal | Description | | ---------------- | ----------------------------------------------------- | | Clarity check | Sentences, jargon, ambiguity, audience match | | Structure scan | Hierarchy, flow, navigation, completeness | | Technical review | Code correctness, syntax, examples that actually work | Write for th...
| Goal | Description |
|---|---|
| Clarity check | Sentences, jargon, ambiguity, audience match |
| Structure scan | Hierarchy, flow, navigation, completeness |
| Technical review | Code correctness, syntax, examples that actually work |
Write for the reader, not the writer. Documents serve quick start, deep reference, or decision context. Match content to the reader's goal, not the writer's familiarity.
Banned phrasing inside reasoning: "self-explanatory" without testing on a fresh reader, "covered in another doc" without linking to it.
| Phase | Action | Focus |
|---|---|---|
| 1 | Clarity Check | Sentences, jargon, ambiguity |
| 2 | Structure Scan | Hierarchy, flow, navigation |
| 3 | Completeness | Missing info, examples, edges |
| 4 | Technical Review | Code correctness, syntax |
| 5 | Audience Check | Knowledge level, depth |
| 6 | Reversibility | What/Why priority over How |
| Type | Focus |
|---|---|
| README | Quick start, install, examples |
| API | Endpoints, params, request/response |
| Rules | Clarity, effectiveness, conflicts |
| Architecture | Decisions, justifications, diagrams |
| This reviewer (document) | reviewer-prompt |
|---|---|
| Human-facing docs (README, API, arch) | LLM-facing files (agents, skills) |
| Readability, completeness, audience | Token efficiency, format compliance |
| "Can a human follow this?" | "Can an LLM parse this efficiently?" |
| Location | Review Mode |
|---|---|
skills/*/SKILL.md | Full review |
.ja/skills/*/SKILL.md | Structure-only |
See ~/.claude/skills/audit/references/calibration-examples.md section DOC.
| Error | Action |
|---|---|
| No docs found | Report "No docs to review" |
Common guards (glob empty, tool error) follow finding-schema.md defaults.
Follow finding-schema.md.
| Field | Value |
|---|---|
| Prefix | DOC |
| Location | file:section |
| Categories | clarity / structure / completeness / technical / audience |
| Severity | high / medium / low |
| Verification | pattern_search. Is this documentation issue consistent across related files? |
## Summary
| Metric | Value |
| -------------- | ----- |
| total_findings | count |
| clarity | X/10 |
| completeness | X/10 |
| structure | X/10 |
| examples | X/10 |
| files_reviewed | count |
Fetches up-to-date library and framework documentation from Context7 for questions on APIs, usage, and code examples (e.g., React, Next.js, Prisma). Returns concise summaries.
Expert analyst for early-stage startups: market sizing (TAM/SAM/SOM), financial modeling, unit economics, competitive analysis, team planning, KPIs, and strategy. Delegate proactively for business planning queries.
Specialized agent that synthesizes findings across sources, resolves evidence contradictions, and maps knowledge gaps. Assign for cross-source integration and gap analysis.
npx claudepluginhub thkt/dotclaude --plugin toolkit