review-coordinator
Private Code Review dependency that structurally validates and aggregates independent worker findings into an inspectable Review brief without re-reviewing or…
Skill by jhonDoe15
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/jhondoe15-review-coordinator
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Node.js package
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/review-coordinator
What's inside
- Skill name
review-coordinator- Description
- Private Code Review dependency that structurally validates and aggregates independent worker findings into an inspectable Review brief without re-reviewing or changing conclusions. Use only when invoked by the Code Review lifecycle.
- License
- MIT
- Instructions
- 100 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (5)
- SKILL.md
- component.json · evals/
- index.js · evals/
- package-closure.json · evals/
- role.json · evals/
SKILL.md (first lines)
# Review Coordinator Assemble one Review brief from unchanged worker outputs. Structural aggregation is the only owned behavior. ## Required input Require the run manifest, immutable diff package, consolidation evidence, specialist-routing decisions, every planned worker output and concern coverage artifact, and the destination for retained artifacts. Each worker must name the same Ticket outcome references and immutable range. ## Required dependency Invoke `take-it-offline` by its exact canonical Skill name. If unavailable, stop with: `Missing internal dependency "take-it-offline"` Do not copy its behavior or use a test Adapter in production. ## Validate structure Before aggregation, validate: - exactly one Domain and one Engineering/Design worker with distinct identities and lens provenance, unless complete consolidation evidence permits one Combined worker, plus every available specialist worker selected by signals; - complete and matching Ticket outcome references and immutable range identity; - all nine Engineering Guidance concern dispositions from each worker, stored separately from findings; - ordered Review-region coverage and explicit worker-declared supersession whose source is an examined higher-level finding from the same worker and region; - every required finding field, confidence range, evidence reference, and acceptance-evidence statement; and - every required retained artifact reference. Any structural failure makes the run incomplete. Preserve valid partial worker artifacts and structured failure evidence, record every required completeness check by its canonical identity, and do not produce a Markdown Review brief. ## Group compatible duplicates Group findings only when workers identify the same underlying problem and their declared conclusions, levels, severities, confidence inputs, Context limits, affected scopes, impacts, and highest actionable fix directions are compatible. Keep every source finding identity and conclusion unchanged. Record why the findings were grouped. Keep incompatible conclusions, authority, severity, and other worker disagreements separate and visible. Group only exact duplicate guidance records. Preserve every distinct record for the same concern as a guidance disagreement; the coordinator neither chooses an authority nor rewrites its disposition. Apply only worker-declared supersession. Record each superseded finding or region, its declaring worker, affected Review region, and higher-level source. The coordinator does not invent, extend, or infer supersession. ## Sort and union Sort findings by: 1. Review level in Requirements & Expectations, Engineering & Architecture, then Code Quality order; 2. severity from highest to lowest; and 3. stable finding identity. Union coverage by worker, lens, Review region, Review level, and Engineering Guidance concern. Union means retaining all source coverage and disagreements, not reconciling them. Record a coordination disposition for every source finding. Allowed dispositions are retained, grouped with named compatible findings, or superseded by a worker-declared higher-level conclusion. ## Assemble the Review brief Write a concise Review summary followed by sorted findings, disagreements, coverage, Context limits, and acceptance evidence. Link the run manifest, immutable diff package, per-worker candidate streams, per-worker concern coverage, coordination dispositions, and completeness state. Use `take-it-offline` to return the final Markdown brief and artifact references to the caller. Preserve worker conclusions in the retained records and brief. ## Boundary The coordinator does not perform a second review, make findings, change severity or confidence, rewrite fix directions, inspect the change for new issues, edit code, publish comments, decompose remediation, or mutate ticket, pull-request, branch, dependency, or release state. ## Completion Complete only when every planned worker output passes every structural check, every source finding has one coordination disposition, coverage and disagreements are retained without loss, and the final Markdown brief and completeness state reference all retained artifacts.
From jhonDoe15/skills, MIT.
More from jhonDoe15/skills
- 0.570score
model-routing
jhonDoe15
Use before the first search or edit of work that needs more than two steps, and whenever bounded work might be handed to another model through `pi-dispatch`.
SkillAFreshness: AClaude Code +9 - 0.564score
incident-investigation
jhonDoe15
Evidence-led, read-only investigation of production incidents and hard-to-localize system or application bugs.
SkillAFreshness: AClaude Code +9 - 0.561score
skill-writing
jhonDoe15
Agent Skill outcome for creating or revising Agent Skills; excludes general agent-facing artifacts, fresh-context handoffs, installation, publication, and…
SkillAFreshness: AClaude Code +9 - 0.538score
readme-writing
jhonDoe15
Use when the user asks to write, rewrite, restructure, review, or correct a project's README.
SkillAFreshness: AClaude Code +9 - 0.529score
engineering-guidance
jhonDoe15
Engineering assessment of an existing technical approach or change for maintainability and standards; also used by declared design, implementation, and review…
SkillBFreshness: BClaude Code +9 - 0.526score
implementation-planning
jhonDoe15
Plan one bounded implementation ticket before code: produce a reviewed technical design and executable consumer-behavior TDD plan for another agent.
SkillBFreshness: BClaude Code +9 - 0.526score
architecture-review
jhonDoe15
Architecture review of existing code, a supplied technical design, or a PR change range.
SkillBFreshness: BClaude Code +9 - 0.524score
skill-evaluation
jhonDoe15
Private evaluation dependency for Agent Skill behavior claims.
SkillBFreshness: BClaude Code +9 - 0.524score
code-review
jhonDoe15
Reviews a complete Ticket outcome through fresh Domain and Engineering/Design lenses, then returns an evidence-backed read-only Review brief.
SkillBFreshness: BClaude Code +9 - 0.524score
pr-carver
jhonDoe15
Use when assessing an existing Git branch or pull request and recommending one PR, parallel PRs, or an ordered stack from its prerequisites, migration…
SkillBFreshness: BClaude Code +9 - 0.524score
implement
jhonDoe15
Use when a ready implementation blueprint and bounded scope need one isolated, TDD-driven patch with validation and a correction-ready implementation handoff.
SkillBFreshness: BClaude Code +9 - 0.523score
slice-plan
jhonDoe15
Private set-level decomposition consumed by Carve; not a user-facing planning outcome.
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 16
- Last commit (this folder)
- Sep 6, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/jhonDoe15/skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from jhonDoe15
- 0.570score
model-routing
jhonDoe15
Use before the first search or edit of work that needs more than two steps, and whenever bounded work might be handed to another model through `pi-dispatch`.
SkillAFreshness: AClaude Code +9 - 0.564score
incident-investigation
jhonDoe15
Evidence-led, read-only investigation of production incidents and hard-to-localize system or application bugs.
SkillAFreshness: AClaude Code +9 - 0.561score
skill-writing
jhonDoe15
Agent Skill outcome for creating or revising Agent Skills; excludes general agent-facing artifacts, fresh-context handoffs, installation, publication, and…
SkillAFreshness: AClaude Code +9 - 0.538score
readme-writing
jhonDoe15
Use when the user asks to write, rewrite, restructure, review, or correct a project's README.
SkillAFreshness: AClaude Code +9 - 0.529score
engineering-guidance
jhonDoe15
Engineering assessment of an existing technical approach or change for maintainability and standards; also used by declared design, implementation, and review…
SkillBFreshness: BClaude Code +9 - 0.526score
architecture-review
jhonDoe15
Architecture review of existing code, a supplied technical design, or a PR change range.
SkillBFreshness: BClaude Code +9
Cite this page
review-coordinator skill. Agent Mart. https://agentmart.dev/skills/jhondoe15-review-coordinator (last updated 2026-10-24)