code-review
Reviews a complete Ticket outcome through fresh Domain and Engineering/Design lenses, then returns an evidence-backed read-only Review brief.
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-code-review
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
Use cases: design
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/code-review
What's inside
- Skill name
code-review- Description
- Reviews a complete Ticket outcome through fresh Domain and Engineering/Design lenses, then returns an evidence-backed read-only Review brief. Use for code review of a ticket, branch, pull request, or immutable implementation range. Excludes implementation, remediation planning, tracker or pull-request mutation, and reviewed-ticket lifecycle ownership.
- License
- MIT
- Instructions
- 117 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (11)
- SKILL.md
- component.json · evals/
- contract-coverage.js · evals/
- contract-coverage.json · evals/
- grader.js · evals/
- index.js · evals/
- outcome.json · evals/
- package-closure.json · evals/
- review-artifact.js · evals/
- role.json · evals/
- trigger.json · evals/
SKILL.md (first lines)
# Code Review Review one complete Ticket outcome without changing it. ## Required input Require: - originating requirements and durable references; - an immutable implementation range with base and head revisions; - the implementation handoff; and - validation evidence. Resolve the range to an immutable diff package before dispatch. Record every input artifact reference in the run manifest. Stop as incomplete if an input is missing, unreadable, mutable, or inconsistent with the range. ## Required dependencies Invoke `review-worker`, `review-coordinator`, and `take-it-offline` by their exact canonical Skill names. Stop before review execution with the first applicable failure: - `Missing internal dependency "review-worker"` - `Missing internal dependency "review-coordinator"` - `Missing internal dependency "take-it-offline"` Use no copied fallback behavior and never select a test Adapter in production. ## Plan fresh lenses Use separate fresh Review workers by default with these change-specific lenses: 1. **Domain** focuses on requirement meaning, user-visible behavior, domain invariants, and acceptance evidence. 2. **Engineering/Design** focuses on responsibilities, architecture, technology, compatibility, failure behavior, maintainability, and validation. One combined worker is valid only when cited mechanical evidence shows that behavior, contracts, state, dependencies, data, and failure handling are all unchanged. Record the mechanical check, observed comparison, and references for each dimension. A missing, false, or unsupported result requires separate Domain and Engineering/Design workers. Inspect change signals before dispatch. Add a fresh technology or specialist Review lens when the changed language, framework, protocol, risk, or requested scope requires it. Record the signals, capability decision, and assigned worker. When required specialist capability is unavailable, record that gap as a Context limit and run no general worker under the specialist label. Give each worker the complete Ticket outcome and the same immutable diff package. A worker receives the complete requirements, range, implementation handoff, validation evidence, repository authority, and input artifact references. Neither worker receives the other worker's output or conclusions. Each worker must resolve Engineering Guidance independently. Do not inherit the implementation handoff's concern dispositions. A missing planned lens or an unsupported combined worker is structurally invalid and cannot become a complete Review brief. ## Retain the review run Keep generated review artifacts outside the repository. Retain: - `run-manifest.json`, with run identity, complete Ticket outcome references, worker identities, lens provenance, immutable range, Ticket outcome fingerprint, consolidation evidence, specialist routing decisions, and an artifact index that binds each body by media type and SHA-256 digest; - `diff-package.json`, the immutable diff package and its base and head; - per-worker candidate streams containing complete finding records; - one per-worker concern coverage artifact, separate from findings; - `coordination.json`, containing coordination dispositions for every grouping, supersession, ordering, and retention decision; - `completeness.json`, containing the completeness state and structural checks; and - `review-brief.md`, the final Markdown brief and concise Review summary. Use `take-it-offline` to preserve the fresh-context handoffs and final artifact references. The owning Review role still defines and validates each review artifact contract. Resolve every indexed body before completion. Validate its schema or Markdown binding, content identity, run, worker, lens, immutable range, Ticket outcome fingerprint, and digest. A missing, stale, swapped, or inconsistent body makes the run incomplete. ## Coordinate structurally Give the coordinator every planned worker output unchanged with retained references. The coordinator validates structure, groups compatible duplicates, sorts findings, unions coverage, preserves worker conclusions, and assembles the Review brief. It performs no second review and makes no new finding. Return an incomplete result when a required worker fails, a required artifact is missing, a worker input identity differs, or any structural check fails. Retain partial worker records and structured failure evidence. Record the exact required completeness-check identities and their states, but do not create or present `review-brief.md` for an incomplete run. ## Read-only boundary Review may read repository, requirement, handoff, validation, and history evidence. It may write only generated review artifacts to temporary artifact storage. It does not: - edit source, tests, configuration, or requirements; - publish review comments; - change issue, branch, pull-request, dependency, or release topology; - decompose or dispatch remediation; or - claim a reviewed-ticket result. ## Completion Complete only when every required lens examined the same complete Ticket outcome, each worker independently resolved all Engineering Guidance concerns, all worker and coordinator structures validate, retained artifacts are inspectable, and the concise Review summary links the immutable range and final Review brief.
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
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 - 0.524score
skill-evaluation
jhonDoe15
Private evaluation dependency for Agent Skill behavior claims.
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 - 0.523score
maintaining-agent-guidance
jhonDoe15
Use when finishing or merging a substantial project change that may require durable updates to agent guidance.
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
code-review skill. Agent Mart. https://agentmart.dev/skills/jhondoe15-code-review (last updated 2026-10-24)