review-worker
Private Code Review dependency that examines a complete Ticket outcome through one change-specific Review lens and returns evidence-backed findings plus…
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-worker
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: testing
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-worker
What's inside
- Skill name
review-worker- Description
- Private Code Review dependency that examines a complete Ticket outcome through one change-specific Review lens and returns evidence-backed findings plus separate Engineering concern coverage. Use only when invoked by the Code Review lifecycle.
- License
- MIT
- Instructions
- 111 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 Worker Inspect one complete Ticket outcome through one assigned Review lens. Produce candidate findings and concern coverage. Do not coordinate other workers. ## Required input Require: - worker identity and lens provenance; - originating requirements and their artifact references; - immutable implementation range and diff package; - implementation handoff; - validation evidence; - applicable repository authority; and - the output artifact destination. Record the worker identity, lens, immutable range identity, and every input artifact reference examined. Stop with an incomplete worker result if any required input is missing or inconsistent. ## Required dependencies Invoke `engineering-guidance` and `take-it-offline` by their exact canonical Skill names. Stop before analysis with the first applicable failure: - `Missing internal dependency "engineering-guidance"` - `Missing internal dependency "take-it-offline"` Resolve Engineering Guidance in this fresh worker context against the complete Ticket outcome. Record all nine concerns using Engineering Guidance's canonical dispositions, including the missing input and affected judgment for `unresolved`. Keep concern coverage separate from findings. Preserve authority conflicts, gaps, and specialist routes. ## Analyze Review regions in order Partition the change into coherent Review regions. A Review region is the smallest part whose implementation would be materially rewritten or removed by one fix. For every region, examine Review levels in this order: 1. Requirements & Expectations 2. Engineering & Architecture 3. Code Quality Record the levels examined, evidence inspected, and any worker-declared supersession. When a finding at a higher level supersedes lower-level analysis for that same region, the source finding must be at an examined level preceding one contiguous superseded suffix. Name each finding suppressed by that declaration, the skipped levels, and the reason. Unaffected Review regions retain complete lower-level coverage. Do not silently omit a region or level, and never use a finding from another region or worker as the source. Use the assigned lens to focus the work, not to narrow the input. Follow relevant evidence into repository history or surrounding code when needed. Report a newly discovered specialist need and its evidence to the Code Review caller. Record a missing capability as a Context limit. The worker does not dispatch another Review worker or change the caller's routing decision. ## Write complete findings Each finding records: - stable finding and region identities; - Review level and severity; - Finding confidence from 0 through 100; - Fix-direction confidence from 0 through 100; - Context limits; - confidence inputs that identify evidence quality, the limits affecting each value, and a rationale for each value; - evidence with source references; - impact; - affected scope; - stable underlying problem and conclusion identity for structural duplicate comparison; - highest actionable fix direction; and - acceptance evidence that would show the fix is complete. Finding confidence measures support for the claim, scope, impact, and severity. Fix-direction confidence measures support for the proposed direction. Neither is a probability, severity, or remediation priority. Each explicit Context limit must affect at least one confidence value, and limited or conflicting evidence cannot support an unaffected maximum value. Report no finding when evidence does not support one. A clean region still receives coverage. ## Return worker artifacts Retain an append-only candidate stream, separate concern coverage, and a worker manifest through the temporary artifact boundary. Preserve source evidence and conclusions verbatim for structural coordination. Use `take-it-offline` to return the artifact references to the caller without relying on prior context. If the worker fails, return its identity, lens, stage, code, message, evidence, and any valid partial stream or coverage instead of representing it as complete. ## Boundary The worker is read-only. It does not change code, publish comments, coordinate findings, adjudicate another lens, plan remediation, or alter ticket, pull-request, branch, dependency, or release state. ## Completion Complete when the worker examined the full Ticket outcome, independently resolved all nine concerns, accounted for every Review region in level order, and returned structurally complete findings and separate coverage with inspectable references.
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-worker skill. Agent Mart. https://agentmart.dev/skills/jhondoe15-review-worker (last updated 2026-10-24)