review-agent-task
Review one completed agent task against its PRD requirements, task boundaries, acceptance criteria, and validation evidence.
Skill by klemie
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/klemie-review-agent-task
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: productivity, agent-building
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
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/review-agent-task
What's inside
- Skill name
review-agent-task- Description
- Review one completed agent task against its PRD requirements, task boundaries, acceptance criteria, and validation evidence. Use before dependent tasks continue.
- License
- MIT
- Instructions
- 33 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Review an Agent Task Review the implementation, not just the completion summary. ## Inputs Read: - The source PRD - The exact task brief - Dependency handoffs - The implementation diff or changed files - Test and validation output ## Review 1. Verify every acceptance criterion with evidence. 2. Confirm the change stays inside the task boundary. 3. Check compatibility with the PRD and completed dependencies. 4. Look for missing tests, regressions, unsafe assumptions, and blockers for later tasks. 5. Re-run focused validation when practical. ## Verdict Return one verdict: - **Pass** — criteria are satisfied and dependent tasks may continue. - **Revise** — list specific required changes, tied to criteria. - **Blocked** — state the missing decision, dependency, or evidence. Do not expand the PRD during review. Route product ambiguity through `grill-me`, then update the task plan if the answer changes downstream work.
From klemie/agent-toolkit, MIT.
More from klemie/agent-toolkit
- 0.570score
help
klemie
Router map for this toolkit.
SkillAFreshness: AClaude Code +9 - 0.566score
compound-engineering
klemie
Captures reusable agent context after a pull request's reviewer agents have approved.
SkillAFreshness: AClaude Code +9 - 0.565score
grill-me
klemie
Universal interaction principle for gathering requirements, navigating decisions, and processing feedback.
SkillAFreshness: AClaude Code +9 - 0.534score
multi-agent-review
klemie
Trigger 3 parallel subagent to review the current work.
SkillAFreshness: AClaude Code +9 - 0.528score
create-skill
klemie
How to add a skill to this router catalog.
SkillBFreshness: BClaude Code +9 - 0.524score
implement-agent-task
klemie
Execute one agent-ready task derived from a PRD.
SkillBFreshness: BClaude Code +9 - 0.523score
clarify-prd
klemie
Workflow to interrogate a vague product idea until it is spec-ready.
SkillBFreshness: BClaude Code +9 - 0.521score
create-agent-tasks
klemie
Turn a product requirements document (PRD) into small, ordered tasks that coding agents can execute independently.
SkillBFreshness: BClaude Code +9 - 0.518score
create-prd
klemie
Workflow to draft a product requirements document.
SkillBFreshness: BClaude Code +9 - 0.518score
address-review-feedback
klemie
Workflow to resolve pull request review comments.
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 16
- Open issues
- 0
- Last commit (this folder)
- Sep 23, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/klemie/agent-toolkit
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from klemie
- 0.570score
help
klemie
Router map for this toolkit.
SkillAFreshness: AClaude Code +9 - 0.566score
compound-engineering
klemie
Captures reusable agent context after a pull request's reviewer agents have approved.
SkillAFreshness: AClaude Code +9 - 0.565score
grill-me
klemie
Universal interaction principle for gathering requirements, navigating decisions, and processing feedback.
SkillAFreshness: AClaude Code +9 - 0.534score
multi-agent-review
klemie
Trigger 3 parallel subagent to review the current work.
SkillAFreshness: AClaude Code +9 - 0.528score
create-skill
klemie
How to add a skill to this router catalog.
SkillBFreshness: BClaude Code +9 - 0.524score
implement-agent-task
klemie
Execute one agent-ready task derived from a PRD.
SkillBFreshness: BClaude Code +9
Cite this page
review-agent-task skill. Agent Mart. https://agentmart.dev/skills/klemie-review-agent-task (last updated 2026-10-24)