review-work

Post-implementation review orchestrator. Launches 5 parallel background sub-agents: Oracle (goal/constraint verification), Oracle (code quality), Oracle (security), unspecified-high (hands-on QA execution), unspecified-high (context mining from GitHub/git/Slack/Notion). All must pass for review to pass. MUST USE before a PR handoff or when the user explicitly asks to review completed work. Triggers: 'review work', 'review my work', 'review changes', 'QA my work', 'verify implementation', 'check my work', 'validate changes', 'post-implementation review'.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A detailed, highly actionable orchestrator with a clear phased workflow and strong validation/feedback loops. Its main weaknesses are repetition of the reliability protocol across sections and a monolithic single-file structure where the five agent prompts could be extracted into reference files.

Suggestions

Deduplicate the reliability guidance (back-off/double-timeout, treat-running-child-as-alive, fallback-only-when conditions) into a single stated-once section and reference it, instead of repeating it near-verbatim in the Tool Compatibility, Subagent Reliability, and Phase 2 sections.

Extract each of the five large agent prompt templates (Agents 1-5) into separate reference files under references/ and link to them from SKILL.md, turning the body into a lean overview that practices progressive disclosure.

Consolidate the repeated 'If a code block below conflicts with this section, this section wins' disclaimer into one statement near the compatibility table rather than stating it three times.

Dimension	Reasoning	Score
Conciseness	The reliability protocol ('back off — double the timeout up to ~5 minutes', 'treat a running child as alive', 'fallback only when... deliverable, ack-only, BLOCKED, or no longer running') repeats near-verbatim across three sections and 'If a code block below conflicts with this section, this section wins' appears three times — concrete but could be tightened, so it lands at 2 rather than the lean score-3 anchor.	2 / 3
Actionability	Provides fully detailed copy-paste agent templates with complete prompts, checklists, output formats, and executable commands ('git diff --name-only HEAD~1'); the OpenCode-to-Codex translation is explicitly justified per the guideline permitting justified flexibility, so it meets the 'fully executable / copy-paste ready' anchor.	3 / 3
Workflow Clarity	Clear Phase 0→3 sequence with explicit validation checkpoints ('Do NOT deliver the final report until ALL 5 lanes have a terminal state'), feedback loops (respawn a smaller reviewer on inconclusive, rerun the affected lane), and a verdict_logic block — matching the 'clear sequence with explicit validation steps and feedback loops' anchor.	3 / 3
Progressive Disclosure	Well-organized into sections but monolithic at ~630 lines with all five large agent-prompt blocks inline and no bundle files; the prompts that could be split into reference files are inline, matching the score-2 'content that should be separate is inline' example rather than the split-out score-3 anchor.	2 / 3
	Total	10 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description: third-person voice, explicit what-and-when, natural trigger phrases, and a distinct multi-agent review niche with five named concrete actions. No dimension falls below the top anchor.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'goal/constraint verification', 'code quality', 'security', 'hands-on QA execution', and 'context mining from GitHub/git/Slack/Notion' — matching the 'lists multiple specific concrete actions' anchor rather than the single-domain score-2 example.	3 / 3
Completeness	Answers both what ('Post-implementation review orchestrator... All must pass for review to pass') and when ('MUST USE before a PR handoff or when the user explicitly asks to review completed work' plus an explicit Triggers list), satisfying the 'clearly answers both what AND when' anchor.	3 / 3
Trigger Term Quality	Triggers 'review my work', 'QA my work', 'check my work', 'verify implementation', and 'validate changes' are natural phrases a user would say, giving good coverage of common variations beyond the score-2 'some relevant keywords' anchor.	3 / 3
Distinctiveness Conflict Risk	The post-implementation 5-agent review niche with distinct triggers ('review changes', 'post-implementation review') is unlikely to fire for unrelated skills, matching the 'clear niche with distinct triggers' anchor rather than the overlapping score-2 example.	3 / 3
	Total	12 / 12 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (637 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: code-yeongyu/lazycodex
Path: plugins/omo/skills/review-work/SKILL.md
Commit: 895b70c

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.