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%Weight 40%Scale 1-5

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

The body is highly actionable and well-sequenced with strong validation checkpoints, but it suffers from repeated harness-compatibility and reliability guidance (the same fork_context/wait_agent/fallback rules appear multiple times) and a monolithic structure where the five full agent-prompt templates are inlined rather than split into reference files. Tightening the duplication and externalizing the prompt templates would meaningfully improve it.

Suggestions

Deduplicate the reliability guidance: the 'timeout only means no new mailbox update arrived / treat a running child as alive' and 'fallback only when completed without deliverable, ack-only, BLOCKED, or no longer running' rules each appear 2-3 times nearly verbatim — state them once in a single 'Subagent Reliability' section and reference it.

Extract the five full agent prompt templates (Agents 1-5) into reference files under references/ (e.g. references/goal-verifier.md, references/qa-executor.md) and link to them from a concise 'Phase 1' overview, reducing the monolithic SKILL.md body.

Collapse the overlapping Codex tool-compatibility and v1/v2 surface sections into one canonical mapping table with a single 'this section wins on conflict' note instead of restating the fork_context translation rules in three places.

Dimension	Reasoning	Score
Conciseness	Mostly efficient operational guidance, but noticeably verbose with near-verbatim repetition across sections — 'A timeout only means no new mailbox update arrived. Treat a running child as alive.' and the 'Fallback only when the child is completed without the deliverable...' clause each recur multiple times, and the Codex tool-compatibility preamble re-explains the same fork_context/wait_agent rules several times.	3 / 5
Actionability	Fully executable: concrete git commands (`git diff --name-only HEAD~1`), copy-paste-ready spawn calls, and five complete prompt templates with explicit output formats and placeholders; covers the common review cases directly.	5 / 5
Workflow Clarity	Clear four-phase sequence (Gather → Launch → Wait & Collect → Deliver) with explicit verdict logic, blocking-issue rules, evidence-preservation checkpoints, and bounded retry/respawn feedback loops for inconclusive lanes.	5 / 5
Progressive Disclosure	No bundle files exist and all content is inlined in one ~640-line SKILL.md; the five large agent prompt templates could be split into separate reference files, and nothing is signaled as living elsewhere. Structure via phase headers is reasonable but content that should be separate is inline.	3 / 5
	Total	16 / 20 Passed

Description

100%Weight 40%Scale 1-5

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

The description is precise and well-constructed: it names the concrete capability (5 parallel sub-agents with distinct review roles), the pass condition, and the explicit trigger phrases a user would naturally say. Both the 'what' and 'when' are answered with concrete, non-generic language. It avoids fluff and over-claims.

Dimension	Reasoning	Score
Specificity	Names the domain and lists multiple concrete actions — 'Launches 5 parallel background sub-agents' covering 'goal/constraint verification', 'code quality', 'security', 'hands-on QA execution', and 'context mining from GitHub/git/Slack/Notion' — with comprehensive coverage.	5 / 5
Completeness	Explicitly answers both 'what' (orchestrates 5 parallel sub-agents, all must pass) and 'when' ('MUST USE before a PR handoff or when the user explicitly asks to review completed work') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural trigger phrases users would actually say: 'review work', 'review my work', 'review changes', 'QA my work', 'verify implementation', 'check my work', 'validate changes', 'post-implementation review'.	5 / 5
Distinctiveness Conflict Risk	Clear niche as a post-implementation review orchestrator with specific, distinct trigger phrases; minimal overlap risk with other skills.	5 / 5
	Total	20 / 20 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: 10f9558

Reviewed: 10 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.