start-work

Execute a Prometheus work plan in Codex with Boulder state, evidence ledger updates, worktree discipline, parallel subagents, and Stop-hook continuation. Use after planning when the user says start work, execute plan, continue plan, resume plan, or asks to run a .omo/plans plan.

Quality

85%

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

70%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 a dense, well-sequenced orchestration workflow with strong validation gates and concrete tooling, but it is held back by repeated disambiguation clauses and inlined reference material that belongs in bundle files.

Suggestions

Consolidate the repeated 'If a code block below conflicts with this section, this section wins' clause into a single statement near the top of the Codex compatibility section instead of repeating it four times.

Move the Codex tool-compatibility table and the Boulder/ledger/DoneClaim JSON schemas into separate reference files under references/ and link to them, reducing the inline wall of text.

Tighten the orchestrator-only rule: state the 'never implement directly' mandate once prominently rather than restating it across the compatibility, ABSOLUTE RULE, Phase 3, and Hard rules sections.

Dimension	Reasoning	Score
Conciseness	Mostly procedural and token-efficient, but repeats the same disambiguation clause ('If a code block below conflicts with this section, this section wins' appears four times) and reiterates the no-implementation rule across multiple sections, adding padding that could be tightened.	3 / 5
Actionability	Provides concrete, mostly-executable guidance — exact tool signatures, JSON schemas for boulder.json/ledger/DoneClaim, and exact QA commands — with a minor gap: external skills (ulw-plan, review-work, debugging) are only named, not interfaced.	4 / 5
Workflow Clarity	A clear Phase 1–5 sequence with explicit validation checkpoints and feedback loops (AdversarialVerify loops back to the executor; review-gate failure routes to the debugging skill), satisfying the high bar for batch/orchestration work.	5 / 5
Progressive Disclosure	No bundle files exist (references/, scripts/, assets/ are absent) yet content that could live in separate files — the Codex tool-compat table, ledger/DoneClaim schemas — is inlined into a ~210-line body; section headers give some structure but references are not split out.	3 / 5
	Total	15 / 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 specific, complete, and well-triggered, clearly stating both what the skill does and when to use it with natural user phrases. It occupies a distinct niche with low conflict risk.

Dimension	Reasoning	Score
Specificity	Names the domain and multiple concrete actions ('Boulder state, evidence ledger updates, worktree discipline, parallel subagents, and Stop-hook continuation'), giving comprehensive coverage of what the skill does.	5 / 5
Completeness	Explicitly answers both 'what' (execute a Prometheus work plan in Codex...) and 'when' (Use after planning when the user says...) with concrete trigger phrases.	5 / 5
Trigger Term Quality	Lists several natural user phrases and synonyms ('start work, execute plan, continue plan, resume plan, or asks to run a .omo/plans plan') that a user would naturally say.	5 / 5
Distinctiveness Conflict Risk	A clear niche (Prometheus work plans in Codex, .omo/plans) with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	20 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: code-yeongyu/lazycodex
Path: plugins/omo/skills/start-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.