ulw-plan

MUST USE for planning before coding when design uncertainty remains after discovery: ambiguous scope, competing decompositions, unclear boundaries, uncertain dependency ordering, architecture decisions, a vague 'just make it good / figure out what to build' brief, or any request to plan, interview, or break work down. Explore-first planning consultant (Prometheus) that grounds in the codebase, asks only the forks exploration cannot resolve - or researches them to best practice when the intent is fuzzy - waits for explicit approval, then writes ONE decision-complete work plan a worker executes with zero further interview. Triggers: ulw-plan, plan this, make a plan, plan before coding, interview me, break this down, start planning, plan mode, just make it good, figure out what to build.

Quality

92%

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

85%

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

A well-architected, actionable planning skill with clear workflow sequencing, validation checkpoints, and clean one-level-deep progressive disclosure. Its main weakness is conciseness — repeated restatements of the same invariants and heavy emphasis inflate the token budget without adding guidance.

Suggestions

State the no-implementation / plan-mode-sticky pledge once in the universal invariants and reference it from the other sections instead of restating it verbatim in the opening announcement, role line, approval gate, and stop rules.

Reduce the ALL-CAPS and bold emphasis to the single most load-bearing rule per section; constant 'MUST'/'NEVER' emphasis dilutes the genuinely critical constraints.

Consolidate the intent-routing trigger list and the review-modifier gate so the modifier rule is not described twice across the routing section.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and free of basic-concept explanations, but padded with redundant reinforcement — the no-implementation pledge is restated in the opening announcement, role line, universal invariants, approval gate, and stop rules — and heavy caps/bold emphasis that could be tightened.	2 / 3
Actionability	Provides concrete executable guidance: the exact 'node scripts/scaffold-plan.mjs <slug> --draft-only' command with flags, copy-paste spawn_agent JSON with field names, and the '- [ ] N. <title>' task-row grammar, matching the level-3 copy-paste-ready anchor.	3 / 3
Workflow Clarity	Clear sequence (opening announcement → intent routing → run script → invariants → approval gate → delegation → stop rules) with explicit validation checkpoints — the structural self-check over the plan and the stop-rule completion checklist — and a repair-before-handoff feedback loop.	3 / 3
Progressive Disclosure	The body is an overview that cleanly defers deep mechanics to one-level-deep, clearly-signaled references (full-workflow.md, intent-clear.md, intent-unclear.md) plus the scaffold script; all referenced bundle files exist and are appropriately split.	3 / 3
	Total	11 / 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, third-person description that concretely states capabilities, gives an explicit trigger list, and answers both what and when with a distinctive niche. Its only weakness is verbosity — it is roughly three times longer than the good examples and carries some branding fluff ('Prometheus', 'decision-complete').

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'grounds in the codebase, asks only the forks exploration cannot resolve... waits for explicit approval, then writes ONE decision-complete work plan' — matching the level-3 anchor for comprehensive specific actions.	3 / 3
Completeness	Clearly answers both what (an explore-first planning consultant that produces one decision-complete plan) and when ('MUST USE for planning before coding when design uncertainty remains...' plus the explicit triggers list), matching the level-3 anchor.	3 / 3
Trigger Term Quality	An explicit 'Triggers:' list gives natural phrases users would say (plan this, make a plan, interview me, break this down, just make it good), giving good coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear planning-before-coding niche with distinctive triggers unlikely to fire for unrelated skills, matching the level-3 clear-niche anchor.	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
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: code-yeongyu/lazycodex
Path: plugins/omo/components/ultrawork/skills/ulw-plan/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.