ulw-loop

Goal-like loop that uses ultrawork mode to decompose work into systematic, evidence-bound steps.

Quality

70%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/omo/components/ulw-loop/skills/ulw-loop/SKILL.md

Quality

Content

86%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, actionable overview that delegates the full workflow to a single clearly-signaled reference and supplies copy-paste-ready tool mappings. Its main weakness is mild verbosity in a few long Non-Negotiables sentences.

Dimension	Reasoning	Score
Conciseness	The body is lean operational guidance that assumes Claude's competence and explains no basic concepts, though a few Non-Negotiables sentences are long and could be tightened, placing it just below the score-5 anchor.	4 / 5
Actionability	Copy-paste-ready commands populate the Codex Tool Mapping table (spawn_agent({...}), wait_agent, git rev-parse --short "HEAD^{tree}", omo ulw-loop create-goals) and cover the common cases, matching the fully-executable score-5 anchor.	5 / 5
Workflow Clarity	Required First Steps gives a clear sequenced entry with a validation gate (read Bootstrap/Execution Loop/Manual-QA/Stop Rules before acting) and validation is heavily emphasized, but the main execution loop is delegated to the reference rather than sequenced inline, keeping it below 5.	4 / 5
Progressive Disclosure	The skill is explicitly compact and points one level deep to a real references/full-workflow.md, naming the exact sections to read per phase — a clear overview with well-signaled single-level references and easy navigation.	5 / 5
	Total	18 / 20 Passed

Description

53%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 conveys a clear niche and core action but omits any explicit "Use when..." trigger guidance, relying on the body for trigger terms. It is jargon-heavy and would benefit from natural user-facing keywords.

Suggestions

Add an explicit "Use when..." clause to the description naming natural trigger phrases (e.g. durable goals, evidence-led delivery, checkpointed long-running work) so completeness can score above 3.

Replace or supplement jargon ("ultrawork mode", "evidence-bound steps") with terms a user would naturally say to lift trigger-term quality.

List one or two more concrete capabilities (e.g. manual QA, checkpointed delegation) to broaden specificity beyond a single action.

Dimension	Reasoning	Score
Specificity	Names the domain ("ultrawork mode") and one concrete action ("decompose work into systematic, evidence-bound steps"), but stops at 1-2 actions without comprehensive coverage, matching the score-3 anchor.	3 / 5
Completeness	Provides a clear "what" but no "Use when..." trigger clause — the "when" guidance lives in the body, not the description — so per the missing-trigger cap it cannot exceed 3.	3 / 5
Trigger Term Quality	Has some relevant keywords ("Goal-like loop", "decompose work") but leans on jargon ("ultrawork mode", "evidence-bound steps") and misses natural synonyms a user would actually say, fitting the score-3 anchor better than 2 or 4.	3 / 5
Distinctiveness Conflict Risk	The niche phrasing ("ultrawork mode", "Goal-like loop") makes it mostly distinct with only minor overlap risk against closely related orchestration skills, landing above the score-3 anchor.	4 / 5
	Total	13 / 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
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

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