ulw-research

Maximum-saturation research orchestration: parallel explore+librarian swarms across codebase, web, official docs, and OSS repos; a recursive EXPAND loop driven by leads workers return in message text; empirical verification by running code; cited synthesis and optional MD/HTML/PDF/PPTX reports. ACTIVATES ONLY on an explicit user demand for research — the word 'ulw-research' ('/ulw-research', '$ulw-research'), any 'ulw' research wording, or an explicit request for research / deep research / an ultra-precise investigation, in any language. Never self-activates for ordinary questions, debugging, or implementation context-gathering. While active it overrides exploration-bounding defaults: exhaustive coverage is the goal.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

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 highly actionable, well-sequenced research-orchestration protocol with strong validation checkpoints, but it is verbose and monolithic. Tightening repetition and splitting the larger sections into reference files would improve token efficiency and navigability.

Suggestions

Remove the repeated 'If a code block below conflicts with this section, this section wins' clause (stated three times) — state the precedence rule once near the tool-compatibility section.

Extract the Phase 3b claim-graph gate, the epistemic-instrumentation field specs, and the search-craft operator table into reference files (e.g. references/claim-gate.md, references/search-craft.md) and link to them from SKILL.md to reduce the monolithic body.

Condense the Codex Harness Tool Compatibility preamble by collapsing the v1/v2 surface notes into a single short table or a dedicated reference file.

Dimension	Reasoning	Score
Conciseness	Most content is novel orchestration protocol Claude does not know, but the file is ~284 lines with clear padding — 'If a code block below conflicts with this section, this section wins' is repeated three times and the Codex tool-compatibility preamble could be tightened.	2 / 3
Actionability	Provides concrete, copy-paste-ready guidance: literal `task(...)` spawn templates, `mkdir -p .omo/ulw-research/$(date +%Y%m%d-%H%M%S)`, `uv run --with <deps>`, `git log --all -S`, and explicit EXPAND/CLAIMS marker formats.	3 / 3
Workflow Clarity	Clear Phase 0→1→2→3→3b→4→5 sequence with explicit convergence stop-rules, Phase 3 execution verification, the Phase 3b claim-gate criteria, and follow-up feedback loops for missing tails and report repair.	3 / 3
Progressive Disclosure	Sections are well-organized with clear headers, but the skill is a single monolithic ~284-line file with no references/scripts/assets bundle; content like the claim-gate protocol, search-craft table, and tool-compatibility section that could be split out is inline.	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, third-person description that concretely states capabilities and provides explicit activation and anti-activation triggers. It is somewhat long, but each clause is informative and there is no vague fluff.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions: 'parallel explore+librarian swarms across codebase, web, official docs, and OSS repos', 'a recursive EXPAND loop', 'empirical verification by running code', 'cited synthesis and optional MD/HTML/PDF/PPTX reports'.	3 / 3
Completeness	Explicitly answers what (research orchestration with swarms, EXPAND loop, verification, synthesis, reports) and when ('ACTIVATES ONLY on an explicit user demand for research'), with explicit trigger guidance so it is not capped at 2.	3 / 3
Trigger Term Quality	Covers natural user phrasings ('research / deep research / an ultra-precise investigation, in any language') alongside the coined trigger 'ulw-research' and its slash/dollar variants.	3 / 3
Distinctiveness Conflict Risk	Clear niche with distinct triggers plus an explicit anti-trigger ('Never self-activates for ordinary questions, debugging, or implementation context-gathering'), making conflict with other skills unlikely.	3 / 3
	Total	12 / 12 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/ulw-research/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.