best-practice-research

[OMX] Bounded best-practice research wrapper using official/upstream evidence first

Quality

67%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/oh-my-codex/skills/best-practice-research/SKILL.md

Quality

Content

85%

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 well-structured, actionable routing workflow with explicit stop/handoff checkpoints and a ready output template; its main weakness is redundant repetition of the terminal/handoff boundary across several sections.

Suggestions

Consolidate the 'terminal / do not implement / stop and hand off' rule into one section and reference it elsewhere rather than restating it in Purpose, Output Contract, and Stop Rules.

Dimension	Reasoning	Score
Conciseness	The body is lean and avoids explaining concepts Claude already knows, but the 'stop and hand off / never implement' message is repeated across Purpose, Terminal By Default, Output Contract, and Stop Rules, so it could be tightened.	2 / 3
Actionability	For an instruction-only wrapper it gives concrete, actionable guidance: named specialists to route to (`explore`, `researcher`, `dependency-expert`), explicit Source-Quality Rules, and a copy-paste-ready Output Contract template.	3 / 3
Workflow Clarity	A clearly numbered Workflow and Specialist Routing sequence is paired with explicit Stop Rules that act as validation checkpoints (stop when grounded; stop and route upward for dependency/architecture/implementation work).	3 / 3
Progressive Disclosure	No bundle files exist and none are needed; the skill is a self-contained, well-sectioned routing wrapper with clear headers and no nested references, so organization alone earns the top level.	3 / 3
	Total	11 / 12 Passed

Description

50%

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 names the skill's domain and evidence-first posture but reads as a technical label rather than a user-facing trigger: it lacks natural keyword coverage, a 'Use when' clause, and clear separation from a generic researcher skill.

Suggestions

Add an explicit 'Use when...' clause listing natural triggers, e.g. 'Use when the user asks for best practices, recommended approach, official guidance, standards, or version-aware upstream behavior.'

Drop or explain the '[OMX]' prefix and the word 'wrapper' so the description leads with user-natural language instead of internal jargon.

Sharpen distinctiveness from `researcher` by stating the boundary, e.g. 'Use for current external best-practice evidence on an already-chosen technology; use researcher for general lookup.'

Dimension	Reasoning	Score
Specificity	Quotes 'best-practice research wrapper' and 'using official/upstream evidence first' name the domain and a couple of characteristics, but do not list multiple concrete actions like the level-3 anchor; it is more than vague level-1 but not comprehensive.	2 / 3
Completeness	It states what the skill does ('best-practice research wrapper using official/upstream evidence first') but has no 'Use when...' trigger clause, which per the judging guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	'best-practice' is a natural user term, but the '[OMX]' prefix and 'wrapper'/'official/upstream evidence first' are jargon, and common variations like 'recommended approach' or 'official guidance' are missing, so it lands at level-2 rather than full coverage.	2 / 3
Distinctiveness Conflict Risk	'best-practice research wrapper' is somewhat specific but 'research' overlaps with a general researcher skill, so it could still trigger for the wrong skill rather than occupying a clearly distinct niche.	2 / 3
	Total	8 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: Yeachan-Heo/oh-my-codex
Path: plugins/oh-my-codex/skills/best-practice-research/SKILL.md
Commit: 435d4a9

Reviewed: 2 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.