best-practice-research

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

Quality

61%

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

75%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 content is a well-organized, concise instruction-only wrapper with concrete routing, an explicit output template, and clear stop/handoff rules. It scores consistently strong across dimensions, with only minor conciseness redundancy and soft (non-validation) workflow checkpoints holding it back from top marks.

Suggestions

Consolidate the terminal/handoff message into one authoritative section and reference it elsewhere instead of restating it four times.

Add a brief worked example of a filled-in Output Contract to lift actionability from concrete to fully copy-paste-ready.

Make the grounding-sufficiency checkpoint more explicit (e.g., a one-line checklist of what "grounded enough" means) to strengthen the workflow feedback loop.

Dimension	Reasoning	Score
Conciseness	The body is well-structured with clear headers and assumes Claude's competence without explaining basic concepts, but the terminal/handoff message is restated across Purpose, Terminal By Default, Output Contract, and Stop Rules, which is minor repetition that could be trimmed.	4 / 5
Actionability	As an instruction-only routing skill it provides concrete, actionable guidance: named specialists (explore, researcher, dependency-expert), ordered routing, a copy-paste Output Contract template, and explicit source-quality directives, with only minor gaps (no worked example).	4 / 5
Workflow Clarity	The Workflow and Specialist Routing sections give a clear ordered sequence with an explicit grounding-sufficiency checkpoint and an upward-route redirect for scope drift; this is a read-only skill so the destructive-operation cap does not apply, but checkpoints are softer than formal validation feedback loops.	4 / 5
Progressive Disclosure	No bundle files exist and the body is appropriately self-contained with well-organized sections and no buried or nested references; at ~83 lines it slightly exceeds the simple-skill threshold, and the inlined routing/contract content plus cross-section redundancy keep it just below a 5.	4 / 5
	Total	16 / 20 Passed

Description

48%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 concise and clearly scoped to a best-practice research niche, but it lacks concrete action verbs and any explicit "Use when..." trigger guidance, capping both specificity and completeness. Trigger-term coverage is decent but missing common synonyms.

Suggestions

Add an explicit trigger clause, e.g. "Use when a task needs current official/upstream best practices, version-aware guidance, standards, or migration notes."

Replace the noun-phrase framing with concrete actions: "Gathers official/upstream evidence, synthesizes a cited recommendation, and hands off to planning."

Broaden trigger terms with natural synonyms ("recommended approach", "current guidance", "standards", "migration notes") to improve user-match recall.

Dimension	Reasoning	Score
Specificity	The description names the domain ("best-practice research wrapper") and one descriptor ("using official/upstream evidence first") but enumerates no concrete actions (e.g., gather, synthesize, cite, handoff), matching the anchor where the domain is named but actions are minimal or generic.	2 / 5
Completeness	The "what" is clear (a bounded best-practice research wrapper), but there is no "Use when..." clause or equivalent trigger guidance; per the rubric, a missing explicit trigger clause caps completeness at 3.	3 / 5
Trigger Term Quality	It includes natural phrases like "best-practice research" and "official/upstream evidence" but omits common synonyms users would say (recommended approach, standards, current guidance, migration), matching the anchor of relevant keywords with missing variations.	3 / 5
Distinctiveness Conflict Risk	The "[OMX]" prefix and "bounded ... wrapper using official/upstream evidence first" carve a clear niche distinct from repo-local explore and dependency-expert, with only minor overlap risk against a generic researcher skill.	4 / 5
	Total	12 / 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
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: 3ad79a8

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.