best-practices-researcher

Researches and synthesizes external best practices, documentation, and examples for any technology or framework. Use when you need industry standards, community conventions, or implementation guidance.

Quality

77%

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 ./.agents/skills/best-practices-researcher/SKILL.md

Quality

Content

62%

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

The content provides a clear, well-sequenced research workflow with a real validation checkpoint, and offers some concrete search templates and skill-mapping lists. Its main weaknesses are verbosity (generic research prose and a large examples block) and the lack of any progressive-disclosure structure or executable code examples.

Suggestions

Trim generic research prose and the <examples> block that Claude already knows; keep only the skill-discovery globs, deprecation-check search templates, and skill mappings to lift conciseness toward score 3.

Add at least one concrete, executable example (e.g., a Context7/web-search command or a sample skill-glob invocation) so actionability reaches copy-paste-ready guidance.

Move the lengthy skill-mapping table and Phase details into a referenced file (e.g., SKILL-MAPPINGS.md) linked one level deep, so the body becomes a lean overview and progressive disclosure reaches score 3.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient but includes generic prose Claude already knows ("Use Context7 MCP to access official documentation", "Search the web for recent articles") and a bulky <examples> block; it is not a score-1 wall of definitions, but it could be tightened to lean guidance.	2 / 3
Actionability	It gives some concrete, executable guidance (search templates like "[API name] deprecated [current year] sunset shutdown" and skill glob paths), but much is still abstract direction ("Evaluate Information Quality", "Organize Discoveries") with no executable code, so it falls short of fully copy-paste-ready score-3 material.	2 / 3
Workflow Clarity	A clearly sequenced Phase 1 -> 1.5 -> 2 -> 3 flow with an explicit validation checkpoint (the mandatory deprecation check: "Report findings before proceeding - do not recommend deprecated APIs"), matching the score-3 anchor of a clear sequence with an explicit validation step.	3 / 3
Progressive Disclosure	The skill is a single monolithic SKILL.md with no bundle files (references/scripts/assets absent) and no one-level-deep linked references; it is organized into clear sections, but at well over 50 lines content that could be split is inline, so it does not reach the score-3 well-signaled reference structure.	2 / 3
	Total	9 / 12 Passed

Description

92%

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 strong: it clearly states concrete actions and an explicit Use-when trigger with natural vocabulary, fully covering what and when. Its only weakness is the broad "any technology or framework" scope, which raises overlap risk with other research-oriented skills.

Dimension	Reasoning	Score
Specificity	"Researches and synthesizes external best practices, documentation, and examples" names multiple concrete actions (research, synthesize) applied to several object types, matching the multi-action score-3 anchor; it is not a score-2 because it lists more than a single domain+action pair.	3 / 3
Completeness	It explicitly answers both what ("Researches and synthesizes external best practices, documentation, and examples for any technology or framework") and when ("Use when you need industry standards, community conventions, or implementation guidance"), matching the score-3 what+when anchor.	3 / 3
Trigger Term Quality	"industry standards, community conventions, or implementation guidance" plus "best practices" are natural phrases users actually say when seeking this kind of help, giving good coverage rather than the partial coverage of score 2.	3 / 3
Distinctiveness Conflict Risk	The triggers are fairly specific but "for any technology or framework" is broad and could overlap with other research/analysis skills, so it is not a clearly bounded niche (score 3) yet it is more specific than a generic "helps with X" (score 1).	2 / 3
	Total	11 / 12 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: udecode/plate
Path: .agents/skills/best-practices-researcher/SKILL.md
Commit: 45116fd

Reviewed: about 14 hours 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.