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

73%

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

67%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.

A well-structured research methodology with concrete, executable search templates and a clear phased workflow. It would benefit from trimming the role preamble, consolidating redundant online-research sections, and generalizing or removing the GitHub-issue-specific 'Special Cases' block.

Suggestions

Remove the role-preamble sentence ('You are an expert technology researcher...') and the closing filler ('Your research should be thorough but focused...') — Claude already understands the research role from the description.

Merge 'Leverage External Sources' and 'Online Research Methodology' into a single concise step list to remove overlap.

Generalize or delete the 'Special Cases' section, which covers only GitHub issues despite the skill targeting any technology or framework.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete search templates and paths, but includes a verbose role preamble ('You are an expert technology researcher...'), a narrow 'Special Cases' section focused only on GitHub issues, and overlapping 'Leverage External Sources'/'Online Research Methodology' sub-sections that could be tightened.	3 / 5
Actionability	Provides executable guidance: concrete search query templates ('"[API name] deprecated [current year] sunset shutdown"'), specific skill-directory globs ('.claude/skills/**/SKILL.md'), explicit skill-name mappings, and named tools (Context7 MCP, Glob, Grep, Read). Minor gaps include no concrete output/synthesis format example.	4 / 5
Workflow Clarity	A clear Phase 1 → 1.5 → 2 → 3 sequence with numbered sub-steps and validation gates (Phase 1.5 'Report findings before proceeding', Phase 1 step 4 'Assess Coverage' branching). Not a 5 because there are no true error-recovery feedback loops, though that is partly inherent to a research task.	4 / 5
Progressive Disclosure	No bundle files exist (references/, scripts/, assets/ all empty) and none are needed for this single-file methodology; the body is well-organized with clear phase headers and numbered steps. The over-50-line length and the oddly-placed 'Special Cases' section keep it just below a 5.	4 / 5
	Total	15 / 20 Passed

Description

78%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.

A strong description that explicitly states both what the skill does and when to use it, with a clear 'Use when...' trigger clause. The main limitation is that only two verbs ('researches', 'synthesizes') describe the actions, leaving the capability list less comprehensive than it could be.

Suggestions

Add one or two more concrete verbs to the what-clause (e.g., 'compares', 'summarizes', 'cites sources') to lift specificity from 3 toward 4-5.

Include the most common user phrasing in the when-clause (e.g., 'Use when the user asks "what are the best practices for..." or "how should I..."') to broaden natural trigger coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('best practices, documentation, and examples for any technology or framework') with two concrete actions ('Researches', 'synthesizes'), matching the anchor for 1-2 concrete actions that are not comprehensive. It does not enumerate the multiple specific actions that would warrant a 4.	3 / 5
Completeness	Clearly answers both: the what ('Researches and synthesizes external best practices, documentation, and examples...') and an explicit when with concrete trigger phrases ('Use when you need industry standards, community conventions, or implementation guidance.').	5 / 5
Trigger Term Quality	The 'Use when...' clause surfaces reasonably natural triggers ('industry standards', 'community conventions', 'implementation guidance') plus 'best practices' in the what-clause, giving good keyword coverage. A 5 would require more synonyms and the most common phrasing users actually say ('what are the best practices for...').	4 / 5
Distinctiveness Conflict Risk	The research/synthesis niche with triggers like 'industry standards' and 'community conventions' is mostly distinct from doing-skills. The very broad 'for any technology or framework' scope creates minor overlap risk with topic-specific skills, keeping it just below a 5.	4 / 5
	Total	16 / 20 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: 9ec2c8e

Reviewed: ~15 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.