framework-docs-researcher

Gathers comprehensive documentation and best practices for frameworks, libraries, or dependencies. Use when you need official docs, version-specific constraints, or implementation patterns.

Quality

57%

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/framework-docs-researcher/SKILL.md

Quality

Content

52%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-structured agent prompt with a clear workflow and a couple of genuinely concrete commands, but it is padded with persona prose and restated standards that inflate the token budget. Actionability is mixed: specific commands sit alongside a lot of abstract direction.

Suggestions

Cut the persona intro, the restated 'Quality Standards' section, and the closing 'Remember:' paragraph — the Workflow already conveys these imperatives.

Convert abstract bullets like 'Extract relevant API references' into concrete actions, e.g. 'Fetch the library's guide section matching the feature via Context7; cite the doc URL and version.'

Add a brief feedback loop to the workflow, e.g. 'If Context7 returns nothing for the feature, fall back to web search; if version is ambiguous, confirm against Gemfile.lock before reporting.'

Dimension	Reasoning	Score
Conciseness	Noticeably verbose: motivational persona ('You are a meticulous...'), restated Quality Standards that duplicate the Workflow, and a closing 'Remember:' paragraph all pad the skill beyond what Claude needs to act.	2 / 5
Actionability	Provides some concrete, copy-pasteable guidance (e.g. `bundle show <gem_name>` and the literal deprecation search string), but the bulk is abstract direction like 'Extract relevant API references' and 'Analyze documentation for recommended patterns'.	3 / 5
Workflow Clarity	A clear five-step numbered workflow with a MANDATORY deprecation checkpoint ('Report findings before proceeding') and a Context7-to-web-search fallback; minor gap is the absence of an explicit error-recovery feedback loop.	4 / 5
Progressive Disclosure	Well-organized into labeled sections (Responsibilities, Workflow, Quality Standards, Output Format, Tool Selection) with no nested references; being a self-contained agent prompt over 50 lines, it is appropriately structured but could trim inline bulk.	4 / 5
	Total	13 / 20 Passed

Description

62%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 cleanly answers both 'what' and 'when' with an explicit Use-when clause and third-person voice. Its main weakness is that the action verbs and trigger terms are somewhat generic and abstract rather than vividly concrete.

Suggestions

Replace generic verbs with concrete operations, e.g. 'Fetches official docs via Context7, locates installed gems with bundle show, and flags deprecated APIs.'

Add natural user-mentionable trigger phrases such as 'when the user asks how to use a library, needs version-specific API behavior, or hits a gem error'.

Sharpen distinctiveness by naming the research scope (e.g. 'for Ruby/JS dependencies') to reduce overlap with general research skills.

Dimension	Reasoning	Score
Specificity	Names the domain ('frameworks, libraries, or dependencies') and two actions ('Gathers comprehensive documentation and best practices'), but the actions are broad rather than the multiple concrete operations seen at level 4-5.	3 / 5
Completeness	Clearly states what it does and includes an explicit 'Use when...' clause with three trigger conditions, but the triggers are somewhat abstract rather than the concrete user-mentionable phrases that characterize level 5.	4 / 5
Trigger Term Quality	Includes relevant terms ('official docs', 'version-specific constraints', 'implementation patterns') but the domain phrase 'frameworks, libraries, or dependencies' is generic and missing common natural variations users would actually say.	3 / 5
Distinctiveness Conflict Risk	The framework/library documentation-research niche is mostly distinct, though the broad domain ('frameworks, libraries, or dependencies') carries minor overlap risk with general coding or research skills.	4 / 5
	Total	14 / 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/framework-docs-researcher/SKILL.md
Commit: cce36d3

Reviewed: about 5 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.