framework-docs-researcher

Use this agent when you need to gather comprehensive documentation and best practices for frameworks, libraries, or dependencies in your project. This includes fetching official documentation, exploring source code, identifying version-specific constraints, and understanding implementation patterns.

Quality

55%

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/00-utilities/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 body presents a well-sequenced workflow with a meaningful validation checkpoint and clear output structure, but it is padded with persona prose and duplicated sections and mixes concrete commands with vague directives.

Suggestions

Remove the persona preamble and motivational closing, and merge the overlapping Core Responsibilities and Workflow Process sections to eliminate restated content.

Convert high-level directives like 'Extract relevant API references' into concrete, executable steps or example commands.

Add an explicit validate-then-fix feedback loop (e.g., verify findings against official docs, retry on conflicting information) to raise workflow clarity.

Dimension	Reasoning	Score
Conciseness	The body is noticeably verbose: persona preamble ('You are a meticulous Framework Documentation Researcher...'), overlapping Core Responsibilities and Workflow Process sections that restate the same gathering/exploration steps, and a motivational closing ('Remember: You are the bridge...') that add padding without new guidance.	2 / 5
Actionability	Provides some concrete, executable guidance such as the deprecation search strings ('[API/service name] deprecated [current year] sunset shutdown') and 'bundle show <gem_name>', but many directives remain high-level ('Extract relevant API references', 'Identify community solutions') without specific executable steps.	3 / 5
Workflow Clarity	The Workflow Process is a clear five-step sequence with an explicit MANDATORY deprecation checkpoint ('Report findings before proceeding') and a Context7-unavailable fallback, but it lacks a full validate-fix-retry feedback loop for error recovery.	4 / 5
Progressive Disclosure	Content is well-organized into clearly headed sections (Core Responsibilities, Workflow Process, Quality Standards, Output Format) with no nested references, but at roughly 85 lines it exceeds the under-50-line simple-skill threshold and contains duplicated responsibility content that could be condensed.	4 / 5
	Total	13 / 20 Passed

Description

58%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 clearly states both purpose and trigger conditions with several concrete capabilities, but is written in second person and lacks the natural synonym and extension coverage that would make triggers comprehensive and distinctive.

Suggestions

Rewrite in third person ('Gathers comprehensive documentation...') to avoid the second-person voice penalty.

Add natural trigger terms and synonyms users actually say, such as 'docs', 'API reference', 'migration guide', and common file extensions or ecosystem cues.

Tighten the capability list to be more comprehensive and distinctive so it is less likely to overlap with generic research skills.

Dimension	Reasoning	Score
Specificity	Names the domain ('frameworks, libraries, or dependencies') and lists several concrete actions ('fetching official documentation, exploring source code, identifying version-specific constraints'), but uses second person ('when you need'), which per the guidelines reduces the specificity score by one from 4 to 3.	3 / 5
Completeness	Explicitly answers both what ('This includes fetching official documentation, exploring source code...') and when ('Use this agent when you need to gather comprehensive documentation...'), though the trigger phrasing could be more varied and concrete, matching the anchor for both present with room for greater specificity.	4 / 5
Trigger Term Quality	Contains relevant keywords like 'documentation', 'best practices', 'frameworks, libraries, or dependencies', but misses common natural variations users would say ('docs', 'API reference', file extensions, 'how to use X'), fitting the anchor for some relevant keywords with missing synonyms.	3 / 5
Distinctiveness Conflict Risk	Scoped to documentation gathering for frameworks/libraries/dependencies, which is somewhat specific, but the broad domain still overlaps with general coding-research and documentation skills rather than occupying a clearly distinct niche.	3 / 5
	Total	13 / 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: marchatton/agent-skills
Path: .agents/skills/00-utilities/framework-docs-researcher/SKILL.md
Commit: a0eadb2

Reviewed: 5 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.