repo-research-analyst

Conducts thorough research on repository structure, documentation, conventions, and implementation patterns. Use when onboarding to a new codebase or understanding project conventions.

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/repo-research-analyst/SKILL.md

Quality

Content

63%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 is a thorough, well-sequenced research procedure with strong actionability and clear scoping logic. Its main weaknesses are verbosity from inlined reference tables and the absence of any progressive-disclosure structure (no bundled reference files despite content that would benefit from them).

Suggestions

Move the manifest-to-ecosystem and infrastructure pattern tables into a reference file (e.g. references/ecosystem-map.md) and link to it, keeping SKILL.md as an overview.

Trim or remove explanations of tooling Claude already knows (e.g. 'Use the native file-search/glob tool') to improve token efficiency.

Add an explicit validation/verification step in the Research Methodology (e.g. 'Cross-check each finding against a second source before reporting') to lift workflow clarity.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and well-structured but includes padded sections (the long manifest-to-ecosystem and pattern tables, plus repeated 'Use native tools' guidance) that assume context Claude already has and could be tightened or moved to a reference file.	3 / 5
Actionability	Provides concrete, executable guidance -- specific globs, named manifest files, ast-grep via shell, skip rules keyed to real file patterns -- with only minor gaps (no example commands for ast-grep or content-search invocations).	4 / 5
Workflow Clarity	Multi-step phases are clearly sequenced (Phase 0.1 -> 0.1b -> 0.2 -> 0.3 -> core responsibilities) with scoping rules and conditional skip logic; the main gap is limited explicit validation/feedback checkpoints given the read-only research nature, which keeps it just below 5.	4 / 5
Progressive Disclosure	The content is monolithic within SKILL.md with no references, scripts, or assets bundle; the large reference tables and output template are inlined where a one-level-deep reference file would aid navigation, and no external files are signaled.	3 / 5
	Total	14 / 20 Passed

Description

83%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 strong: third person, concise, and explicit about both capabilities and trigger conditions, with concrete natural-language trigger phrases. It would benefit from a few more specific synonyms (e.g. 'codebase research', 'conventions') to maximize trigger coverage.

Suggestions

Add common synonyms to the trigger clause, e.g. 'Use when researching a codebase, onboarding, or learning project conventions and patterns'.

Name the concrete output (e.g. 'produce a structured research summary') to sharpen the 'what' further.

Dimension	Reasoning	Score
Specificity	Lists several concrete research targets ('repository structure, documentation, conventions, and implementation patterns') naming the domain plus multiple specific actions, with only minor gaps in coverage compared to the body's full phase list.	4 / 5
Completeness	Explicitly answers both what ('Conducts thorough research on repository structure, documentation, conventions, and implementation patterns') and when ('Use when onboarding to a new codebase or understanding project conventions') with a concrete trigger clause.	5 / 5
Trigger Term Quality	Includes natural user phrases ('onboarding to a new codebase', 'understanding project conventions') that users would actually say, missing only a few synonyms and file-extension-style trigger variants.	4 / 5
Distinctiveness Conflict Risk	The repository-research niche is fairly distinct from most skills, though 'understanding project conventions' has minor overlap risk with general code-review or onboarding skills.	4 / 5
	Total	17 / 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/repo-research-analyst/SKILL.md
Commit: cce36d3

Reviewed: 10 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.