source-driven-development

Grounds every implementation decision in official documentation. Use when you want authoritative, source-cited code free from outdated patterns. Use when building with any framework or library where correctness matters.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

85%

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

The body delivers an actionable, clearly sequenced workflow with concrete templates, examples, and checkpoints. Its only real weakness is mild verbosity in motivational framing sections that add length without adding instruction.

Suggestions

Trim the 'Common Rationalizations' table or condense it to the one or two rows that add guidance beyond what the Red Flags list already covers, to improve token efficiency.

Shorten the Overview rationale ('Training data goes stale, APIs get deprecated...') since the motivation is self-evident from the skill's purpose.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete tables, templates, and examples, but sections like the 'Common Rationalizations' table and Overview rationale explain motivation Claude already grasps, so it could be tightened.	2 / 3
Actionability	Highly actionable throughout: a dependency-file mapping table, an authoritative source hierarchy, BAD/GOOD fetch examples, citation code blocks, a conflict-surfacing template, and a verification checklist.	3 / 3
Workflow Clarity	The DETECT → FETCH → IMPLEMENT → CITE sequence is explicit with validation checkpoints (ask the user on ambiguous versions, surface conflicts, end-of-process checklist) and clear error-recovery guidance.	3 / 3
Progressive Disclosure	A single-file skill with no bundle references, but it is well-organized into clearly headed sections that map directly to each process step, supporting easy navigation.	3 / 3
	Total	11 / 12 Passed

Description

75%

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 answers both what the skill does and when to use it, with explicit trigger guidance and a distinctive niche. It is held back from a higher overall score by moderately abstract trigger phrasing and a single broad action rather than a list of specific ones.

Suggestions

Add a concrete list of actions (e.g., 'detects framework versions, fetches official docs, cites sources in code') rather than one broad claim to lift specificity.

Use natural trigger phrases users actually say (e.g., 'is this deprecated?', 'which version supports X?', 'official docs') instead of abstract phrasing like 'where correctness matters'.

Dimension	Reasoning	Score
Specificity	Names the domain ('grounds every implementation decision in official documentation', 'source-cited code') and the core action, but does not list multiple distinct concrete actions like the score-3 anchor does.	2 / 3
Completeness	Explicitly states what the skill does (grounds decisions in official docs, source-cited code) and provides two explicit 'Use when...' trigger clauses, satisfying both what and when.	3 / 3
Trigger Term Quality	Relevant trigger terms exist ('building with any framework or library where correctness matters'), but they lean abstract and miss common concrete phrasings a user would naturally say, so it falls short of full coverage.	2 / 3
Distinctiveness Conflict Risk	The niche (official-doc-grounded, source-cited implementation) is distinct and its triggers are unlikely to fire for unrelated skills.	3 / 3
	Total	10 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: addyosmani/agent-skills
Commit: 70b7506

Reviewed: 3 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.