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 Use when you want authoritative, source-cited code free from outdated patterns.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

78%

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 ./skills/source-driven-development/SKILL.md

Quality

Content

81%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 well-structured, actionable instruction skill with an explicit multi-step workflow and strong verification checklist including feedback loops. Its only notable weakness is minor verbosity in the rationalizations and threat-model prose that could be tightened for token efficiency.

Suggestions

Tighten the 'Common Rationalizations' table and 'Retrieval Safety' prose to the highest-signal entries; several rows restate the same 'verify, don't trust memory' point and could be condensed to improve token efficiency.

Consider moving the detailed citation dialogue and CONFLICT DETECTED examples into a brief reference snippet while keeping the core rules inline, reducing body length without losing actionability.

Dimension	Reasoning	Score
Conciseness	The body is largely efficient and assumes Claude's competence (e.g. the DETECT→FETCH→IMPLEMENT→CITE flow, source-hierarchy table), but sections like 'Common Rationalizations' and the threat-model prose add some explanatory padding that could be trimmed without losing signal.	4 / 5
Actionability	It gives concrete, copy-paste-ready patterns (dependency-file mapping table, BAD/GOOD fetch examples, code-comment citation templates, a CONFLICT DETECTED dialogue) with minor gaps — it stops short of a fully executable fetch command template and relies on illustrative URLs.	4 / 5
Workflow Clarity	The four-step DETECT→FETCH→IMPLEMENT→CITE process is clearly sequenced with explicit checkpoints: ask the user on version ambiguity, surface doc-vs-code conflicts, flag unverified patterns, and a final verification checklist with explicit feedback loops for error recovery.	5 / 5
Progressive Disclosure	Content is well-organized into clearly signaled sections (Overview, When to Use, Process steps, Red Flags, Verification) with no bundle files to offload; it is a single-file skill so structure is appropriate, though the security subsection lightly references the external `security-and-hardening` skill rather than a bundled reference.	4 / 5
	Total	17 / 20 Passed

Description

75%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 what the skill does and when to use it with explicit trigger clauses, and uses appropriate third-person voice. Its main weaknesses are moderate specificity (one core action rather than several concrete ones) and broad distinctiveness that risks overlap with general coding skills.

Suggestions

Add 1-2 more concrete actions (e.g. 'detects framework versions from dependency files, fetches official docs, cites sources') to lift specificity from a single core action to a comprehensive list.

Narrow the trigger scope or add a distinguishing qualifier (e.g. 'when you want every framework-specific decision backed by a cited doc') to reduce overlap with general code-writing skills.

Dimension	Reasoning	Score
Specificity	The description names the domain ('implementation decisions' / 'framework or library') and one concrete action ('Grounds every implementation decision in official documentation') but does not enumerate several specific actions; it conveys the core activity of source-citing rather than a list of concrete operations.	3 / 5
Completeness	It explicitly answers both 'what' ('Grounds every implementation decision in official documentation') and 'when' via two explicit 'Use when' trigger clauses with concrete phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Phrases like 'authoritative, source-cited code', 'correctness matters', and 'building with any framework or library' are natural, with good keyword coverage; it stops short of comprehensive synonym/extension coverage, lacking common variations like specific framework names or 'docs'.	4 / 5
Distinctiveness Conflict Risk	The trigger 'building with any framework or library where correctness matters' is broad and would overlap with many code-writing skills; the source-citing niche helps but the framing is wide enough to risk overlap with related skills.	3 / 5
	Total	15 / 20 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
Path: skills/source-driven-development/SKILL.md
Commit: df1edb2

Reviewed: about 18 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.