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 Use when you want authoritative, source-cited code free from outdated patterns.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

47%

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

The canonical home for this skill is source-driven-development in addyosmani/agent-skills

Quality

Content

77%Scale 1-3

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

This is a well-crafted skill with strong actionability and workflow clarity. The four-step process is clearly defined with concrete examples, conflict resolution templates, and a thorough verification checklist. The main weakness is moderate verbosity — the 'Common Rationalizations' table and some explanatory text could be trimmed since they explain reasoning Claude doesn't need, and the document could benefit from splitting into a concise overview with supporting reference files.

Suggestions

Trim or remove the 'Common Rationalizations' table — it explains motivations Claude doesn't need and adds ~15 lines of non-actionable content.

Consider extracting the 'Red Flags' and 'Verification' checklist into a separate reference file to keep the main SKILL.md focused on the core 4-step process.

Dimension	Reasoning	Score
Conciseness	The skill is well-written but includes some unnecessary verbosity. The 'Common Rationalizations' table, while useful, is somewhat preachy and explains things Claude should already understand (e.g., why verification matters). The 'When to Use' / 'When NOT to use' sections and the ASCII process diagram add bulk without proportional value. The core process could be tightened significantly.	2 / 3
Actionability	The skill provides highly concrete, actionable guidance: specific file names to check for versions, exact URL patterns for fetching docs, citation format examples with real code, conflict resolution templates, and a clear source hierarchy table. The examples are realistic and copy-paste ready (e.g., the useActionState citation pattern, the stack detection output format).	3 / 3
Workflow Clarity	The four-step process (Detect → Fetch → Implement → Cite) is clearly sequenced with explicit validation checkpoints. The skill includes feedback loops for conflicts (surface to user, don't silently pick), verification for unverified patterns, and a comprehensive verification checklist at the end. The conflict detection template is a strong validation checkpoint.	3 / 3
Progressive Disclosure	The content is well-structured with clear headers and sections, but it's a monolithic document at ~200 lines that could benefit from splitting. The Red Flags, Common Rationalizations, and Verification checklist sections could be separate reference files. However, since no bundle files exist, the single-file approach is understandable, and the internal organization with headers is reasonable.	2 / 3
	Total	10 / 12 Passed

Description

17%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This description suffers from vague, buzzword-heavy language ('authoritative, source-cited code free from outdated patterns') without specifying concrete actions the skill performs. The trigger scope is far too broad ('any framework or library where correctness matters'), making it indistinguishable from other coding skills and likely to cause conflicts in a multi-skill environment.

Suggestions

Replace vague language with specific concrete actions, e.g., 'Looks up official documentation, validates API usage against current docs, and cites documentation sources in code comments.'

Narrow the 'Use when...' clause with specific trigger terms users would say, e.g., 'Use when the user asks to check the docs, verify API usage, find official examples, or ensure code follows current library documentation.'

Add distinctive scope boundaries to reduce conflict risk, e.g., specifying what kind of documentation lookup this performs versus general coding assistance.

Dimension	Reasoning	Score
Specificity	The description uses vague, abstract language like 'grounds every implementation decision' and 'authoritative, source-cited code free from outdated patterns.' It does not list any concrete actions (e.g., 'looks up documentation,' 'validates API usage,' 'checks version compatibility').	1 / 3
Completeness	It has a 'Use when...' clause, which addresses the 'when' question, but the 'what' is extremely vague ('grounds every implementation decision'). The 'when' clause is also overly broad ('any framework or library where correctness matters'), making it nearly universal rather than a useful trigger.	2 / 3
Trigger Term Quality	The description lacks natural keywords a user would actually say. Terms like 'authoritative,' 'source-cited,' and 'outdated patterns' are not phrases users naturally use. Missing practical trigger terms like 'documentation,' 'docs,' 'API reference,' 'check docs,' or specific framework names.	1 / 3
Distinctiveness Conflict Risk	The description is extremely generic — 'any framework or library where correctness matters' could apply to virtually any coding skill. It would conflict with nearly every development-related skill in a collection.	1 / 3
	Total	5 / 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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: finlay611/agent-skills
Path: skills/source-driven-development/SKILL.md
Commit: 45e2460

Reviewed: 4 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.