specalign

Align spec files with implementation. Detects drift between spec and code, surfaces discrepancies, user decides whether to update spec or code. Use when both a spec file and its implementation are in context.

1.12x

Quality

81%

Does it follow best practices?

Impact

92%

1.12x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Quality

Content

75%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.

A well-structured, actionable instruction-only skill with a clear six-step workflow and built-in validation. The main drag is redundancy between the always-active Principles section and the workflow steps, which keeps conciseness and progressive_disclosure at 4.

Suggestions

Collapse the 'Principles (Always Active)' Mutation Policy and Bidirectional Awareness bullets into the workflow steps they duplicate, or reference them once to remove the redundancy and lift conciseness.

Add an explicit feedback loop in Step 5: 'If lint/typecheck/tests fail, fix and re-run until green' to upgrade workflow_clarity to 5.

Include one short worked DRIFT-NN example with real quoted spec/code lines so the report template is unambiguous and actionability reaches 5.

Dimension	Reasoning	Score
Conciseness	Lean and free of concept-padding, using tables and templates instead of prose, but the 'Principles (Always Active)' section (Mutation Policy, Bidirectional Awareness) partially duplicates Step 5 and the workflow, so not every token earns its place.	4 / 5
Actionability	Provides concrete, copy-paste-ready templates (DRIFT-NN report, mapping table, summary) and specific search globs ('.spec.md', '-spec.md', 'SPEC.md'), with minor gaps — no fully worked real example showing a populated DRIFT entry.	4 / 5
Workflow Clarity	Six clearly sequenced steps with an explicit decision gate (Step 4) and validation (lint/typecheck/tests in Step 5), so the destructive-op cap at 3 does not apply; falls short of 5 because the 'if validation fails, fix and re-validate' feedback loop is implicit rather than stated.	4 / 5
Progressive Disclosure	A single self-contained SKILL.md with clear headers, a mapping table, and no nested references; no bundle files exist to reference. Minor organization gaps from the Principles/Workflow redundancy keep it at 4 rather than 5.	4 / 5
	Total	16 / 20 Passed

Description

87%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.

A strong description that explicitly states both capabilities and a concrete use-when trigger, with a distinctive niche. It is slightly short of comprehensive action coverage and a few natural synonyms, keeping specificity and trigger_term_quality at 4.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions — 'Detects drift between spec and code, surfaces discrepancies, user decides whether to update spec or code' — but stops short of the comprehensive multi-action list of a 5.	4 / 5
Completeness	Clearly answers 'what' ('Align spec files with implementation. Detects drift... surfaces discrepancies, user decides...') and 'when' with an explicit concrete 'Use when both a spec file and its implementation are in context' trigger phrase.	5 / 5
Trigger Term Quality	Good coverage of relevant terms ('spec file', 'implementation', 'spec', 'code', 'drift', 'discrepancies') with a 'Use when' clause, but lacks common synonyms like 'specification' and the trigger 'both a spec file and its implementation are in context' is somewhat technical rather than conversational.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (spec-vs-implementation drift) with a trigger requiring both a spec file and its implementation in context, making accidental firing for unrelated skills unlikely.	5 / 5
	Total	18 / 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: NeverSight/skills_feed
Path: data/skills-md/0xbigboss/claude-code/specalign/SKILL.md
Commit: 2f57aec

Reviewed: about 22 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.