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.
87
83%
Does it follow best practices?
Impact
92%
1.12xAverage score across 3 eval scenarios
Passed
No known issues
Quality
Discovery
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.
This is a reasonably well-crafted description that clearly defines its niche and includes an explicit 'Use when' clause with a specific trigger condition. Its main weaknesses are moderate specificity in the actions described and limited coverage of natural trigger terms users might use when they need this skill.
Suggestions
Add more concrete actions such as 'compare function signatures, check parameter consistency, highlight missing or extra fields' to improve specificity.
Expand trigger terms to include natural variations like 'specification', 'out of sync', 'spec mismatch', 'code doesn't match spec', or 'sync spec'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (spec-code alignment) and some actions (detects drift, surfaces discrepancies, user decides whether to update spec or code), but the actions are somewhat abstract—it doesn't specify concrete operations like 'compare function signatures', 'check parameter types', or 'generate diff reports'. | 2 / 3 |
Completeness | Clearly answers both what ('Detects drift between spec and code, surfaces discrepancies, user decides whether to update spec or code') and when ('Use when both a spec file and its implementation are in context') with an explicit trigger clause. | 3 / 3 |
Trigger Term Quality | Includes relevant terms like 'spec', 'implementation', 'drift', and 'discrepancies', but misses common natural variations users might say such as 'specification', 'out of sync', 'spec mismatch', 'code doesn't match spec', or 'sync spec with code'. | 2 / 3 |
Distinctiveness Conflict Risk | The niche of spec-implementation alignment is quite specific and unlikely to conflict with other skills. The trigger condition ('both a spec file and its implementation are in context') is distinctive and well-scoped. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
92%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a high-quality skill that clearly defines both passive awareness principles and an explicit alignment workflow. The drift categorization is comprehensive and the workflow includes proper validation checkpoints, user decision gates, and a summary template. The only minor weakness is that all content lives in one file, though the length is reasonable enough that this is a minor concern.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every section earns its place. No unnecessary explanations of what specs or drift are in abstract terms—it jumps straight into categorization and actionable workflow. The drift categories table is dense and useful, not padded. | 3 / 3 |
Actionability | Provides concrete file patterns to search, a specific mapping table format, a numbered discrepancy template with exact formatting (DRIFT-NN with quoted spec/code), explicit decision options, and post-change validation steps (lint/typecheck/tests). Fully actionable without being code-heavy, which is appropriate for this instruction-oriented skill. | 3 / 3 |
Workflow Clarity | Six clearly sequenced steps with explicit validation checkpoints: run lint/typecheck after code changes, run tests if they exist, confirm before non-trivial edits, and a summary step that tracks resolution status. The feedback loop of 'outline change → confirm → edit → validate' is well-defined. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear sections (Principles vs Workflow) and good use of headers, but everything is in a single file. The drift categories and mutation policy sections could potentially be referenced separately for a cleaner overview, though at ~80 lines this is borderline acceptable as a single file. | 2 / 3 |
Total | 11 / 12 Passed |
Validation
100%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
- NeverSight/skills_feed
- Commit
f772de4
- Reviewed
Table of Contents
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.