Name: spec-to-code-compliance
Rating: 60 (1 reviews)
Author: administrakt0r

spec-to-code-compliance

Verifies code implements exactly what documentation specifies for blockchain audits. Use when comparing code against whitepapers, finding gaps between specs and implementation, or performing compliance checks for protocol implementations.

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/spec-to-code-compliance/SKILL.md

The canonical home for this skill is spec-to-code-compliance in administrakt0r/AI-Agents-Safe-Coding-Skills

Quality

Content

56%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-sequenced seven-phase audit workflow with strong taxonomies and an explicit completeness gate, but it is weakened by verbosity/redundancy and by deferring concrete examples and checklists to bundle files that are not actually present.

Suggestions

Create the referenced bundle files (IR_EXAMPLES.md, OUTPUT_REQUIREMENTS.md, COMPLETENESS_CHECKLIST.md) under references/ — or inline a single compact worked example and checklist — so the deferred guidance is actually reachable.

Tighten redundancy: consolidate the ANTI-HALLUCINATION REQUIREMENTS with the GLOBAL RULES, keep a single 'See IR_EXAMPLES.md' pointer, and trim the Rationalizations table to the highest-value rows.

Add explicit inter-phase validation checkpoints (e.g. 'Spec-IR complete before starting Phase 3') so the sequence is gated step-by-step, not only at the final completeness review.

Dimension	Reasoning	Score
Conciseness	The phase-by-phase structure is mostly efficient and assumes competence, but the repeated 'See IR_EXAMPLES.md' pointers (phases 2, 3, 4, 5), the Rationalizations table, and the restated ANTI-HALLUCINATION section (which echoes the GLOBAL RULES) are padding that could be tightened, matching anchor 3 rather than the lean anchor 4.	3 / 5
Actionability	Concrete taxonomies are provided (the match_type enum, CRITICAL/HIGH/MEDIUM/LOW severity levels, the 16-section report outline), but the actionable worked examples are deferred to IR_EXAMPLES.md, which is not present in the bundle, leaving key details incomplete — anchor 3.	3 / 5
Workflow Clarity	Phases 0–6 are clearly sequenced and a Completeness Verification step with confidence thresholds (>=0.8) gates the final report, but inter-phase validation checkpoints are mostly implicit and the verifying checklist lives in a missing COMPLETENESS_CHECKLIST.md, so it does not reach the explicit-feedback-loop anchor 5.	4 / 5
Progressive Disclosure	References are clearly signaled and one level deep (IR_EXAMPLES.md, OUTPUT_REQUIREMENTS.md, COMPLETENESS_CHECKLIST.md), but none of these files exist in references/, scripts/, or assets/, so navigation is broken and the SKILL.md effectively inlines what should be split — anchor 3 rather than the well-organized anchor 4.	3 / 5
	Total	13 / 20 Passed

Description

83%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, third-person description that explicitly answers both what the skill does and when to use it, with concrete domain-specific trigger terms. Minor gaps in action distinctiveness and keyword synonyms keep it just below top marks on specificity, trigger quality, and distinctiveness.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'Verifies code implements exactly what documentation specifies', 'comparing code against whitepapers', 'finding gaps between specs and implementation', 'compliance checks for protocol implementations' — but the actions overlap conceptually (verify/audit/compliance), so it is not quite the comprehensive, distinct coverage of anchor 5.	4 / 5
Completeness	It clearly states the 'what' ('Verifies code implements exactly what documentation specifies for blockchain audits') and the 'when' with concrete trigger phrases ('Use when comparing code against whitepapers, finding gaps..., or performing compliance checks...'), matching the anchor 5 example of explicitly answering both what and when.	5 / 5
Trigger Term Quality	Good keyword coverage with natural domain terms a blockchain auditor would say — 'whitepapers', 'specs', 'implementation', 'compliance checks', 'protocol implementations', 'blockchain audits' — but it omits common synonyms/extensions (e.g. 'specification', 'yellow paper', 'design doc'), keeping it just below anchor 5.	4 / 5
Distinctiveness Conflict Risk	The blockchain-audit / spec-to-code-compliance niche is mostly distinct with clear triggers, but there is minor overlap risk with the explicitly referenced 'audit-context-building' skill and other general audit skills, so it sits at anchor 4 rather than the minimal-conflict anchor 5.	4 / 5
	Total	17 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills-claude/skills/spec-to-code-compliance/SKILL.md
Commit: 57c135b

Reviewed: 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.