---
title: "Specification to Code Compliance: review, setup & limitations · Undominated.ai"
canonical: https://undominated.ai/skills/trailofbits-spec-to-code-compliance/
description: "Compare authoritative requirements with implementation evidence and retain undecidable or unchecked requirements."
---

# Specification to Code Compliance: review, setup & limitations · Undominated.ai

> Compare authoritative requirements with implementation evidence and retain undecidable or unchecked requirements.

[← Explore all skills](/skills/)

SECURITY / trailofbits

# Specification to Code Compliance

Compare authoritative requirements with implementation evidence and retain undecidable or unchecked requirements.

 [See setup guidance ↓](#setup)[Original source ↗](https://github.com/trailofbits/skills/tree/8e54050ae63c2f62224c35b1616efe71865b4777/plugins/spec-to-code-compliance/skills/spec-to-code-compliance)

SOURCE REVIEW

 Reviewed 2026-10-14
 Evidence 3 linked sources
 Publisher trailofbits
 Licence [CC-BY-SA-4.0 ↗](https://github.com/trailofbits/skills/blob/8e54050ae63c2f62224c35b1616efe71865b4777/LICENSE)
 Revision 8e54050ae63c
 [Read what was—and wasn’t—checked ↓](#review)

“Check code against the documentation that specifies it - which requirements hold, which the code contradicts, which are absent, and what the code does that”

 [trailofbits · upstream description ↗](https://github.com/trailofbits/skills/blob/8e54050ae63c2f62224c35b1616efe71865b4777/plugins/spec-to-code-compliance/skills/spec-to-code-compliance/SKILL.md) Our analysis follows below.

01 / THE REASONING

## Why this made the selection.

 - The skill compares code with a document that says what the code is supposed to do. It is not a general bug hunt, and it is not a documentation rewrite.
- The rubric sets severity by consequence, not by how far the wording and the code diverged.
- The definition uses six implementation verdicts and independent code/document refutation, with explicit reporting for unreadable and unverified inputs.
- Audit a protocol or contract implementation against its actual specification

### A good fit for

 - Checking an implementation against a whitepaper, protocol note, or design document that already exists.
- Reading notChecked and unverified rows before treating a compliance report as complete.
- Audit a protocol or contract implementation against its actual specification
- Separate absent, partial, contradicted and stronger-than-required behavior

### Weigh up before choosing

 - Declared tools are Workflow, Task, Read, Grep, and Glob. There is no WebFetch in the frontmatter. The check writes local report files and is not meant to be done inline for a long requirement list.
- A bug that neither the code comment nor the document mentions is out of scope.
- This review did not execute the resource.
- Requires authoritative specification text and relevant source; general bug hunting without a spec is outside scope.
- Unreadable documents, fan-out limits, unverified refutations and notChecked requirements are coverage gaps, not compliance.
- Complete plugin agents and Workflow orchestration are required for the documented command.

02 / THE REVIEW RECORD

## What we actually inspected.

Source review has boundaries. A clear record is more useful than a “safe” badge.

### Material inspected

 - plugins/spec-to-code-compliance/skills/spec-to-code-compliance/SKILL.md
- plugins/spec-to-code-compliance/skills/spec-to-code-compliance/resources/DIVERGENCE_RUBRIC.md
- LICENSE
- README.md

### Our findings

 - Tools are local reads plus the workflow. It writes spec-compliance/REPORT.md and one file per requirement. It does not fetch the specification from the network by itself.
- It does not apply when there is no document of intended behaviour, and it does not look for bugs both artefacts are silent about.
- The workflow section says it does not make the severity judgment for you. The rubric ties that judgment to consequence, not to how far the words and the code diverged.
- The definition uses six implementation verdicts and independent code/document refutation, with explicit reporting for unreadable and unverified inputs.

### Not established by this review

 - The resource was not executed and its tools were not called.
- The compliance workflow was not dispatched and no report was written.
- No skill execution, authenticated service operation, or outcome benchmark was performed.

The review applies to the material and revision named here. A newer upstream release can change its behavior.

03 / PUT IT TO WORK

## Add a skill to your workflow.

[Upstream setup instructions ↗](https://github.com/trailofbits/skills/blob/8e54050ae63c2f62224c35b1616efe71865b4777/README.md)
 - Check out trailofbits/skills at 8e54050ae63c2f62224c35b1616efe71865b4777 and install the complete spec-to-code-compliance plugin through the publisher-supported host workflow, retaining sibling agents, workflows, scripts and references.
- Provide specification and code paths, scope and requirement limit; retain the complete plugin.
- Inspect the requirements inventory and unverified/notChecked sections with REPORT.md; review consequences of deviations rather than wording alone.

### Before you start

 - A local checkout and the tools required by the selected workflow

### Compatibility

A supported full-plugin host; Workflow orchestration requires the Workflow capability named in the definition

### Local instructions; runtime access depends on the workflow

 - Read specification and source files; run model analysis/refutation workers and write compliance reports.

### Cost model

Instructions are free; agent usage and separately licensed tools can incur charges.

04 / FOLLOW THE EVIDENCE

## The source trail.

Our notes are separate from the original resource. Check upstream before adopting a new version.

 - [Pinned skill definition ↗](https://github.com/trailofbits/skills/blob/8e54050ae63c2f62224c35b1616efe71865b4777/plugins/spec-to-code-compliance/skills/spec-to-code-compliance/SKILL.md) Checked 2026-10-14 https://github.com/trailofbits/skills/blob/8e54050ae63c2f62224c35b1616efe71865b4777/plugins/spec-to-code-compliance/skills/spec-to-code-compliance/SKILL.md Supports: summary, whySelected, bestFor, limitations, install, access, review
- [Publisher repository and installation guidance ↗](https://github.com/trailofbits/skills/blob/8e54050ae63c2f62224c35b1616efe71865b4777/README.md) Checked 2026-10-14 https://github.com/trailofbits/skills/blob/8e54050ae63c2f62224c35b1616efe71865b4777/README.md Supports: install
- [CC-BY-SA-4.0 licence ↗](https://github.com/trailofbits/skills/blob/8e54050ae63c2f62224c35b1616efe71865b4777/LICENSE) Checked 2026-10-14 https://github.com/trailofbits/skills/blob/8e54050ae63c2f62224c35b1616efe71865b4777/LICENSE Supports: license

KEEP COMPARING

## Other approaches to consider.

Related by category or shared topics. These are alternatives to inspect, not a measured quality order.

 [### Burp Project Parser ↗ Extract and search captured Burp traffic while distinguishing empty results from parser startup failures.](/skills/trailofbits-burpsuite-project-parser/)[### C and C++ Security Review ↗ Coordinate scoped native C/C++ security review and assemble findings with an explicit coverage ledger.](/skills/trailofbits-c-review/)[### DWARF Debug Information ↗ Inspect DWARF symbols, types, line tables and address mappings using tool-specific commands.](/skills/trailofbits-dwarf-expert/)

 [AI Tools ↗](/tools/)[Skills ↗](/skills/)[Agents ↗](/agents/)[MCP Servers ↗](/mcp-servers/)[Workflows ↗](/workflows/)

## Continue your investigation

 - [Choose a toolkit](/tools/)
- [Inspect execution hosts](/agents/)
- [Check tool access](/mcp-servers/)
- [Check project dependencies](/check-repo/)
