AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Spec Vs Impl Checker

skill-firstp1ck-pi-coding-agent-forge-spec-vs-impl-checker · by Firstp1ck

Agents should invoke this skill when a spec, plan, README, issue, or requirement must be verified against implementation. Traces requirements to code, checks interface contracts, and reports gaps or mismatches.

No reviews yet
0 installs
5 views
0.0% view→install

Install

$ agentstack add skill-firstp1ck-pi-coding-agent-forge-spec-vs-impl-checker

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-firstp1ck-pi-coding-agent-forge-spec-vs-impl-checker)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
16d ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Spec Vs Impl Checker? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Spec-vs-Implementation Checker

Systematically verify that every specification requirement is implemented correctly.

Process

Step 1 — Build Requirement Registry

Extract every requirement from the spec and combined plan into a structured registry:

| Req ID | Source | Section | Requirement | Type |
|---|---|---|---|---|
| REQ-001 | spec.md | 4.1 | Users can register with email/password | Functional |
| REQ-002 | spec.md | 4.1 | Email must be validated (format + uniqueness) | Validation |
| REQ-003 | combined-plan.md | 2 | Passwords hashed with bcrypt (cost 12) | Security |
| REQ-004 | architecture.md | 3.2 | Auth module exposes /api/auth/* endpoints | Interface |

Step 2 — Trace to Implementation

For each requirement, find the implementing code:

| Req ID | Implementation | File(s) | Test(s) | Status |
|---|---|---|---|---|
| REQ-001 | register() handler | src/auth/handlers.rs:45 | test_register | VERIFIED |
| REQ-002 | validate_email() | src/auth/validation.rs:12 | test_email_validation | VERIFIED |
| REQ-003 | hash_password() | src/auth/crypto.rs:8 | — | UNTESTED |
| REQ-004 | router config | src/auth/mod.rs:20 | test_auth_routes | VERIFIED |

Step 3 — Verify Each Requirement

For each traced requirement:

  1. Read the code — Does the implementation match what the spec describes?
  2. Check the tests — Is there a test that verifies this specific requirement?
  3. Run the test — Does the test actually pass?
  4. Check edge cases — Does the implementation handle the edge cases the spec implies?

Status values:

| Status | Meaning | |---|---| | VERIFIED | Implemented correctly, tested, test passes | | IMPLEMENTED | Code exists but no specific test | | UNTESTED | Code exists, test exists but doesn't cover this requirement | | PARTIAL | Partially implemented (e.g., happy path only, missing error handling) | | MISSING | No implementation found for this requirement | | DEVIATED | Implementation differs from spec (document how) |

Step 4 — Interface Contract Verification

For each module interface defined in the architecture:

  • Verify the interface exists as specified (endpoints, function signatures, types)
  • Verify error contracts (what errors can be returned, in what format)
  • Verify data contracts (request/response shapes match the architecture doc)
  • Test cross-module integration points

Step 5 — Generate Traceability Report

# Spec-vs-Implementation Report — 

**Date:** YYYY-MM-DD
**Spec Requirements:** N
**Verified:** X (Y%)
**Partial/Missing:** Z

## Requirement Traceability Matrix

[Full table from steps 1-3]

## Interface Contract Status

[Table of module interfaces and their verification status]

## Gaps Found

### Missing Implementations
- REQ-XXX: [description, severity]

### Deviations from Spec
- REQ-YYY: Spec says [X], implementation does [Y]. Impact: [assessment]

### Untested Requirements
- REQ-ZZZ: Implemented but no test coverage

When to Escalate

  • Missing implementation → Bug report to Forge
  • Spec ambiguity → Flag to Clawpick for Sage/Prism clarification
  • Architecture deviation → Flag to Arc
  • Security constraint not met → Flag to Zero

Watchdog skill — Spec-vs-implementation traceability and verification

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.