verify-against-spec SKILL.md skillA

verify-against-spec from webreactiva/yesyak is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add webreactiva/yesyak/verify-against-spec@git:20261017.b634987

Pins git:20261017.b634987 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
webreactiva/yesyak
Path
skills/verify-against-spec/SKILL.md
Versions recorded
4
Latest version
git:20261017.b634987, committed Oct 17, 2026
First version recorded
Sep 27, 2026
Size
2,761 bytes
Repository stars
3
License
MIT

Verifies an implementation against its spec criterion by criterion. It maps every acceptance criterion to tests and code, fills coverage gaps with reproduction scripts, lists deviations that are not criteria, and writes a verification report. Use it whenever the user asks to check the implementation against the spec, which criteria are met or not, whether the work is complete, or for a coverage or compliance report before review or merge.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Verify against spec

Passing tests are not the goal. The question is "is every promise in the spec kept, and how do we know".

## 1. Collect evidence

1. Run the full check and record the result.
2. List every test name with a verbose reporter, for example `npx vitest run --reporter=verbose` or `pytest -v`.
3. For each acceptance criterion, find the tests that cover it and the code that implements it.

## 2. Classify each criterion

| Level | Meaning |
| --- | --- |
| Suite, full | A test in the suite covers every part of the criterion |
| Suite, partial | Tests cover part of it; you checked the rest with a script now |
| Logic tested, entry point manual | The logic has tests; you checked the command or script around it by hand |
| Manual only | The spec says it is manual, or no automated check is possible |
| ❌ Not met | The behavior differs from the criterion |

Be strict. A test that checks the ids in a list does not cover "shows id, customer, total and state".

## 3. Check the gaps with a script
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add webreactiva/yesyak/verify-against-spec@sha256:852cbbedbeb3fa69

The line at the top of this page pins the label git:20261017.b634987, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_pfvwiszwagezroai.svg)](https://markdownregistry.com/a/art_pfvwiszwagezroai)

2 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 4 versions of this file, between Sep 27, 2026 and Oct 17, 2026, about one every 7 days.

versioncommittedcommitsizeaudit
git:20261017.b634987 latest2026-10-17 b634987 2,761 BA view · diff
git:20261017.04386562026-10-17 0438656 2,755 BA view · diff
git:20260927.87257af2026-09-27 87257af 2,650 BA view · diff
git:20260927.d224a3a2026-09-27 d224a3a 2,641 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (2761 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

webreactiva/yesyak · 3 stars · license MIT · pushed 2026-10-31 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_pfvwiszwagezroai
GET https://markdownregistry.com/api/v1/resolve?ref=webreactiva/yesyak/verify-against-spec
GET https://markdownregistry.com/api/v1/blob/852cbbedbeb3fa6946a51c56700dd0d5beb07c0cafc3284da56c422f56e593ae

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from webreactiva/yesyak

yak-bench SKILL.md skill
webreactiva/yesyak · .claude/skills/yak-bench/SKILL.md · Internal benchmark of this repository. It takes a small real project, drives a weaker agent (OpenCode in tmux, as a…
git:20261030.4afff19 · audit A · 3 stars
AGENTS.md AGENTS.md file
webreactiva/yesyak · AGENTS.md
git:20261017.75a50dc · audit A · 3 stars
CLAUDE.md CLAUDE.md file
webreactiva/yesyak · CLAUDE.md
git:20260928.79ace91 · audit B · 3 stars
agent-hook-guard SKILL.md skill
webreactiva/yesyak · skills/agent-hook-guard/SKILL.md · Turns one problem that the reviews found into one hook of the agent. A hook is a check that the agent tool runs by…
git:20261017.b634987 · audit A · 3 stars
ask-yak SKILL.md skill
webreactiva/yesyak · skills/ask-yak/SKILL.md · Tells the user where their work is in the YesYak process and what comes next. It reads the branch, the progress file…
git:20261017.75a50dc · audit A · 3 stars
browser-acceptance-testing SKILL.md skill
webreactiva/yesyak · skills/browser-acceptance-testing/SKILL.md · Tests acceptance criteria and edge cases as an end user in a real browser (Chrome DevTools MCP, Playwright or the…
git:20261017.b634987 · audit A · 3 stars
bug-intake SKILL.md skill
webreactiva/yesyak · skills/bug-intake/SKILL.md · Entry point for one bug report. Capture it, triage it without changing anything (severity, owning area, layers crossed…
git:20261023.b04ffec · audit A · 3 stars
customize-yak SKILL.md skill
webreactiva/yesyak · skills/customize-yak/SKILL.md · Adapts the YesYak process to a project or a person without editing any skill. It detects what the project already has…
git:20261031.1bf6fd8 · audit A · 3 stars
decision-record-log SKILL.md skill
webreactiva/yesyak · skills/decision-record-log/SKILL.md · Convention for recording implementation decisions as ADRs (Architecture Decision Records) in docs/decisions/, each with…
git:20261017.b634987 · audit A · 3 stars
domain-language SKILL.md skill
webreactiva/yesyak · skills/domain-language/SKILL.md · Fixes the domain language of one feature after the interview, so the spec, code, tests and UI all say the same thing…
git:20261017.b634987 · audit A · 3 stars
execute-plan-loop SKILL.md skill
webreactiva/yesyak · skills/execute-plan-loop/SKILL.md · Implements a plan step by step in a loop until the end. Each step has one capability, tests and a manual check…
git:20261017.b634987 · audit A · 3 stars
feature-delivery-pipeline SKILL.md skill
webreactiva/yesyak · skills/feature-delivery-pipeline/SKILL.md · Orchestrates the full feature workflow from a vague request to a reviewed pull request, with a checkpoint for the user…
git:20261023.b04ffec · audit A · 3 stars

Every file in webreactiva/yesyak

Browse by kind, by grade A, or by owner.