Home / lamngockhuong / aiteamkit · skills/verify/SKILL.md · GitHub

verify skillA

verify is agent-read markdown (skill) from lamngockhuong/aiteamkit: Confirm a change works by running the real thing: start the app the way the project starts it, exercise it with real requests, assert the side effect in the data rather than the status code, compare the screen against the design when asked, and stop after three rounds with a named person rather than patching indefinitely. Use when the suite is green and nobody has yet seen the feature work, before handing a ticket to QA, or before a release goes out. Triggers on: "verify", "verify this works", ".

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

What the file says

# Verify on the Running System (`atk:verify`)

Runs the thing and looks. A green suite proves that the checks somebody wrote still pass; it does
not prove that the record was written, that the job reached the queue, or that the screen renders
what the design says. This skill closes that distance, on the real application, with the commands
the project itself uses.

It has one built-in limit. After three rounds of fix and retry it stops and hands the problem to a
person by name, because a failure that survives three fixes is usually a design question wearing a
bug's clothes.

## Scope

Handles: starting the application the way `.atk/profile.md` says to start it, waiting for the
readiness signal, exercising the change with real requests or real interaction, asserting the side
effect in data, queue, and logs, comparing screens against the design under `--ui`, retrying at most
three times, escalating by name past that, and stopping every process it started.

Does NOT handle: writing the test plan or the test cases, which is `atk:qa` and happens before this
skill has anything to run; proving the cause of a defect (`atk:fix`); building the change
…

Read the whole file at its exact version.

How to install

Latest version
mdr add lamngockhuong/aiteamkit/verify@git:20260922.2c10be8
Exact content
mdr add lamngockhuong/aiteamkit/verify@sha256:230d85095070ec48

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_v2zajehw2vlxh2vb.svg)](https://markdownregistry.com/a/art_v2zajehw2vlxh2vb)

1 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260922.2c10be8 latest2026-09-22 2c10be8 15,311 BA view · diff
git:20260922.3896e1f2026-09-22 3896e1f 15,231 BA view · diff
git:20260922.c7615a52026-09-22 c7615a5 14,727 BA view · diff
git:20260920.d282a912026-09-20 d282a91 14,294 BA view · diff
git:20260918.73a33f42026-09-18 73a33f4 14,246 BA view · diff
git:20260918.dcc08e92026-09-18 dcc08e9 14,144 BA view · diff
git:20260918.cddb6932026-09-18 cddb693 14,136 BA view · diff
git:20260918.93b0fac2026-09-18 93b0fac 13,985 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, 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 (15311 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

lamngockhuong/aiteamkit · 5 stars · license MIT · pushed 2026-09-24 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_v2zajehw2vlxh2vb
GET https://markdownregistry.com/api/v1/resolve?ref=lamngockhuong/aiteamkit/verify
GET https://markdownregistry.com/api/v1/blob/230d85095070ec48904a3112edfc3d364a55347f75f8ab04010201f68a36edb8

Your agent 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.

More from lamngockhuong/aiteamkit

CLAUDE.md claude
lamngockhuong/aiteamkit · CLAUDE.md
git:20260924.59d6cfa · audit A · 5 stars
breakdown skill
lamngockhuong/aiteamkit · skills/breakdown/SKILL.md · Break an epic or a design document into owned, sequenced tasks: one deliverable each, an owner, a dependency order, the…
git:20260922.c7615a5 · audit A · 5 stars
catchup skill
lamngockhuong/aiteamkit · skills/catchup/SKILL.md · Summarise an epic or a pull request for someone who was not in the conversation that produced it: what the work is and…
git:20260921.7fc6a05 · audit A · 5 stars
convention skill
lamngockhuong/aiteamkit · skills/convention/SKILL.md · Extract, record, and enforce the coding conventions a team actually follows: branch and commit rules, naming, layering…
git:20260923.3195eb0 · audit A · 5 stars
design-doc skill
lamngockhuong/aiteamkit · skills/design-doc/SKILL.md · Write the technical design document a team reviews before coding, plus the ADR that records the decision behind it…
git:20260924.59d6cfa · audit A · 5 stars
estimate skill
lamngockhuong/aiteamkit · skills/estimate/SKILL.md · Estimate a backlog and fill a sprint against real team capacity: size each item with a stated basis, mark the…
git:20260922.c7615a5 · audit A · 5 stars
fix skill
lamngockhuong/aiteamkit · skills/fix/SKILL.md · Fix a defect the way a team reviewer will accept: capture the failure verbatim, prove the cause before changing a line…
git:20260922.2c10be8 · audit A · 5 stars
git skill
lamngockhuong/aiteamkit · skills/git/SKILL.md · Carry a finished piece of work into version control: read what changed, stage it after scanning for anything that must…
git:20260922.2c10be8 · audit A · 5 stars
handover skill
lamngockhuong/aiteamkit · skills/handover/SKILL.md · Hand work over to another person or team so nothing depends on the leaver's memory: the true state of each item…
git:20260920.d282a91 · audit A · 5 stars
help skill
lamngockhuong/aiteamkit · skills/help/SKILL.md · Answer which atk skill to run. With no argument it reads the state of the project, meaning the profile, the artifacts…
git:20260923.1028253 · audit A · 5 stars
implement skill
lamngockhuong/aiteamkit · skills/implement/SKILL.md · Write the code for a piece of work the way a team will accept it: decide whether the work needs a plan before a line is…
git:20260924.59d6cfa · audit A · 5 stars
incident skill
lamngockhuong/aiteamkit · skills/incident/SKILL.md · Run a production incident and close it properly: a timeline built from evidence, impact and severity, the proven root…
git:20260922.c7615a5 · audit A · 5 stars

Every file in lamngockhuong/aiteamkit

Other files named verify

verify skill
yeachan-heo/oh-my-claudecode · skills/verify/SKILL.md · Verify that a change really works before you claim completion
git:20260401.ff9223c · audit A · 39,312 stars
verify skill
zenbu-labs/terminal-browser · .claude/skills/verify/SKILL.md · Drive an engine app headlessly in a pty, record a video of the whole verification, and open a summary page (video +…
git:20260721.c3339dc · audit A · 3,204 stars
verify skill
alsk1992/cloddsbot · src/skills/bundled/verify/SKILL.md · Verify agent identity using ERC-8004 on-chain registry
git:20260130.5926fbf · audit A · 2,830 stars
verify skill
codeaholicguy/ai-devkit · skills/verify/SKILL.md · AI DevKit · Enforce evidence-based completion claims — require fresh command output before reporting success. Use when…
git:20260703.7628b9e · audit A · 1,633 stars
verify skill
sethgammon/citadel · skills/verify/SKILL.md · Self-test the Citadel hook pipeline from within a live session. Exercises real tool calls (Write, Edit, Bash, Read) and…
git:20260919.f58febd · audit A · 923 stars
verify skill
oliver-kriska/claude-elixir-phoenix · plugins/elixir-phoenix/skills/verify/SKILL.md · Verify Elixir/Phoenix changes — compile, format, and test in one loop. Use after implementation, before PRs, or after…
git:20260724.918f809 · audit A · 555 stars
verify skill
yonatangross/orchestkit · plugins/ork/skills/verify/SKILL.md · Grade work that already exists and decide whether it can merge. Runs the project's current unit, integration, and E2E…
v4.7.0 · audit A · 283 stars
verify skill
sd0xdev/sd0x-harness · skills/verify/SKILL.md · Verification loop — lint -> typecheck -> unit -> integration -> e2e
git:20260404.1c6641c · audit A · 189 stars

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