Skip to content
Agentmart
Submit a tool

verification

AC/IV/TCのCoverage Map、max observed Risk、Required Controlsに対応する最小十分な検証をfail-fast順で行い、requirements gapとtest gapを分離する。

Skill by hondasports

IndexedMIT
Write a review

Chalk Labs

Need help deploying verification?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/hondasports-verification

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

AC/IV/TCのCoverage Map、max observed Risk、Required Controlsに対応する最小十分な検証をfail-fast順で行い、requirements gapとtest gapを分離する。

Use cases: testing

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/verification

What's inside

Skill name
verification
Description
AC/IV/TCのCoverage Map、max observed Risk、Required Controlsに対応する最小十分な検証をfail-fast順で行い、requirements gapとtest gapを分離する。
License
MIT
Instructions
199 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Verification

## 原則

「全部実行した」ではなく、**AC / relevant IVとrequired boundaryを証明した**ことをPASS条件にする。

PREPAREのCoverage Mapを使い、ここで仕様やtest caseをゼロから再導出しない。

required checksが通った後にcheckを広げたり繰り返したりするのは、次の時だけ。

- new content change
- material failure
- unresolved concern
- Required Controlが追加Evidenceを要求

それ以外はtask completionへ進む。

## Context discipline

通常読むのは:

- AC / IV / TC IDsと短いcontract
- behavior change map / changed files
- Risk / Controls
- Coverage Map
- current revision
- open findings

Issue全文・chat履歴・Requirements Skill全文はcontract conflict / requirements gap時だけ再読する。

## Fail-fast order

1. scopeable static / owning `tsconfig`
2. targeted unit / contract test
3. affected Worker / D1 integration test
4. required functional Playwright E2E
5. repo-wide regressionは原則CI Aftercare

上流失敗で下流結果が無意味になる場合、高価なcheckを先に走らせない。

修正後はdeltaで無効化されたcheckだけ再実行する。

## Low-impact test policy

reversible / low-impact変更で、implementation detailを鏡写しするだけの新規testを要求しない。

追加するtestはobservable AC / IVまたはRequired Controlをmaterialに証明するものだけにする。

ただし次は省略しない。

- Re:Me protected behaviorのboundary proof
- auth / ownership denial
- destructive / stateful failure path
- required browser E2E
- migration / data compatibility control

## Forward coverage

全AC / relevant IVについて:

- 対応TCまたは明示NOT_REQUIRED理由がある
- TCが実行されobservable contractを確認する
- multi-layer contractなら必要なboundaryまでEvidenceが届く

mock call回数や内部fieldだけではuser/caller contractの証明にならない場合がある。

## Reverse coverage

Implementationのbehavior change mapを確認する。

behavior-changing diffがAC / IV / design deviationへ対応しなければ `requirements_gap` としてPREPAREへ戻す。

## Requirements gap / Test gap

- `requirements_gap`: 必要behaviorがAC/IVに無い、またはdiffがcontract外 → PREPARE
- `test_gap`: AC/IVは明確やがProofが無い → test/evidence追加

Testが無いことを理由に仕様を無かったことにしない。

## Relevant dimensions

PREPAREで`relevant`になったものだけ確認する。

- happy path
- boundary
- error / failure
- empty / loading
- auth / ownership
- persistence / state transition
- caller compatibility
- concurrency / idempotency
- navigation / accessibility

新Evidenceがない限り、`not_applicable`観点をここで再議論しない。

## Re:Me controls

### Auth / access

Auth0 / Worker authorization / ownership変更では許可経路だけでなくdenial / cross-userを確認する。

sealed letterは到着・開封前の本人にも本文/attachmentを返さないことをserver boundaryで検証する。

### Data / state

D1 schema / validator / ownership / delivery state変更ではaffected route / query / mutation相当のAPI path / callerを確認する。

sent letter immutability、delivery idempotency、notification separation、exact schedule privacyを関連変更時に検証する。

legacy Convex → D1 migrationではsource export / mapping / rollbackに必要な範囲だけConvex側Evidenceを取る。

### R2+

Riskとrelevant dimensionに応じて boundary / error / partial failure / state compatibilityを追加する。

## Browser E2E

user-visible画面・遷移・操作を変更した場合、**その画面・遷移そのもの**をPlaywrightで踏む。

From hondasports/Re-Me, MIT.

More from hondasports/Re-Me

Signals

Stars
0
Forks
0
Open issues
2
Last commit (this folder)
Sep 5, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from hondasports

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get verification running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying verification?

CallGet help
Cite this page

verification skill. Agent Mart. https://agentmart.dev/skills/hondasports-verification (last updated 2026-10-24)