Skip to content
Agentmart
Submit a tool

requirements

PREPAREを所有し、Spec Confidence、scope、ID付きAcceptance Criteria/Invariant、Risk、Required Controls、Coverage Mapを一度だけ確定する。長文再読を避けつつ仕様・要件・test case漏れを早期検出する。

Skill by hondasports

IndexedMIT
Write a review

Chalk Labs

Need help deploying requirements?

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-requirements

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

PREPAREを所有し、Spec Confidence、scope、ID付きAcceptance Criteria/Invariant、Risk、Required Controls、Coverage Mapを一度だけ確定する。長文再読を避けつつ仕様・要件・test case漏れを早期検出する。

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/requirements

What's inside

Skill name
requirements
Description
PREPAREを所有し、Spec Confidence、scope、ID付きAcceptance Criteria/Invariant、Risk、Required Controls、Coverage Mapを一度だけ確定する。長文再読を避けつつ仕様・要件・test case漏れを早期検出する。
License
MIT
Instructions
244 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# PREPARE / Requirements

## 目的

実装前に「何を作るか」「何を守るか」「何を証明するか」を一度だけ決める。

所有するもの:

- Goal / In scope / Out of scope
- `ACxx` Acceptance Criteria
- `IVxx` Preserve / Invariant
- relevant requirement dimensions
- material assumptions
- Spec Confidence
- Risk / max observed Risk
- Required Controls
- compact Coverage Map
- `TCxx` Verification plan
- 必要十分な Impact summary

`C0` のままImplementationへ進まない。

## Instruction priority / autonomy

current explicit user instructionを、一般的なSkill guidanceより優先する。Safety invariantは別。

ユーザーがすでに許可したread-only discovery、reversible repository edit、review / fix、tests / verification、branch作成、requested / implied PR create/updateについて、このSkillだけを理由に追加permissionを要求しない。

質問やHuman Gateの前に、まず次を終える。

1. cheapな許可済みdiscovery
2. source priorityに沿った仕様復元
3. reversibleな準備
4. concrete alternativesとmaterial differenceの提示

その上でmaterial choiceが残る時だけC0としてHuman Gateへ進む。

## Context discipline

PREPARE後にsource本文を後工程へコピーしない。

- authoritative sourceはURL / path / Issue comment等の参照だけ残す
- AC / IV / TCはIDで引き継ぐ
- unchangedなGoal / scope / Risk / Controlsを各stageで再要約しない
- source再読はcontract conflict / requirements gap / unbounded impact時だけ

探索は狭く始める。

1. symbol / filename search
2. direct definition
3. direct caller
4. direct test
5. materialな未解決がある時だけ拡張

「漏れが怖いから最初から全repoを読む」はdefaultにしない。

## Mid-turn steering

作業中に追加ユーザー指示が来たら、current explicit user instructionとして取り込む。

- affected Goal / scope / AC / IV / TC / Risk / Controlsだけ更新
- unaffected contractとsame-content Evidenceは保持
- PREPAREを最初から無条件にやり直さない
- material choiceが新たに発生した時だけHuman Gateを検討

## Workspace Preflight

repository fileを変更するlocal taskでは `skills/workspace-preflight/SKILL.md` を使う。

GitHub connector等のAPI writeでは、専用task branch・base=`main`・task identity確認を同等Evidenceとする。

## Spec Confidence

- `C2 confirmed`: 目的・期待結果・主要ACが明確でmaterial conflictなし
- `C1 reconstructed`: docs / tests / current patternからmaterial choiceなしに復元可能
- `C0 unclear`: authorized discovery後も複数の妥当な成果物がありmaterial choiceが残る
- `C0 conflicted`: source reconciliation後もdesired stateについてauthoritative sourceが矛盾

Source priority:

1. current user instruction
2. latest explicitly approved spec / ADR
3. current Issue / comments
4. canonical docs
5. tests
6. current implementation / pattern

現在仕様が「BからAへ変更」と明示する場合、実装Bとの差はexpected deltaでありconflictではない。

## Material assumptions

実装結果を変えうる推測だけ記録する。

- cheapに確認できる → 実装前に確認
- sourceから一意に復元できる → C1 evidence
- authorized discovery後も複数のmaterial choiceが残る → C0

特にRe:Meでは次の意味を推測で決めない。

- sealed / unsealed visibility
- sent letter immutability
- delivery / notification state
- ownership / authorization
- exact scheduling privacy
- reply → future thread semantics

## Requirement completeness scan

runtime behavior変更では次を一度だけ `relevant` / `not_applicable` へ分類する。

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

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 requirements 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 requirements?

CallGet help
Cite this page

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