本文へ移動
cccskills
無料GitHub で公開

project-specification

Transforms project briefs into testable specifications with user stories and acceptance criteria. Use after brainstorming, before planning.

インストール方法を見る

含まれるファイル(1)

  • SKILL.md4.6 KB

SKILL.md(原文)

インストールする前に、エージェントに与えられる指示の中身を確認できます。

Delegation

For detailed specification writing workflows, this skill delegates to spec-kit:spec-writing as the canonical implementation. Use this skill for quick specification needs; use spec-kit for thorough specification documents.

When To Use

  • After brainstorming phase completes
  • Have project brief but need detailed requirements
  • Need testable acceptance criteria for implementation
  • Planning validation and testing strategy
  • Translating business requirements into technical specs
  • Defining scope boundaries and out-of-scope items

When NOT To Use

  • Still exploring problem space (use Skill(attune:project-brainstorming) instead)
  • Already have detailed specification (use Skill(attune:project-planning) instead)
  • Refining existing implementation (use code review skills)
  • Making strategic decisions (use Skill(attune:war-room) for complex choices)

Integration

With spec-kit:

  • Delegates to Skill(spec-kit:spec-writing) for methodology
  • Uses spec-kit templates and validation
  • Enables clarification workflow

Without spec-kit:

  • Standalone specification framework
  • Requirement templates
  • Acceptance criteria patterns

Documentation Audience

Carry the brief's Doc audience field into the specification, and treat it as a requirement rather than a note: it decides what the project's README, guides, and tutorials may contain. When the brief did not set one, ask, do not guess.

Specify the deep-dive destination alongside it, so extraction has somewhere to go before the first document is written: modules/ for skills, docs/deep-dive/<topic>.md for repo docs. Tier table and cut test: scribe:slop-detector module audience-targeting.md.

Record the Tradeoff (decision journal)

If the specification settled a design decision with real alternatives (a chosen data model, an interface boundary, a constraint accepted), record it to docs/tradeoffs.md before continuing (draft and confirm):

  • If leyline is installed, invoke Skill(leyline:decision-journal) and append a tradeoff entry (the decision, the options weighed, and what was sacrificed; set phase to specify). Show the draft; append on confirmation.
  • Fallback (leyline absent): append to docs/tradeoffs.md using the in-file ENTRY TEMPLATE; assign the next TR-NNN id.

Post-Completion: Workflow Continuation (REQUIRED)

Automatic Trigger: After Quality Checks pass and docs/specification.md is saved, MUST auto-invoke the next phase.

When continuation is invoked:

  1. Verify docs/specification.md exists and is non-empty
  2. Display checkpoint message to user:
    Specification complete. Saved to docs/specification.md.
    Proceeding to planning phase...
    
  3. Invoke next phase:
    Skill(attune:project-planning)
    

Bypass Conditions (ONLY skip continuation if ANY true):

  • --standalone flag was provided by the user
  • docs/specification.md does not exist or is empty (phase failed)
  • User explicitly requests to stop after specification

Do NOT prompt the user for confirmation: this is a lightweight checkpoint, not an interactive gate. The user can always interrupt if needed.

Exit Criteria

  • docs/specification.md exists, is non-empty, and passes Quality Checks.
  • Every functional requirement has testable acceptance criteria.
  • The documentation audience tier is stated, carried from the brief or asked for when the brief omitted it.
  • Any design decision with real alternatives is recorded to docs/tradeoffs.md (or there was no meaningful design fork).
  • The next phase is auto-invoked unless a bypass condition holds.

Related Skills

  • Skill(spec-kit:spec-writing) - Spec-kit methodology (if available)
  • Skill(attune:project-brainstorming) - Previous phase
  • Skill(attune:project-planning) - AUTO-INVOKED next phase after specification
  • Skill(attune:mission-orchestrator) - Full lifecycle orchestration

Related Commands

  • /attune:specify - Invoke this skill
  • /attune:specify --clarify - Run clarification workflow
  • /attune:blueprint - Next step in workflow

Examples

See /attune:specify command documentation for complete examples.

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

同じリポジトリのスキル

概要と使いどころ

Shapes turns action-first: action leads, steps numbered, state restated. Use for ADHD-friendly output. Do not use to trim tokens; use response-compression.

日本語の概要は準備中です。原文の説明を表示しています。

athola/claude-night-market3412026年10月10日 更新

Inverts burden of proof for code additions. Use when reviewing PRs, planning refactors, or running unbloat to challenge every addition's necessity.

日本語の概要は準備中です。原文の説明を表示しています。

athola/claude-night-market3412026年10月10日 更新

Tracks per-agent token usage and flags waste in parallel dispatch. Use when evaluating parallel agent efficiency or after a multi-agent run.

日本語の概要は準備中です。原文の説明を表示しています。

athola/claude-night-market3412026年10月10日 更新

Coordinates Claude agent teams via filesystem protocol. Use when orchestrating parallel agents with task dependencies. Do not use for single-agent tasks.

日本語の概要は準備中です。原文の説明を表示しています。

athola/claude-night-market3412026年10月10日 更新

Evaluates API surface design, consistency, and exemplar alignment. Use when reviewing public API changes or before releasing a new API surface.

日本語の概要は準備中です。原文の説明を表示しています。

athola/claude-night-market3412026年10月10日 更新

Selects architecture paradigm via research before scaffolding. Use when architecture is undecided and the choice needs justification and documentation.

日本語の概要は準備中です。原文の説明を表示しています。

athola/claude-night-market3412026年10月10日 更新

athola のスキルをすべて見る

このスキルの問題を報告する