跳到正文
cccskills
免费在 GitHub 公开

sr:spec

Phase 2 of the SRS workflow. Reads projects/{slug}/brainstorm.md and writes a comprehensive spec.md. No word limit.

中文简介正在准备中。当前显示原文说明。

查看安装方法

包含的文件(1)

  • SKILL.md3.5 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

sr:spec

Goal: turn the brainstorm output into a structured, comprehensive spec. No word limit — every section must be fully written.


Step 0 — Identify Project

Ask user for the project slug (or detect from context):

AskUserQuestion: "Which project to write spec for? (slug name or path to brainstorm.md)"

Read projects/{slug}/brainstorm.md. If it doesn't exist, tell the user to run /sr:brainstorm first.


Step 1 — Write spec.md

Write projects/{slug}/spec.md. No word limit. Every sub-section fully written.

§1 — Project Overview

  • System name (confirmed in brainstorm)
  • Problem statement (what problem does this solve?)
  • Solution summary (what does the system do, for whom, how)
  • Primary success metrics (how will we know it's working?)

§2 — Actors

One full entry per confirmed actor:

  • Name and role
  • Technical proficiency (non-technical | basic | intermediate | expert)
  • Domain knowledge level
  • Frequency and channel of use (web | mobile | API | all)
  • Accessibility needs (if any)
  • Data access scope (read | write | admin)

§3 — Features (IN Scope)

For each confirmed feature:

  • Feature name + cluster
  • Description in user's own words (verbatim from brainstorm)
  • AI-expanded detail (what sub-capabilities does this imply?)
  • Actors who use it
  • Priority tier: Essential | Conditional | Optional

§4 — OUT of Scope

Table: Feature | Reason excluded | Planned for version Every item from brainstorm OUT scope list.

§5 — Technical Constraints

  • Tech stack: languages, frameworks, runtime
  • Hosting / deployment model
  • Existing systems to integrate (name, protocol, direction)
  • Security standards (auth model, encryption requirements)
  • Compliance: applicable regulations + specific obligations

§6 — Business Rules

Numbered list. Each rule: precise, testable statement. Example: "BR-01: A user cannot place an order if their account balance is below the order total." Cover every rule surfaced in brainstorm Round 5.

§7 — NFR Baselines

Table format:

IDCharacteristicTargetStatus
NFR-01Response Time< 500ms at p95Confirmed
NFR-02Availability99.9% uptimeConfirmed
NFR-03Data Retention7 years[TBD: legal to confirm | owner: PM | resolve-by: Sprint 1]

§8 — Assumptions

Numbered list. Each assumption: what is assumed + what happens if the assumption is wrong.

§9 — Open Items

Every [TBD] from the brainstorm open-items section, with:

  • What is unknown
  • Who needs to answer it
  • Impact if unresolved

Step 2 — Confirm Before Finishing

After writing, do a self-check:

  • Every confirmed actor appears in at least one feature entry?
  • Every confirmed feature has a priority tier?
  • Every [TBD] from brainstorm.md appears in §9?
  • Every business rule is numbered and testable?

Fix any gaps before outputting the handoff message.


Step 3 — Handoff

Output:

Spec written: projects/{slug}/spec.md

Actors:         {count}
Features (IN):  {count}
OUT scope:      {count}
Business rules: {count}
NFR baselines:  {count confirmed} confirmed, {count TBD} [TBD]
Open items:     {count}

Next: /sr:plan → breaks this spec into per-section SRS plan files

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Build robust backend systems — APIs (REST, GraphQL, gRPC), authentication (OAuth 2.1, JWT), databases, performance optimization, security (OWASP Top 10), scalability patterns (microservices, caching, sharding), and testing. Use when designing APIs, implementing auth, optimizing queries, handling security vulnerabilities, building microservices, or developing production-ready backend systems.

中文简介正在准备中。当前显示原文说明。

DangQuangSE/team-development-skills192026年10月19日 更新

caveman

免费

Terse output mode — strips filler/articles/hedging, ~75% token reduction. Activate whenever: context is filling up, user says be brief/terse/caveman/less tokens, or CAVEMAN_TRIGGERED appears in context. Persists every response until CAVEMAN_RELEASED or user says stop/normal mode.

中文简介正在准备中。当前显示原文说明。

DangQuangSE/team-development-skills192026年10月19日 更新

Explore and debate solutions before writing code. Use when the user poses a design question, asks "how should I approach X", wants to think through options before committing, or says anything like "let's brainstorm", "what's the best way to...", "I'm not sure how to tackle this", or "should I use X or Y". Always runs before /ck:plan for novel or ambiguous features. No code is written — only: explore → clarify → spec → report.

中文简介正在准备中。当前显示原文说明。

DangQuangSE/team-development-skills192026年10月19日 更新

ck-cook

免费

Implement a feature phase by phase from a phased JSON master or Markdown plan. Before each phase, confirm whether to create/run unit tests and whether to run ck:quality, unless explicit flags supply those choices. Supports token-budgeted execution, resumable state, and TDD handoff to ck:test.

中文简介正在准备中。当前显示原文说明。

DangQuangSE/team-development-skills192026年10月19日 更新

ck-fix

免费

Fix a bug using Scout → Diagnose → Fix → Review → Finalize. Use when the user pastes an error message, stack trace, or test failure, or says "fix this bug", "something's broken", "tests are failing", "I'm getting an error". Also accepts `--from-quality <report>` or `--from-test <report>` to fix exactly the findings/failures a report lists. Modes (pick one): --fast (trivial errors — lint, type, build — skip scout and review), --hard (mandatory review, no auto-approve).

中文简介正在准备中。当前显示原文说明。

DangQuangSE/team-development-skills192026年10月19日 更新

ck-plan

免费

Plan a feature or system before implementation. Use when the user says "plan this", "I want to build X", "how do I implement Y", or when /ck:brainstorm produces a spec.md. Always run before /ck:cook. Modes (pick one): --fast (simple, single-file), --hard (research + red-team + validate). Composable flag (combine with any mode): --tdd — propagates into the cook pipeline. Every phase gets Design Constraints and Quality/Testing State; ck:cook confirms optional test and quality checks per phase.

中文简介正在准备中。当前显示原文说明。

DangQuangSE/team-development-skills192026年10月19日 更新

查看 DangQuangSE 的全部技能

报告此技能的问题