本文へ移動
cccskills
無料GitHub で公開

sr-improve

Phase 8 of the SRS workflow. Generates an improvement report covering deferred features, technical risks, validation warnings, and next-version candidates. No word limit.

インストール方法を見る

含まれるファイル(2)

  • SKILL.md3.1 KB
  • agents/openai.yaml212 B

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。

sr-improve

Goal: produce a candid improvement report — what was deferred, what carries risk, what should be resolved before development starts. Reference specific FR/NFR IDs.


Step 0 — Identify Project

Ask the user: "Which project? (slug)"

Read from projects/{slug}/:

  • spec.md (for deferred features and open items)
  • srs/appendix-b-open-issues.md (for all [TBD] items)
  • srs/03-03-performance.md (for [TBD] NFRs)
  • Validator output if available (WARNs from $sr-validate)

Step 1 — Write improvement-report.md

Write projects/{slug}/improvement-report.md. No word limit.

§1 — Deferred Features (Next Version Candidates)

List every feature marked OUT of scope in spec.md that the user mentioned but deferred. For each:

  • Feature name
  • Why deferred (user's reason from brainstorm, if stated)
  • Estimated effort level (low | medium | high) — AI estimate only, not a commitment
  • Suggested version: v1.1 | v2.0 | unknown

§2 — Technical Risks

For each unresolved [TBD] in NFRs:

  • NFR-ID + description
  • What data is needed to set the target
  • Risk if unresolved: (A) test cannot be written (B) SLA cannot be committed (C) architecture decision blocked
  • Suggested owner + resolve-by milestone

For each external integration in §3.1:

  • Integration name + system
  • Risk: dependency on third-party uptime / API versioning / rate limits
  • Mitigation suggestion

§3 — FR Refinement Suggestions

Identify FRs that are:

  • Too broad (combines multiple behaviors that should be separate FRs)
  • Missing negative cases (what happens when it FAILS?)
  • Missing actor variants (same action, different permission level)

List each with the suggested split or addition.

§4 — NFR Gaps

NFRs with [TBD] Response Measure → list with: what benchmark test would produce the real number. NFRs with adjective-only measure (should have been caught by validator) → rewrite suggestion.

§5 — Validation Warnings

Enumerate every WARN from $sr-validate with:

  • Warning text
  • Which file/FR/NFR it refers to
  • Recommended resolution (specific action, not "review this")
  • Urgency: must resolve before dev | should resolve before QA | can defer

§6 — Process Recommendations

Observations about the requirements process itself:

  • Rounds where user input was vague → note the topic area for follow-up workshop
  • Assumptions that carry high invalidation risk → flag for stakeholder sign-off
  • Missing subject-matter expert input (e.g., "no security architect reviewed NFR-02")

Step 2 — Handoff

Output:

Improvement report: projects/{slug}/improvement-report.md

Deferred features:      {count}
Technical risks:        {count}
FR refinement items:    {count}
NFR gaps:               {count}
Validation warnings:    {count}
Process recommendations:{count}

Next: $sr-save → saves project context files for future sessions

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

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.

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。

DangQuangSE/team-development-skills192026年10月9日 更新

caveman

無料

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.

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。

DangQuangSE/team-development-skills192026年10月9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.

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。

DangQuangSE/team-development-skills192026年10月9日 更新

ck-cook

無料

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.

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。

DangQuangSE/team-development-skills192026年10月9日 更新

ck-fix

無料

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).

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。

DangQuangSE/team-development-skills192026年10月9日 更新

ck-plan

無料

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.

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。

DangQuangSE/team-development-skills192026年10月9日 更新

DangQuangSE のスキルをすべて見る

このスキルの問題を報告する