business-case-study-internal
Use when writing a tier-2 internal case study from a business-value run: tagged outcomes, lessons, and a replication guide for other teams.
- License 许可
- MIT
- 所属仓库
- tony/skills
- 最近更新
- 2026-11-08
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- business-case-study-internal
- metadata
- { "source": "plugins/business/skills/case-study-internal/SKILL.md", "argument-hint": "[run directory]" }
- description
- Use when writing a tier-2 internal case study from a business-value run: tagged outcomes, lessons, and a replication guide for other teams.
- allowed-tools
- [ "Bash", "Read", "Write", "Grep", "AskUserQuestion" ]
- disable-model-invocation
- true
02 资源文件 6
- 参考文档agents/openai.yaml306 B
- 参考文档references/audiences.md5.9 KB
- 脚本references/business.py79.1 KB
- 参考文档references/interim-format.md14.2 KB
- 参考文档references/prose-rules.md4.5 KB
- 参考文档references/provenance.md4.3 KB
03 SKILL.md 正文
Internal Case Study (tier 2)
Turn a run package into a narrative case study for internal
circulation: what happened, what it measured, what other teams can
take from it. The tier-2 contract is in audiences.md.
Read references/interim-format.md first. It defines the run
location, the completeness gate, and the output frame. Defer these
until the gate passes:
references/provenance.mdreferences/audiences.md: the tier-2 contract.
User arguments: $ARGUMENTS
Procedure
1. Locate the run and pass the gate
Per interim-format.md § Rendering a report. When the request names a
workflow, take the first line of runs --workflow <slug> as the run.
2. Ask for what the run package lacks
The run package holds no maintainer, no lessons, and no replication
notes, and may hold no build time. With a question tool, ask the user
once, in one batch (ask-user-choice), for: the maintainer's role, the
build time if build-hours is not registered, what worked and what did
not, and what the team would change. Record the answers in
findings.md under a ## User-supplied context heading, with a
build time also appended to assumptions.yaml as an ESTIMATED entry
(provenance.md); then run business.py gate <run> again. Name a
person only as a role. Without a question tool, or without an answer, write
each such part as unknown with the data that would resolve it.
3. Render the case study
Write <run>/reports/case-study-internal.md as a narrative in this
fixed order:
- Situation: the team, the recurring task, why it cost enough to act on.
- What was built: the skill or workflow, its build time (tagged), and who maintains it.
- Measured outcomes: every figure tagged, denominator stated, window pinned. Include the costs: verification time, failed runs, maintenance.
- Lessons: what worked, what did not, what the team would do differently.
- How other teams can replicate: prerequisites, the expected ramp (and the excluded novelty window), and where results are likely to differ.
Take every item from the run package or the user's answers; a part neither holds is written as unknown with the data that would resolve it, never supplied from inference.
Write it per references/prose-rules.md.
Then scan for individuals with references/business.py scan --run <run> --tier 2 <run>/reports/case-study-internal.md (absolute path); it reads the README
People: line and reports each name; rewrite it as a role, since tier 2
allows roles only. Then run steps 4 and 5 of interim-format.md § Rendering
a report: the money check, then stamp.
Output
Hero success form: ✓ Case study: <one-line outcome with tag>.
Sections and stopped-run shape as in interim-format.md. Panel options: write the public
case study next (read the business-case-study-public skill and follow it),
adjust the narrative, or stop.
Portability notes
ask-user-choice— present the listed options and wait for the user to pick one. Hosts with a structured multiple-choice tool (Claude Code'sAskUserQuestion) should use it; otherwise print a numbered list and wait for a numbered reply. Never proceed on an assumed answer.$ARGUMENTS— the text the user passed when invoking this skill. If your host does not substitute it, read it as the user's request in the current turn, and ask when there is none.- Bundled files — every relative path in this skill points at a file shipped inside this skill directory. Read them from here, not from the host's plugin tree.
04 同仓库更多 Skills
serene-bliss
Use when asked to make a CLI --help, docs page, error message, or tooling UX more serene or calmer for developer experience; returns text, no edits.
review
Weave code review: run independent adversarial reviews in parallel, then synthesize findings
refine
Use when asked to refine a draft, iterate on code until cleaner, or polish a README through repeated critique and improvement.
prompt
Weave prompt: compare independent adversarial implementations, then adopt the single best one
plan
Weave planning: compare independent adversarial plans, then synthesize the best one
fix-review
Fix weave review findings: validate, add test coverage, fix, and commit each as atomic changes