← ClaudeAtlas

business-case-study-internallisted

Write the tier-2 internal case study — situation, what was built, tagged outcomes with denominators, lessons, replication guide for other teams
tony/ai-workflow-plugins · ★ 2 · AI & Automation · score 59
Install: claude install-skill tony/ai-workflow-plugins
# 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. Tier 2: internal team and repo names allowed; individuals anonymized to roles. Value is engineer-hours, cycle time, and capacity; never money. Read `references/interim-format.md` first — it defines run location and the completeness gate. Defer these rendering references until the gate passes; a refused render never loads them: - `references/provenance.md` — tag rendering, anti-inflation rules, the no-currency contract. - `references/audiences.md` — the tier-2 contract. User arguments: $ARGUMENTS ## Context Recent runs — run this command and read the output: ```bash sh -c 'ls -dt "$HOME"/Documents/*/business/ /mnt/c/Users/*/Documents/*/business/ 2>/dev/null' | head -5 | grep . || echo "(no runs found)" ``` ## Procedure ### 1. Locate the run Use the `$ARGUMENTS` path if given, else the newest run per `interim-format.md`. Confirm the choice with the user. ### 2. Completeness gate Run the completeness gate from `interim-format.md`. Refuse to render from an incomplete package; list what is missing and stop. ### 3. Render the case study Read the deferred references above, then write `<run>/reports/case-study-internal.md` as a narrative in this fixed order: 1. **Situation** — the team, the recurring task, why it cost enough to act on. 2. **What was built** — the skill or workflow, its build t