use-case-collection
Steal Dataiku's owned-catalog + 3-question skip, not the gated PDF. Use when the user pastes content.dataiku.com/dataiku-ai-agent-use-case-collection, mentions predictive maintenance, clinical trial agents, expertise / knowledge / security families, or Agent Connect. Fail closed. No Dataiku.
- License 许可
- MIT
- 最近更新
- 2026-11-09
- Stars
- ★ 1
- Forks
- 0
01 前言 Front Matter
- name
- use-case-collection
- description
- Steal Dataiku's owned-catalog + 3-question skip, not the gated PDF. Use when the user pastes content.dataiku.com/dataiku-ai-agent-use-case-collection, mentions predictive maintenance, clinical trial agents, expertise / knowledge / security families, or Agent Connect. Fail closed. No Dataiku.
02 资源文件 2
- 其他.env.example275 B
- 参考文档references/detailed-guide.md18.6 KB
03 SKILL.md 正文
Use-case collection (steal the method)
Dataiku ships eight vertical demos behind a password PDF. We keep an owned catalog and skip the agent when the work is simple if-then, one clean source, or a static process.
Do not open the gated PDF. Do not sign up for Dataiku. Do not stand up Agent Connect.
Does it help?
| Surface | Use Dataiku? | Use instead |
|---|---|---|
| Password PDF | No | evaluate_source |
| Maintenance / clinical demo | No | evaluate_family |
| Do we need an agent? | No | evaluate_agent_need |
| More agents | No | Rank IAP / WQTU, not tokens |
Before claiming a collection case
python3 scripts/use_case_collection.py \
--source local_catalog \
--family iap_attempt \
--complexity simple_if_then \
--data single_clean \
--process static \
--cases scripts/tests/fixtures/use_case_collection.json \
--cite case:iap-attempt-path
Allow only when every JSON ok is true (process exit 0).
04 同仓库更多 Skills
writing-plans
Use when you have a spec or requirements for a multi-step task, before touching code
workflow-economics-lite
Escape AI pilot purgatory: require completion-loop workflows with one owner, baseline, economic metric, system-of-record integration, and audit trail. Block orphan chatbots and interest-as-ROI claims.
verification-before-completion
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
value-center-lite
Apply InfoQ Rohrer value-center / VSM five questions (agency + coherence). Use when planning work, shipping releases, or auditing agent autonomy claims. Fail closed on product-only slogans without WQTU/paywall value.
using-superpowers
Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions
using-git-worktrees
Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback