pipeshub-ai/sharp

Letzte erfasste Quellaktivität: 16. Oktober 2026 um 06:32

SkillsMP-Katalog aktualisiert: 5. November 2026 um 19:57

gesammelte Skills: 15

GitHub-Stars: 4
GitHub-Forks: 0

Mit einem KI-Assistenten installieren

Diesen Prompt kopieren und in den verwendeten KI-Assistenten einfügen.

Follow https://skillsmp.com/skill-install/prompt.md to install Agent Skills from https://github.com/pipeshub-ai/sharp.

README des Repositorys

README-Quelldatei: README.md

README-Quelldatei lesen

Vollständige README anzeigen

# sharp **Stay sharp while AI does the work.** sharp is a plugin for Claude Code (with Codex packaging) that keeps people learning and judging instead of just approving AI output. It's built on learning research and tested with A/B experiments. > The biggest risk from AI might be human laziness. We get the answer, move on, and our understanding quietly gets shallower. sharp makes the AI work in a way that keeps *you* thinking, and adds as little to each answer as it can. ## What it does - **Your judgment stays in charge.** Irreversible actions (dropping data, force-pushing shared branches, deploying, publishing, emailing customers, signing) stop for a 6-line **Decision Card**: the context, what can't be undone, the options, a recommendation, and then *your call*. A deterministic gate backs it up, and a decision journal brings the call back 30 days later for a retrospective. - **You understand what changed and why.** A 4-line **Change Brief** replaces the usual wall of summary: *What & why · Who/where/when · Impact (Verified / Not verified) · Next time*. `/sharp:walkthrough` gives a 2-minute guided tour of any change. - **You reason, not just receive.** In coach and learn mode, or on topics you choose to grow in, one question at the right moment, then the loop closes with *your* rule for next time. - **Lessons come back when they're needed.** Lessons are rules with their context ("when X, in context C, do Y, because Z, unless U"). When a similar situation appears, sharp asks: *"You've seen this before: what did you learn, and is anything different here?"* - **It stays out of the way.** At most one question per reply, no coaching during incidents, one line for mechanical edits, and `#skip` and `#ship 3h` always work. ## Does it work? (A/B, Haiku 5.5, judged blind by Opus 5.5) | Scenario | Without sharp | With sharp | |---|---|---| | "Drop this table" / "delete the test accounts" | went ahead without asking, **every time** | stopped, explained, offered a backup, asked: **100%** | | Junior persona journeys: prompted to reason | 8% | **75%** | | …left with a reusable rule | 17% | **75%** | | …words per conversation | 543 | **432** | | A similar bug to one you've fixed before | 0% invited recall | **100%** (near transfer) | | Student asks for the homework answer | answer handed over | hint-first coaching | | Production incident | — | zero extra friction | Also measured honestly: proportionality is 0.67 with sharp vs 0.83 without; **far transfer** across domains is 0% in every arm; and one research idea I expected to win (a semantic lesson index) lost. Everything is in [docs/EXPERIMENTS.md](docs/EXPERIMENTS.md). ## Install ```bash /plugin marketplace add pipeshub-ai/sharp /plugin install sharp@pipeshub-plugins ``` That's it. **sharp works out of the box with sensible defaults** (mode `light`, detail `brief`, role `general`). After installing, Claude Code may say *"5 userConfig options not yet set"*; that's optional, and you can skip it. To customize it later (optional), run `/plugin configure sharp@pipeshub-plugins`, open `/config`, or use `/sharp:mode` and `/sharp:grow`. See [sharp/README.md](sharp/README.md) for every setting, command and gate rule. ## Read more - [docs/FRAMEWORK.md](docs/FRAMEWORK.md): the framework, and how sharp behaves in each situation and role - [docs/RESEARCH.md](docs/RESEARCH.md): the learning science behind each feature, with evidence ratings - [docs/EXPERIMENTS.md](docs/EXPERIMENTS.md): every A/B round, including what failed - [docs/LIMITATIONS.md](docs/LIMITATIONS.md): **known limitations and open problems. Help wanted!** - [ROADMAP.md](ROADMAP.md): what's next, including a human pilot ## Prior art [learning-opportunities](https://github.com/DrCatHicks/learning-opportunities) pioneered optional learning exercises for Claude Code and Codex, and Anthropic's learning and explanatory output styles inspired the coaching modes. sharp adds the enforced one-way door gate and decision journal, transfer-first lessons with just-in-time recall, the Change Brief, and an experiment suite. ## Privacy Everything stays on your machine (`~/.sharp/`). No telemetry. Prompt text is never stored. ## Contributing sharp has ten open problems, from far transfer to a human pilot, each with a *done when* criterion. Start with [docs/LIMITATIONS.md](docs/LIMITATIONS.md). The quickest wins are labelled gate cases and realistic scenarios or personas from your field. See [CONTRIBUTING.md](CONTRIBUTING.md). ## License [MIT](LICENSE) © 2026 PipesHub

README des Repositorys wird geladen…

Skills in diesem Repository

Klassifizierung ausstehend