calibrating
Use after a knowledge-work deliverable ships or gets human edits. Triggers on "that draft worked", "they rewrote half of it", "remember this for next time", or…
Use when a mindpowers spec exists and the user wants the actual deliverable written, such as "draft it", "write the memo from the spec", or right after mindstorming locks a spec. Not for code; not for drafting without a spec (offer mindstorming first).
$ npx -y skills add rohitgehe05/mindpowers --skill drafting --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/draftingContext preview
The summary Claude sees to decide when to auto-load this skill.
Use when a mindpowers spec exists and the user wants the actual deliverable written, such as "draft it", "write the memo from the spec", or right after mindstorming locks a spec. Not for code; not for drafting without a spec (offer mindstorming first).
name: drafting description: Use when a mindpowers spec exists and the user wants the actual deliverable written, such as "draft it", "write the memo from the spec", or right after mindstorming locks a spec. Not for code; not for drafting without a spec (offer mindstorming first).
The second step in the mindpowers loop: shape (mindstorming) -> draft (drafting) -> review (reviewing-docs) -> remember (calibrating). Mindstorming turns a rough idea into a locked spec. Drafting turns that locked spec into the finished document, holding it to the standards baked into the matched template.
Drafting does not re-litigate the spec. The thinking already happened. This skill's job is faithful, high-quality execution: realize every section, honor every exclusion, apply the template's hard requirements, and flag any deviation instead of silently making one.
Think precisely; respond plainly. Use common words and short sentences. Explain an unavoidable technical term the first time it appears, and give one short example when a rule could be misunderstood. For a material conclusion about the draft, a blocker, or a deviation, give a compact explanation: the recommendation or conclusion, what you checked, the main reasons, uncertainty, and the next step. Do not dump internal machinery. If the user says the explanation is unclear, explain it again from scratch.
This skill needs a spec with `status: locked` from `docs/mindpowers/specs/`.
1. **Find the spec.** Use the one the user names, or the most recent spec in `docs/mindpowers/specs/` if the request is ambiguous (e.g. "draft it" right after a mindstorming session). Also check legacy `docs/brainstorm/` if it exists and nothing newer is in `docs/mindpowers/specs/`. 2. **Status is `draft`.** Do not draft from it. Tell the user the spec isn't locked yet, and ask whether to lock it now or go back to mindstorming to finish shaping it. 3. **Status is `superseded`.** Warn the user this spec was superseded (and by what, if the frontmatter or a newer spec says so). Confirm they still want to draft from it before proceeding. 4. **No spec exists for the ask.** Do not draft cold. Give one short pitch for shaping the audience, goal, and constraints first, something like "I don't see a spec for this. Want to shape the audience, goal, and constraints first so the draft has something clear to follow?" If the user confirms, switch to `mindstorming`; do not switch before confirmation. Respect whatever the user decides. If they insist on skipping it, draft anyway, but say plainly that the quality bars (audience fit, standards, anti-pattern checks) will be weaker without a spec to hold the draft to.
A locked spec approves the working brief for drafting. It does not establish content readiness or grant external approval. A locked spec may therefore have `readiness: not-ready`. When the user asks to proceed from one, draft it while keeping the deliverable provisional: preserve the spec's readiness value, evidence qualifications, material blocking gaps, and external-review status. Keep `readiness` limited to `ready | not-ready`; never encode approval in it. Do not polish any of these states into unsupported certainty, readiness, or approval.
1. **Read the spec and its template.** Load the spec file, then load `skills/mindstorming/references/<type>.md` using the spec's `type` frontmatter field. If `type` is `self-shape`, there's no template file to load; draft against the spec's own sections instead. 2. **Draft against the template's standards.**
3. **Run the draft self-review checklist** (mirrors mindstorming's spec checklist, applied to the draft instead of the spec):
Fix what you can inline before showing the draft. Anything you can't fix without more input, flag rather than silently paper over. 4. **Report the checklist results inline.** When you hand the draft to the user, list what the self-review checked and what it found, including any deviations from the spec and why. Don't bury this in a preamble; make it visible. 5. **Save the draft.** Following the file contract:
Your AI should ask better questions before it writes. Most AI writing tools turn ambiguity into polished prose.
Repo: rohitgehe05/mindpowers
Use after a knowledge-work deliverable ships or gets human edits. Triggers on "that draft worked", "they rewrote half of it", "remember this for next time", or…
Use before a finished document ships, when the user asks "fact-check this", "is this ready to send", "check the numbers", or after drafting/review hand off a…
Use before drafting any non-code knowledge-work deliverable, including strategic memos, business reviews, OKR defences, PRDs, decision docs, briefing docs,…
Use when the user has a finished or near-finished document (memo, business review, PRD, decision doc, briefing, comms, framework, talking points, post-mortem)…
Use when a user wants to test, sharpen, frame, or gather evidence for a customer or business problem before pitching a direction, prioritising work, or writing…