{"id":"decide","name":"decide","summary":"決定を下す際には、負担を支える質問を選び、順に説明し、通話(または「待つ」)を行い、将来の参照のためにその理由をアーカイブする構造化されたワークフローが欲しい場合。","body":"# /decide — Structured decision workflow + archive\n\nPicks load-bearing questions from the 37signals guide, walks through them, reaches a call, archives the rationale with a revisit date.\n\n## Step 1 — Capture the decision\n\nGet from the user:\n- **The decision** in one sentence (what are we deciding between?)\n- **Stakes**: low / medium / high (how much does this matter?)\n- **Reversibility**: easy / hard / one-way door\n- **Deadline**: when does this need to be decided? Or \"open\"?\n- **Context** (optional, 1–3 sentences)\n\nIf any are missing, ask. Don't proceed with vague framing.\n\n## Step 2 — Triage the question set\n\nRead `references/questions.md` for the full set (the 37signals 38 + house additions, e.g. Q39 opportunity cost) and category mapping. Pick 6–8 based on the decision's characteristics:\n\n**Default 5 (always ask):**\n- Q1 — Does this decision actually need to be made?\n- Q2 — Is the right person making this decision?\n- Q8 — How easily can we reverse it?\n- Q9 — First instinct? (capture before \"thinking\" muddies it)\n- Q3 — A year from now, how will we feel about this?\n\n**Add based on type:**\n\n| If… | Add |\n|---|---|\n| Reversibility = hard / one-way door | Q14 (is there a wrong decision?), Q17 (knock-on effects), Q34 (principles bent) |\n| Time pressure | Q5 (why hesitating?), Q15 (different tomorrow?), Q22 (when do we have to decide?) |\n| Multiple people involved | Q21 (someone else's practice rep?), Q27 (would another opinion help?), Q35 (multiple people deciding what one should?) |\n| Lots of data / analysis | Q19 (what missing info would change it?), Q26 (data vs gut?), Q9 deepened |\n| Recurring decision | Q11 (last time?), Q23 (one-and-done or repeating?) |\n| Customer-facing | Q24 (anyone outside depending?), Q25 (customer vs us impact?) |\n| Money decision | Q38 (in the end, is this about money?), Q36 (return on effort?), Q39 (what does yes displace?) |\n| Big time / focus commitment | Q39 (opportunity cost), Q36 (return on effort?), Q20 (creates or eliminates work?) |\n| Stuck / not deciding | Q4 (why hasn't it been made already?), Q10 (what if we don't decide?), Q31 (do you even care?) |\n\nCap at ~8 questions. More than that turns into analysis paralysis (which is itself one of the things this skill exists to prevent).\n\nTell the user which questions you picked and why, then proceed.\n\n## Step 3 — Walk through\n\nAsk the questions one at a time, or in a tight cluster if the user wants to write fast. Capture their answers verbatim — don't paraphrase into corporate-speak.\n\nFor Q9 (first instinct), get the answer BEFORE diving into analysis. The point is to surface the gut call so we can later check if \"analysis\" was just rationalization.\n\n## Step 4 — Reach a call\n\nSynthesize the answers into a decision. Options:\n\n- **Decide now** — answers point to a clear call\n- **Decide smaller** — break into 2–3 smaller decisions (Q7)\n- **Wait** — flag what info / time would change the answer (Q19, Q15)\n- **Don't decide** — the decision doesn't need to be made (Q1, Q10)\n- **Wrong person** — kick to the right decider (Q2, Q35)\n\nState the call clearly. No hedging.\n\n## Step 5 — Set the revisit\n\nPick a revisit date based on when consequences would show up:\n- Decisions about tools/processes: 30 days\n- Decisions about strategy/positioning: 90 days\n- Decisions about hires/partnerships: 90–180 days\n- Decisions about products/launches: 30–60 days post-launch\n\nWrite what to look for on the revisit (\"did MRR move? did the partner ship? do clients still ask for X?\").\n\n## Step 6 — Archive\n\nArchives live in `${MAKERSKILLS_CONFIG:-$HOME/.config/makerskills}/decide/archive/` (create the directory if missing). Never write archives inside the skill's own folder — skill installs and upgrades re-sync from source and wipe anything saved there.\n\n**Migration:** if this skill's folder contains an old `references/decisions-archive/` with user entries, move those files into the archive directory before writing anything new.\n\nWrite to `<archive dir>/<YYYY-MM-DD>-<slug>.md`:\n\n```markdown\n# Decision: <one-line>\n\n**Date:** YYYY-MM-DD\n**Decide by:** <date or \"open\">\n**Reversibility:** easy / hard / one-way door\n**Stakes:** low / medium / high\n\n## Context\n<1–3 sentences>\n\n## Questions\n\n### <Q3 phrasing>\n<answer>\n\n### <Q8 phrasing>\n<answer>\n\n(only questions actually applied — heading is the question text, not \"Q3\")\n\n## Decision\n**<the call, stated clearly>**\n\n## Rationale\n<2–3 sentences synthesizing the answers>\n\n## Expected outcome\n<what should be true if this was right, by <date>>\n\n## Revisit\n**<YYYY-MM-DD>** — <what to look for>\n\n## Source\nQuestions adapted from [The 37signals Guide to Making Decisions](https://37signals.com/how-we-make-decisions)\n```\n\nAppend to `<archive dir>/INDEX.md` (create if missing):\n\n```markdown\n- 2026-06-16 — [<decision>](./<filename>.md) — **<call>** — <one-line rationale> — revisit 2026-09-16\n```\n\n## Step 7 — Surface\n\nShow the archive entry in chat. Tell the user the archive path. Offer:\n\n- *\"Want me to schedule a /loop reminder for the revisit date?\"* (would use the `loop` skill to fire at the right time)\n- *\"Push to Notion as a decision card?\"*\n- *\"Need a follow-up decision after this one?\"*\n\n## Future enhancements\n\n- Auto-create a calendar event or cron reminder for the revisit (via `compound-engineering:schedule`)\n- Composable with `business-brainstorm` — brainstorm scores the idea on 9 dimensions; `decide` formalizes the go/no-go after\n- Grep past decisions for patterns (\"show me decisions I made that were marked 'easy reverse' but didn't reverse\")\n\n## Composes with\n\n- `business-brainstorm` — brainstorm → decide is a natural pipeline for \"should I build X\"\n- `deep-research` — when a decision is waiting on info (Q19), trigger research first\n- Memory — load `feedback_*.md` for principles that might be at play (Q34)\n- `loop` / `compound-engineering:schedule` — for revisit reminders\n\n## Notes on quality\n\n- **Don't ask all 38.** The point of triage is to skip questions that don't apply. Eight relevant questions > thirty-eight padded ones.\n- **Don't soften the call.** \"Probably yes, lean toward, maybe should\" wastes the skill. Pick.\n- **The first instinct (Q9) is sacred.** Always capture it before analysis. If the final call differs from the first instinct, the rationale needs to explain why — that's the whole point of the question.\n- **Archive every decision, even small ones.** The compounding value comes from being able to grep \"what did I decide about pricing last year\" — and that requires writing them down even when they feel obvious in the moment.","author":"@coreyhaines31","ownerProfile":null,"authorContacts":null,"sourceUrl":"https://github.com/coreyhaines31/makerskills/tree/main/skills/decide","license":"MIT","category":"productivity","lang":"en","tokens":1685,"stars":0,"calls30d":2,"claimed":false,"visibility":"public","origin":"crawler","version":"0.1.0","createdAt":"2026-08-22","updatedAt":"2026-08-22","files":[{"path":"references/questions.md","size":5190,"sha256":"95a5e51cecdbc16a2f19cacdcd22f04f38778d5171a5099f29b3e324b9015741"}],"requires":{"mcp":[],"tools":[]},"safety":{"flags":[],"scannedAt":"2026-08-22","hasScripts":false,"networkEndpoints":["37signals.com"]}}