decide · wrg32786 — Claude Code skill: what it does, how to install
This Claude Code skill weighs a decision against selected criteria and returns a structured recommendation. Run /decide to compare options or ask for help choosing a course of action.
MIT ★ 26 updated 2026-11-16
npx skills add wrg32786/aigent-os --skill decide -a claude-codeWhat decide does
decide identifies the choice at hand, then selects 4–6 relevant criteria from a set of twelve. These include reversibility, cost, revenue impact and opportunity cost. It also checks the decision against priorities and the agent’s authority level.
The result includes a recommendation, the criteria behind it, a trade-off, confidence, authority and an immediate next step. Low confidence turns the recommendation into an experiment; Level 3 decisions remain for a human to make. The skill draws on system/04_decision_frameworks.md, system/14_decision_framework.md and system/12_authority_matrix.md.
What it helps with
- compare possible courses of action
- weigh delay against opportunity cost
- check whether the agent has authority to act
- turn a low-confidence choice into an experiment
Example prompts for the agent
- Compare launching this feature now with moving it to the next sprint:
/decide. - Help choose between these two implementation options:
/decide. - Assess whether to pursue this opportunity:
/decide.
How to install decide
1Skills CLI (Vercel)
npx skills add wrg32786/aigent-os --skill decide -a claude-code2Manually: put the files in place
~/.claude/skills/decide/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/decide/
1Skills CLI (Vercel)
npx skills add wrg32786/aigent-os --skill decide -a codex2Manually: put the files in place
.agents/skills/decide/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add wrg32786/aigent-os --skill decide -a cursor2Manually: put the files in place
.cursor/skills/decide/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install wrg32786/aigent-os skills/decide2Manually: put the files in place
.github/skills/decide/SKILL.md1Skills CLI (Vercel)
npx skills add wrg32786/aigent-os --skill decide -a gemini-cli2Platform CLI
gemini skills install https://github.com/wrg32786/aigent-os --path skills/decideManually: put the files in place
.devin/skills/decide/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add wrg32786/aigent-os --skill decide -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about decide
How do I install decide in Claude Code?
Run npx skills add wrg32786/aigent-os --skill decide -a claude-code. The skill file is located at ~/.claude/skills/decide/SKILL.md.
What does decide do?
It evaluates a decision through selected criteria and returns a recommendation with its trade-off, confidence level and next action.
Which criteria does decide consider?
Its set of twelve includes reversibility, revenue impact, cost, time sensitivity and opportunity cost. It chooses 4–6 criteria that fit the decision.
Source text
SKILL.md · MIT
--- name: decide description: "Apply a 12-lens decision framework. Use when weighing options, making a call, or asking for help deciding." trigger: /decide --- # Decision Framework Run any decision through the evaluation framework from `system/04_decision_frameworks.md`. Produces a structured recommendation. ## Usage `/decide [decision or opportunity to evaluate]` ## Process 1. **Parse the decision** — What's being decided? What are the options? 2. **Run relevant lenses** — Not all 12 apply to every decision. Select the 4-6 most relevant: - Leverage — disproportionate output? - Alignment — advances an active priority? - Reversibility — can it be undone? - Time Sensitivity — does waiting cost anything? - Revenue Impact — creates/protects/accelerates revenue? - Asymmetry — large upside, bounded downside? - Dependency — unblocks other work? - Cost — money, time, attention? - Compounding — gets better over time? - Simplicity — simpler path available? - Confidence — how certain are the inputs? - Opportunity Cost — what are we NOT doing? 3. **Check against principal's decision framework** — `system/14_decision_framework.md` - Does it pass the pattern filter? - Where does it sit in the priority stack? - Does it pass the asymmetry test? 4. **Check authority level** — `system/12_authority_matrix.md` - Is this Level 1 (just do it), Level 2 (recommend), or Level 3 (human only)? ## Output Format ``` DECISION: [What we're deciding] OPTIONS: [A vs B vs C] RECOMMENDATION: [What to do and why] KEY LENSES: [3-4 lenses that drove the recommendation] TRADE-OFF: [What we're giving up] CONFIDENCE: [High / Medium / Low — and why] AUTHORITY: [Level 1/2/3 — can the AIgent act or needs approval] NEXT ACTION: [Specific immediate step] ``` ## Rules - Be direct. Recommend, don't waffle. - If confidence is low, structure it as an experiment, not a commitment. - If it's Level 3, present the analysis but explicitly say "this is your call." - Always name the trade-off. Every yes is a no to something else.
© wrg32786 · MIT · wrg32786/aigent-os
Similar skills
All skills for Agent setup: memory, context, orchestration →decide by other authors comes first.