Skill
yolo-debug
Use when a reported problem, failure, or bug needs a systematic root-cause investigation — reproduce → isolate → fix → verify — recorded as one durable…
Development
Skill
/yolo-decide
Use when facing a design or architecture decision that benefits from multiple perspectives before committing. Produces a decision record under workspace/decisions/. Triggers on "help me decide X vs Y", "which approach", "should we use A or B".
Install
$ npx -y skills add CoriChui/yolo --skill yolo-decide --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/yolo-decide
Context preview
The summary Claude sees to decide when to auto-load this skill.
Use when facing a design or architecture decision that benefits from multiple perspectives before committing. Produces a decision record under workspace/decisions/. Triggers on "help me decide X vs Y", "which approach", "should we use A or B".
SKILL.md
yolo-decide.SKILL.mdname: yolo-decide
description: Use when facing a design or architecture decision that benefits from multiple perspectives before committing. Produces a decision record under workspace/decisions/. Triggers on "help me decide X vs Y", "which approach", "should we use A or B".
yolo-decide
Reach a defensible decision via multi-perspective analysis, and record it.
Procedure
0. The multi-perspective analysis runs at the billed `agents.decide` tier. Confirm the decision framing before launching it — the plan-gate analogue for a decision (`.claude/yolo/conventions.md` *The two gates*). **STOP and wait for the human here** (state the framing, then pause) — do not state the framing and slide into the analysis in the same turn. Skip only if the user pre-consented. 1. State the decision and the options crisply. 2. Argue each option from several lenses — at minimum correctness/risk, simplicity/maintainability, and pragmatism/cost. Surface the strongest case FOR and AGAINST each. 3. Recommend one option, with explicit rationale, the alternatives considered, dissents (minority concerns worth recording), and revisit triggers (conditions that should reopen this). 4. Write `workspace/decisions/<slug>.md` with: decision, rationale, approach, alternatives_considered, dissents, revisit_triggers, confidence. Confirm before overwriting an existing slug. 5. Commit (`yolo: decision <slug>`).
When to reach for `bakeoff` instead
`yolo-decide` is a single-pass, multi-lens analysis — right for most X-vs-Y calls. For a **high-stakes, hard-to-reverse decision with several defensible options** (architecture, migration, tool selection), the [`bakeoff`](https://github.com/CoriChui/bakeoff) skill runs a heavier judged tournament: it generates diverse candidate solutions, auto-derives a rubric for the problem, scores each with independent judges, and adversarially refutes the leader. If `bakeoff` is installed, offer it for those cases, then record its verdict as the decision here (`workspace/decisions/<slug>.md`) so the trail stays in one place.
Constraints
- Read-only with respect to code; the only file you write is the decision record.
- No status field; decisions are standalone records.
- Run the multi-perspective analysis at the `agents.decide` tier from `workspace/config.yaml`.
Read more
name: yolo-decide description: Use when facing a design or architecture decision that benefits from multiple perspectives before committing. Produces a decision record under workspace/decisions/. Triggers on "help me decide X vs Y", "which approach", "should we use A or B".
yolo-decide
Reach a defensible decision via multi-perspective analysis, and record it.
Procedure
0. The multi-perspective analysis runs at the billed `agents.decide` tier. Confirm the decision framing before launching it — the plan-gate analogue for a decision (`.claude/yolo/conventions.md` *The two gates*). **STOP and wait for the human here** (state the framing, then pause) — do not state the framing and slide into the analysis in the same turn. Skip only if the user pre-consented. 1. State the decision and the options crisply. 2. Argue each option from several lenses — at minimum correctness/risk, simplicity/maintainability, and pragmatism/cost. Surface the strongest case FOR and AGAINST each. 3. Recommend one option, with explicit rationale, the alternatives considered, dissents (minority concerns worth recording), and revisit triggers (conditions that should reopen this). 4. Write `workspace/decisions/<slug>.md` with: decision, rationale, approach, alternatives_considered, dissents, revisit_triggers, confidence. Confirm before overwriting an existing slug. 5. Commit (`yolo: decision <slug>`).
When to reach for `bakeoff` instead
`yolo-decide` is a single-pass, multi-lens analysis — right for most X-vs-Y calls. For a **high-stakes, hard-to-reverse decision with several defensible options** (architecture, migration, tool selection), the [`bakeoff`](https://github.com/CoriChui/bakeoff) skill runs a heavier judged tournament: it generates diverse candidate solutions, auto-derives a rubric for the problem, scores each with independent judges, and adversarially refutes the leader. If `bakeoff` is installed, offer it for those cases, then record its verdict as the decision here (`workspace/decisions/<slug>.md`) so the trail stays in one place.
Constraints
- Read-only with respect to code; the only file you write is the decision record.
- No status field; decisions are standalone records.
- Run the multi-perspective analysis at the `agents.decide` tier from `workspace/config.yaml`.
Ships withyolo
Reasoning-first development for Claude Code. Git is the source of truth; status is derived, never stored. YOLO turns "I want X" into a planned, executed, verified, and landed change, driven by conversation and git rather than tracked status files.
Get the whole plugin
Other skills on yolo.
Skill
yolo-feature
Use when the user wants to build, add, or implement a feature. Captures intent, drafts a brief, confirms, then composes research → plan → execute → verify →…
Skill
yolo-finish
Use when a feature is implemented and verified, to land it. Default path is PR + CI check, with the ship gate confirming before the irreversible merge;…
Skill
yolo-init
Use when setting up YOLO in a project for the first time, or repairing the setup. Scaffolds workspace/config.yaml and the features/, decisions/, and debug/…
Skill
yolo-intake
Use when a feature should draw on the project's reference material for context. yolo-intake does NOT fetch, import, or copy anything — it points YOLO at a…