Go Skill
The user just saw a set of options you offered (numbered issues with A/B/C sub-options, or a recommendation block with alternatives). They don't want to re-read them — they want the one YOU recommended to be executed now.
Execution
Step 1: Locate the most recent options block
Scan the prior assistant messages in this conversation for the most recent message that:
- Enumerated 2+ options (A/B/C, 1/2/3, "Option 1/Option 2"), OR
- Presented a "Top pick" / "Recommended" / "Default" alongside alternatives
If multiple option sets exist in recent history, use the most recent one that is still actionable — ignore ones already resolved by subsequent messages.
Step 2: Identify the recommendation
Look for an explicit recommendation marker:
- Words like "recommend", "推荐", "I'd go with", "Top pick", "Default:", "Suggest"
- A pick you marked with
★, ▶, bold, or placed first as "the one to pick"
Step 3: Confirm and execute
If the recommendation is unambiguous:
- State in one line:
→ going with {option label}: {short description}
- Execute immediately — no re-asking, no re-explaining tradeoffs
- Proceed to the full task the options were gating
If options existed but no clear recommendation was flagged:
- Surface the top 2 in a single line each with tradeoffs
- Ask: "No clear default in my last message — {A} or {B}?"
- Do NOT execute until the user picks
If no recent options block exists (within the last ~5 assistant turns):
- Respond: "Nothing pending to pick — what would you like me to go with?"
- Stop.
Rules
- One sentence of confirmation, then act. This skill exists because the user wants speed.
- Don't re-derive the recommendation — trust what you already decided. If you said "I recommend A" 30 seconds ago, pick A now.
- Don't expand scope.
/go executes the specific option; it doesn't also kick off related work you didn't offer.
- If the recommended option has side effects that need confirmation (file deletion,
git reset --hard, force-push, migrations, .env edits): confirm once before executing. /go does not override the destructive-action rule in CLAUDE.md.
- Multiple numbered issues with their own A/B/C (e.g. from Plan Mode): pick the recommended letter for each numbered issue and execute them in order. Mention the combined choice in one line (e.g.
→ going with 1A, 2B, 3A).
Completion Status
- ✅ DONE: Identified recommendation, executed it, produced the expected output.
- ⚠ DONE_WITH_CONCERNS: Executed but noticed the recommendation now looks weaker than when first given — flag that.
- ❌ BLOCKED: No clear recommendation or no recent options — asked user for clarification.
- ❓ NEEDS_CONTEXT: Recommendation requires a destructive action that needs explicit approval.
1---2name: go3description: Accept the recommendation from the most recent A/B/C option set and execute it without re-asking. Use when the user says "按你推荐的来" / "go with your pick" — they glanced at the options, the recommendation looked right, they don't want to re-read all of them.4---56# Go Skill78The user just saw a set of options you offered (numbered issues with A/B/C sub-options, or a recommendation block with alternatives). They don't want to re-read them — they want the one YOU recommended to be executed now.910## Execution1112### Step 1: Locate the most recent options block1314Scan the prior assistant messages in this conversation for the most recent message that:15- Enumerated 2+ options (A/B/C, 1/2/3, "Option 1/Option 2"), OR16- Presented a "Top pick" / "Recommended" / "Default" alongside alternatives1718If multiple option sets exist in recent history, use the **most recent one that is still actionable** — ignore ones already resolved by subsequent messages.1920### Step 2: Identify the recommendation2122Look for an explicit recommendation marker:23- Words like "recommend", "推荐", "I'd go with", "Top pick", "Default:", "Suggest"24- A pick you marked with `★`, `▶`, bold, or placed first as "the one to pick"2526### Step 3: Confirm and execute2728**If the recommendation is unambiguous:**29- State in one line: `→ going with {option label}: {short description}`30- Execute immediately — no re-asking, no re-explaining tradeoffs31- Proceed to the full task the options were gating3233**If options existed but no clear recommendation was flagged:**34- Surface the top 2 in a single line each with tradeoffs35- Ask: "No clear default in my last message — {A} or {B}?"36- Do NOT execute until the user picks3738**If no recent options block exists (within the last ~5 assistant turns):**39- Respond: "Nothing pending to pick — what would you like me to go with?"40- Stop.4142## Rules4344- **One sentence of confirmation, then act.** This skill exists because the user wants speed.45- **Don't re-derive** the recommendation — trust what you already decided. If you said "I recommend A" 30 seconds ago, pick A now.46- **Don't expand scope.** `/go` executes the specific option; it doesn't also kick off related work you didn't offer.47- **If the recommended option has side effects that need confirmation** (file deletion, `git reset --hard`, force-push, migrations, `.env` edits): confirm once before executing. `/go` does not override the destructive-action rule in CLAUDE.md.48- **Multiple numbered issues with their own A/B/C** (e.g. from Plan Mode): pick the recommended letter for each numbered issue and execute them in order. Mention the combined choice in one line (e.g. `→ going with 1A, 2B, 3A`).4950## Completion Status5152- ✅ **DONE**: Identified recommendation, executed it, produced the expected output.53- ⚠ **DONE_WITH_CONCERNS**: Executed but noticed the recommendation now looks weaker than when first given — flag that.54- ❌ **BLOCKED**: No clear recommendation or no recent options — asked user for clarification.55- ❓ **NEEDS_CONTEXT**: Recommendation requires a destructive action that needs explicit approval.