菜单
ALWAYS activate this skill before fixing ANY bug, error, test failure, CI/CD issue, type error, lint, log error, UI issue, code problem.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Create or update TheOneKit agent .md files with canonical structure. Use when adding a new agent, updating maxTurns/model, or fixing frontmatter fields.
Design and review agentic systems against Claude Code architecture canon — agent loops, tool interfaces, prompt-cache strategy, MCP/hooks/memory primitives, CLI vs Agent SDK.
Answer technical questions with context-aware skill activation. Use for 'how does X work', 'what is the best way to', 'explain this pattern' queries.
Monitor a PR to green+merged. Use for: 'babysit pr', 'watch pr', 'monitor pr', 'flaky ci', 'auto merge'. Retries flaky CI, resolves simple conflicts, auto-merges when approved+green.
Generate ideas and explore solutions with context-aware skill activation. Use for 'how should I approach X', 'what are the options for Y', 'help me think through this'.
Cap-table + equity administration for US/foreign C-Corps — Carta vs Pulley vs AngelList Stack comparison, 83(b) elections (30-day strict deadline, NO extensions), 409A valuations ($1.5-3K), SAFE notes (YC post-money template), Series Seed terms, vesting agreements, founder reverse vesting. Pre-Series A: DIY spreadsheet or Pulley Startup ($1,200/yr) sufficient.
| name | t1k:fix |
| description | ALWAYS activate this skill before fixing ANY bug, error, test failure, CI/CD issue, type error, lint, log error, UI issue, code problem. |
| keywords | ["fix","bug","error","resolve","patch","repair","test-failure"] |
| argument-hint | [issue] [--auto|--review|--quick|--parallel] |
| effort | medium |
| version | 1.108.0 |
| origin | theonekit-core |
| repository | The1Studio/theonekit-core |
| module | t1k-base |
| protected | true |
Fix issues with intelligent classification and registry-based routing.
AskUserQuestion is deferredAskUserQuestion is a deferred tool: its name appears in the deferred-tools system-reminder but its schema is NOT loaded at session start. Direct invocation fails with InputValidationError.
Operational pre-step (mandatory before drafting any structured multi-option question):
AskUserQuestion is in the loaded tool list. If not, run:
ToolSearch(query="select:AskUserQuestion", max_results=1)
Failure mode this guard prevents: assistant remembers the rule, drafts the question correctly in its head, then because the tool isn't loaded, falls back to "I'll just write the options as prose, and call the tool next time." Drafting prose bullets first is a violation — see rules/always-ask-on-unresolved.md "Forbidden prose" table.
Pick by intent; keep loading minimal.
| Intent | Path |
|---|---|
| Diagnose and fix one bug end-to-end | Default --auto (Steps 1–6 below) |
| Trivial issue (lint, single type error) | --quick (skips deep diagnose) |
| Want human checkpoint before applying fix | --review |
| Multiple unrelated bugs at once | --parallel (sub-agents per issue) |
| 3+ fix attempts already failed | STOP — escalate to architecture discussion (HARD-GATE below) |
| Flag | Description |
|---|---|
--auto | Autonomous mode (default) |
--review | Human-in-the-loop review mode |
--quick | Quick mode for trivial issues |
--parallel | Route to parallel implementer agents per issue |
Follow protocol: skills/t1k-cook/references/routing-protocol.md
This command uses roles: implementer, t1k-debugger
Follow protocol: skills/t1k-cook/references/activation-protocol.md
| Step | Name | Key Action | Reference |
|---|---|---|---|
| 0 | Mode Selection | Ask user for workflow mode if no --auto | references/mode-selection.md |
| 1 | Scout | Map affected files, deps, tests — NEVER skip | references/workflow-quick.md |
| 2 | Diagnose | Structured root cause analysis — NEVER skip | references/diagnosis-protocol.md |
| 3 | Complexity | Classify: Simple/Moderate/Complex/Parallel | references/complexity-assessment.md |
| 4 | Fix | Implement per selected workflow | references/workflow-standard.md |
| 5 | Verify + Prevent | Run exact pre-fix commands, add regression test | references/prevention-gate.md |
| 6 | Finalize | Report, t1k-docs-manager, commit offer | — |
Detailed workflow diagrams: references/fix-workflow-overview.md
| Level | Indicators | Workflow |
|---|---|---|
| Simple | Single file, clear error, type/lint | references/workflow-quick.md |
| Moderate | Multi-file, root cause unclear | references/workflow-standard.md |
| Complex | System-wide, architecture impact | references/workflow-deep.md |
| Parallel | 2+ independent issues OR --parallel | Parallel implementer agents |
Specialized: references/workflow-ci.md, references/workflow-logs.md, references/workflow-test.md, references/workflow-types.md, references/workflow-ui.md
/t1k:scout (Step 1) — understand before diagnosing/t1k:debug (Step 2) — systematic root cause investigation/t1k:think (Step 2) — structured hypothesis formation[t1k:skill-bug kit="..." skill="..." bug="..." evidence="..."]
marker in your final message. The lesson-collector hook will queue a
GitHub issue on the owning kit repo.Full activation matrix: references/skill-activation-matrix.md
Follow protocol: skills/t1k-cook/references/subagent-injection-protocol.md
Sub-agent forking: see skills/t1k-architecture/references/fork-hygiene.md.