debug
Systematic root-cause analysis for bugs, errors, and unexpected behavior. Use to debug this, find the root cause, or investigate why is this failing. Also invoked as ultradebug.
- License 许可
- MIT
- 最近更新
- 2026-11-11
- Stars
- ★ 1
- Forks
- 1
01 前言 Front Matter
- name
- debug
- triggers
- [ "debug this", "why is this failing", "root cause", "investigate", "ultradebug" ]
- description
- Systematic root-cause analysis for bugs, errors, and unexpected behavior. Use to debug this, find the root cause, or investigate why is this failing. Also invoked as ultradebug.
02 资源文件 1
- 参考文档manifest.json1.2 KB
03 SKILL.md 正文
Debug
Systematic 7-step debugging. Don't guess — trace.
Steps
- Reproduce — get a minimal, reliable reproduction
- Locate — find the exact file, line, and call path where it breaks
- Hypothesize — list 2-3 competing explanations
- Evidence — for each hypothesis: what would confirm or rule it out
- Test — run the fastest confirming/ruling test first
- Fix — change exactly what the evidence points to
- Verify — confirm fix resolves the issue, run full test suite
Rules
- Never change code before you know the root cause
- Read the actual error message — don't skim it
- Check assumptions: is the value what you think it is? Add a log
- Distinguish "symptom" from "cause" — fix the cause
- If stuck after 3 hypotheses, add instrumentation before guessing more
Output
Root cause: <one sentence>
Location: <file>:<line>
Fix: <what to change and why>
04 同仓库更多 Skills
token-audit
Audit historical Claude Code token usage from JSONL session files — shows total spend, cache hit rates, top costly sessions, weekly trends, and where tokens are going. Run after heavy sessions or weekly to measure optimization impact. Answers how many tokens a session used, how expensive was that session, session cost, and token usage report.
smart-model-route
Auto-classify prompt complexity via Haiku (with heuristic fallback) and inject model routing hints for Agent tool calls. Wired as a UserPromptSubmit hook — fires on every prompt, routes low tasks to Haiku, standard to Sonnet, complex to Sonnet with thorough reasoning, and critical (security/arch/migrations) to Opus. Handles model selection, for example choose model by task complexity.
smart-commands
Decision guide for when to proactively use Claude Code slash commands — /think, /model, /compact, /clear. Use when choosing whether to invoke a command before or during a task, or when a complexity-classifier hook has flagged a task as high or critical. Pairs with the complexity-classifier UserPromptSubmit hook. Answers when to compact, should I switch models, and whether to use extended thinking. Use to pick the right /model command and switch model.
spec-ship
暂无简介
spec-new
Create a committed per-feature spec under `docs/specs/YYYY-MM-DD-<slug>/{spec,tasks}.md` with frontmatter (status, created, owner, pr, tags). Promotes an ephemeral `.claude/plans/<name>.md` into a persistent, searchable artifact. Use when starting a feature that's larger than a one-shot PR.
roadmap-refresh
Regenerate `docs/roadmap.md` for a repo from all specs under `docs/specs/` + their frontmatter (status, tags, pr). Produces Now/Next/Recently-shipped sections. Run after creating / shipping a spec, or at the start of a new session for orientation.