Detective
Debugging presented as a case log — titled episodes moving clue -> hypothesis -> ruled-out -> culprit -> fix. Narrative framing over disciplined diagnosis; keeps full technical accuracy. Best for diagnosing bugs and investigations. Use when user invokes /detective, says "detective mode" / "detective style" / "case log". One of a rotating wardrobe with /panels and /punchy.
Install
npx skills add thatmike1/claude-skills --skill detectivegit clone --depth 1 https://github.com/thatmike1/claude-skills.git /tmp/claude-skills
mkdir -p ~/.claude/skills
cp -r /tmp/claude-skills/deprecated/detective ~/.claude/skills/detectivePersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
Present debugging and investigation work as a detective's case log — hypothesis-driven, evidence-first, narrated as you close in on the culprit. Full engineering capability stays intact; the narrative is a presentation layer over real diagnosis, never a substitute for it. ## Persistence ACTIVE EVERY RESPONSE until told otherwise. No drift back to default after many turns. Off only on: "stop detective" / "normal mode" / switching to another style skill (/panels, /punchy, /caveman). ## Frame - Open with **The case:** one or two lines — the symptom and what "solved" looks like. - Log progress as short **episodes**, each a bold title stating the move or clue (1–3 sentences each): - **Clue: only async jobs fail** — what you observed. - **Hypothesis: stale cache** — what you suspect and why. - **Ruled out: config drift** — what you eliminated and how. - When found, call it: **The culprit** — root cause stated plainly, with the evidence that convicts it. - Close with **The fix**, and **Loose ends** if relevant (regression risk, sibling code with the same bug). ## Discipline under the hood The story must reflect real method: reproduce first, change one variable at a time, state what would falsify each hypothesis, verify the fix kills the symptom. If guessing, label it **Working theory (unverified)** — never dress a guess as a conviction. ## Voice
Details
- Skill name
detective- Repository
- thatmike1/claude-skills
- Path
deprecated/detective/SKILL.md- Repo updated
- 18 November 2026
FAQ
What does the Detective skill do?
Debugging presented as a case log — titled episodes moving clue -> hypothesis -> ruled-out -> culprit -> fix. Narrative framing over disciplined diagnosis; keeps full technical accuracy. Best for diagnosing bugs and investigations. Use when user invokes /detective, says "detective mode" / "detective style" / "case log". One of a rotating wardrobe with /panels and /punchy.
How do I install the Detective skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add thatmike1/claude-skills --skill detective. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Detective popular?
It lives in thatmike1/claude-skills, which has 10 GitHub stars and 1 forks.
Related skills
Afk Prompt
10thatmike1/claude-skills
Write a copy-paste prompt that hands one or more tasks (usually beads issues) to a fresh Claude instance to run autonomously while the user is away — no questions, no waiting for input. Includes picking which tasks are safe to run unattended. Use when the user says they're going AFK (shower, lunch, errand, overnight), asks "which tasks can just run without me", or wants an autonomous/batch prompt. For attended sessions the user will steer, use the live-prompt skill instead.
AI CV Scanner
10thatmike1/claude-skills
Mine Claude Code conversation history to answer questions about your AI experience. Scans session indexes, spawns parallel subagents to deep-dive relevant conversations, and drafts evidence-based answers. Use when user mentions CV, AI experience, questionnaire, scan my conversations, or needs to document their AI usage.
Arena
10thatmike1/claude-skills
Give several T3 child candidates the same prompt, rank them against a rubric written before they run, pick a base and graft the best of the rest into it. Run with /arena when one attempt at a non-trivial artifact would lock in the wrong shape.
Vincent Trading Engine for Agents
5HeyVincent-ai/agent-skills
Strategy-driven automated trading for Polymarket and HyperLiquid. Use this skill when users want to create trading strategies, set stop-loss/take-profit/trailing stop rules, or manage automated trading. Triggers on "trading strategy", "stop loss", "take profit", "trailing stop", "automated trading", "trading engine", "trade rules", "strategy monitor".
Spec Coach
5boxabirds/spec-coach
Activate when the user is writing, editing, or discussing software requirements, specifications, acceptance criteria, user stories, or feature definitions. Also activate when the user asks to build, implement, or create a feature and no specification or requirements document has been referenced or exists in the conversation. Do NOT activate for bug fixes, refactoring, documentation, or tasks where requirements are already clearly defined in the conversation.
Cue Financial Deep Read
8sensedeal/cue-skills
用 Cue 跑「财报深读」场景的深度研究:多源公开数据交叉、结论带来源。 Run Cue deep research for the "Financial Deep Read" scenario. 触发 Triggers: 财报深读、财务与业绩、信披与监管 / financial deep read, footnote risk scan, audit opinion
Browse the most popular Claude skills, all finance & crypto skills, or write your own with the skills generator.