Minimal Code Fix
cobusgreyling/loop-engineering
Makes the smallest code change that fixes one well-scoped problem, such as a CI failure, review comment or typo, without refactoring anything unrelated.
Finds root cause before applying fixes for errors, crashes, regressions, failing tests, broken behavior, and screenshot-reported defects.
Install Hunt
$ npx skills add ninehills/skills --skill hunt -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install ninehills/skills hunt --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/ninehills/skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/hunt .claude/skills/hunt && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "hunt" agent skill from https://github.com/ninehills/skills/tree/main/hunt into .claude/skills/hunt/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hunt", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/ninehills/skills/tree/main/huntType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add ninehills/skills --skill hunt -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install ninehills/skills hunt --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ninehills/skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/hunt .agents/skills/hunt && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "hunt" agent skill from https://github.com/ninehills/skills/tree/main/hunt into .agents/skills/hunt/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hunt", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add ninehills/skills --skill hunt -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install ninehills/skills hunt --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ninehills/skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/hunt .cursor/skills/hunt && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "hunt" agent skill from https://github.com/ninehills/skills/tree/main/hunt into .cursor/skills/hunt/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hunt", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/ninehills/skills.git --path hunt--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add ninehills/skills --skill hunt -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install ninehills/skills hunt --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ninehills/skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/hunt .gemini/skills/hunt && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "hunt" agent skill from https://github.com/ninehills/skills/tree/main/hunt into .gemini/skills/hunt/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hunt", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install ninehills/skills huntInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add ninehills/skills --skill hunt -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/ninehills/skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/hunt .github/skills/hunt && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "hunt" agent skill from https://github.com/ninehills/skills/tree/main/hunt into .github/skills/hunt/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hunt", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add ninehills/skills --skill hunt -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install ninehills/skills hunt --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ninehills/skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/hunt .opencode/skills/hunt && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "hunt" agent skill from https://github.com/ninehills/skills/tree/main/hunt into .opencode/skills/hunt/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hunt", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
hunt- GitHub stars
- 280
- Token cost
- ~4.8k tokens
- SKILL.md length
- 2,641 words
- Files
- 5 (incl. references)
- Skills in repo
- 38
- Repo updated
- First seen
- Licence
- None found
At a glance
Finds root cause before applying fixes for errors, crashes, regressions, failing tests, broken behavior, and screenshot-reported defects.
- Works in 2 steps: Protect the user's worktree first: run… → Find candidate good tag: git tag…
- Users report in any language errors
- SKILL.md covers Outcome Contract, Diagnosis Signals, Durable Context Preflight and Hard Rules, plus 12 more sections
- Calls git, bash and node
What it does
Hunt is an agent skill from ninehills/skills. Finds root cause before applying fixes for errors, crashes, regressions, failing tests, broken behavior, and screenshot-reported defects. Use when users report in any language errors, crashes, broken behavior, regressions, failing tests, screenshot evidence, or something that used to work and now fails. Not for code review or new features.
Its SKILL.md is about 4.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including reference files (for example `references/failure-patterns.md`, `references/ime-unicode.md` and `references/logging-techniques.md`).
It sits in Development, covering Failing and flaky tests and Root cause analysis.
When your agent uses it
- Users report in any language errors
- Broken behavior
- Screenshot evidence
- Something that used to work and now fails
Example prompts
- “Use the hunt skill to find root cause before applying fixes for errors, crashes, regressions, failing tests, broken behavior, and…”
- “/hunt”
Workflow steps
2 steps, taken from the first numbered list in SKILL.md.
- Protect the user's worktree first: run git status --short --branch -uall. If modified, staged, or untracked files exist, do not bisect in…
- Find candidate good tag: git tag --sort=-version:refname | head -10 or ask the user for the last known-good commit.
What it can do on your machine
Read from SKILL.md and the folder at commit f3e82a7. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
gitbashnode
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Hunt loads about 4.8k tokens when it runs, and up to ~8.6k if it reads all its reference files. Until then it costs about 87 tokens; SKILL.md has 2,641 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
Without a licence we can't republish the file, so here is its outline and opening line. It has 2,641 words (~4,771 tokens).
“Prefix your first line with 🥷 inline, not as its own paragraph.”
- name
- hunt
- when_to_use
- 排查, 查查, 报错, 崩溃, 不工作, 不对, 跑不通, 以前是好的, 回归, 截图回归, 判断错误原因, 判断为什么报错, 反复修不好, debug, regression, used to work, broke after update, why broken, not working, what's…
- dispatch_intent
- Error, crash, regression, screenshot-reported defect, test failure, stale cache, runtime boundary, why broken
Files
SKILL.md and 4 other files (references) in hunt of ninehills/skills.
- SKILL.md
- references/failure-patterns.md
- references/ime-unicode.md
- references/logging-techniques.md
- references/rendering-debug.md
Open the folder on GitHubat commit f3e82a7
Compare with similar skills
Hunt next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Hunt this skillninehills/skills | 280 | — | ~4.8k | Automated safety check: Pass | None | |
| Minimal Code Fixcobusgreyling/loop-engineering | 11k | 1 repos | ~671 | Automated safety check: Notes | MIT | |
| Backprop: Bug-to-Spec ProtocolJuliusBrussee/cavekit | 1.2k | — | ~653 | Automated safety check: Pass | MIT | |
| CI TriageMentra-Community/MentraOS | 2.4k | — | ~582 | Automated safety check: Pass | Apache-2.0 | |
| Root Cause Debuggingjsmastery-pro/skills | 1.5k | — | ~1.8k | Automated safety check: Notes | MIT | |
| Superpowers Systematic Debuggingchristopherarter/superpowers-reasonix | 102 | — | ~2k | Automated safety check: Pass | MIT |
Similar skills
Backprop: Bug-to-Spec Protocol
JuliusBrussee/cavekit
After a bug is found, traces its root cause and feeds a new testable invariant back into the project spec so the bug class can't recur.
CI Triage
Mentra-Community/MentraOS
Triage failing GitHub PR checks: list failures with gh, fetch capped Actions logs, skip non-Actions checks, and summarize root cause.
Root Cause Debugging
jsmastery-pro/skills
Runs a reproduce, localize, hypothesize, test, fix and verify loop to find a bug's root cause, applies the minimal fix and hands off a regression test.
Superpowers Systematic Debugging
christopherarter/superpowers-reasonix
Any bug, failing or flaky test, or surprise behavior?. An agent skill from christopherarter/superpowers-reasonix.
CI Fix
warpdotdev/oz-skills
Diagnose and fix GitHub Actions CI failures. An agent skill from warpdotdev/oz-skills.
More from ninehills/skills
All 38 skills in this repoAlphaear Predictor
ninehills/skills
Market prediction skill using Kronos. An agent skill from ninehills/skills.
Alphaear Signal Tracker
ninehills/skills
Track finance investment signal evolution and update logic based on new finance market information.
Fireworks Tech Graph
ninehills/skills
A skill your agent uses when the user wants to create any technical diagram - architecture, data flow, flowchart, sequence, agent/memory, or concept map - and export as SVG+PNG.
Alphaear Sentiment
ninehills/skills
Analyze finance text sentiment using FinBERT or LLM. An agent skill from ninehills/skills.
Bggg Creator Image2ppt
ninehills/skills
把图片、截图、海报、PPT 页面截图、HTML 或 SVG 设计稿转换成可编辑 PPTX 的 Codex skill. An agent skill from ninehills/skills.
Bggg Creator Image2psd
ninehills/skills
把一张或多张图片整理成 PSD 图层文件的创作与转换 skill。当用户需要 image2psd、图片转 PSD、 多张图片拼成 PSD、海报/设计稿拆成多个图层、白底转透明、颜色聚类拆层、把 Codex/AI 生图结果拆成元素图再合成 PSD、 或希望输出 layered PSD、可在 Photoshop/Photopea 中编辑的分层栅格文件时，应该使用此 skill。
Related
Categories
Questions about Hunt
What does Hunt do?
Finds root cause before applying fixes for errors, crashes, regressions, failing tests, broken behavior, and screenshot-reported defects. Hunt is an agent skill from ninehills/skills. Finds root cause before applying fixes for errors, crashes, regressions, failing tests, broken behavior, and screenshot-reported defects.
When should I use Hunt?
Hunt fits situations like: users report in any language errors; broken behavior; screenshot evidence; something that used to work and now fails.
How do I install Hunt in Claude Code?
Run `npx skills add ninehills/skills --skill hunt -a claude-code`. Or copy the skill folder (hunt in ninehills/skills) into .claude/skills/hunt in your project. Claude Code loads it when a task matches its description.
How do I install Hunt in Codex?
Run `npx skills add ninehills/skills --skill hunt -a codex`. Or copy the skill folder (hunt in ninehills/skills) into .agents/skills/hunt in your project. Codex loads it when a task matches its description.
Can I use Hunt in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ninehills/skills --skill hunt -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/hunt, .gemini/skills/hunt, .github/skills/hunt and .opencode/skills/hunt in your project.
What does Hunt need to run?
Going by SKILL.md and its folder, Hunt needs the command-line tools its instructions call (git, bash and node).
Does Hunt access the network?
SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Hunt safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Hunt use?
No licence was found for Hunt or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.
How many tokens does Hunt use?
About 4.8k tokens (SKILL.md is roughly 19k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 3.8k tokens, read only when the agent opens those files.
What are the alternatives to Hunt?
Skills that share tags, products or a category with Hunt: Minimal Code Fix (cobusgreyling/loop-engineering, 11k stars), Backprop: Bug-to-Spec Protocol (JuliusBrussee/cavekit, 1.2k stars), CI Triage (Mentra-Community/MentraOS, 2.4k stars) and Root Cause Debugging (jsmastery-pro/skills, 1.5k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Hunt?
ninehills (a GitHub user) maintains it in ninehills/skills, which has 280 GitHub stars. The repository holds 38 skills in this directory. The repository was last updated on June 22, 2026.
Source: ninehills/skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.