context-hunter
Discover codebase patterns, conventions, and unwritten rules before making changes. Use when implementing features, fixing bugs, or refactoring code.
Best use case
context-hunter is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Discover codebase patterns, conventions, and unwritten rules before making changes. Use when implementing features, fixing bugs, or refactoring code.
Teams using context-hunter should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/context-hunter/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How context-hunter Compares
| Feature / Agent | context-hunter | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Discover codebase patterns, conventions, and unwritten rules before making changes. Use when implementing features, fixing bugs, or refactoring code.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
Best AI Skills for Claude
Explore the best AI skills for Claude and Claude Code across coding, research, workflow automation, documentation, and agent operations.
Cursor vs Codex for AI Workflows
Compare Cursor and Codex for AI coding workflows, repository assistance, debugging, refactoring, and reusable developer skills.
SKILL.md Source
# Context Hunter Before writing code, investigate how similar problems are already solved in this codebase. ## Before Implementation ### Discover Existing Patterns 1. **Find analogous features**: Search for code that solves similar problems. Study it before proposing your approach. 2. **Trace data flow**: How does similar data move through the system? Note caching, validation, and error handling patterns. 3. **Identify utilities**: Search for existing helpers before creating new ones. ### Detect Unwritten Conventions Look for implicit rules encoded in the codebase: - **Schema patterns**: `deleted_at` columns indicate soft-deletion. Audit columns indicate tracking requirements. - **Naming patterns**: Note consistency in `user_id` vs `userId` vs `userID`. - **Test patterns**: What's tested thoroughly reveals team priorities. ### Verify Assumptions - Run the test suite to understand current state - Check linter and formatter configs - Read recent commits in affected areas - Examine database schemas for constraints ## During Implementation ### Match Existing Code Your changes should be indistinguishable from existing code: - Use the same patterns, abstractions, and utilities - Follow the same error handling approach - Respect module boundaries - Match naming conventions exactly ### Surface Concerns When you discover conflicts between requirements and existing patterns: - Ask clarifying questions before proceeding - Flag risks you've identified - Offer alternatives that align with codebase conventions ## Checklist Before proposing changes, confirm: - [ ] Studied analogous features in the codebase - [ ] Checked for reusable utilities - [ ] Reviewed test patterns for similar functionality - [ ] Noted naming and schema conventions - [ ] Verified approach matches existing patterns
Related Skills
evals-context
Provides context about the Roo Code evals system structure in this monorepo. Use when tasks mention "evals", "evaluation", "eval runs", "eval exercises", or working with the evals infrastructure. Helps distinguish between the evals execution system (packages/evals, apps/web-evals) and the public website evals display page (apps/web-roo-code/src/app/evals).
context-fundamentals
This skill should be used when the user asks to "understand context", "explain context windows", "design agent architecture", "debug context issues", "optimize context usage", or discusses context components, attention mechanics, progressive disclosure, or context budgeting. Provides foundational understanding of context engineering for AI agent systems.
zinc-database
Access ZINC (230M+ purchasable compounds). Search by ZINC ID/SMILES, similarity searches, 3D-ready structures for docking, analog discovery, for virtual screening and drug discovery.
zarr-python
Chunked N-D arrays for cloud storage. Compressed arrays, parallel I/O, S3/GCS integration, NumPy/Dask/Xarray compatible, for large-scale scientific computing pipelines.
yeet
Use only when the user explicitly asks to stage, commit, push, and open a GitHub pull request in one flow using the GitHub CLI (`gh`).
xlsx
Spreadsheet toolkit (.xlsx/.csv). Create/edit with formulas/formatting, analyze data, visualization, recalculate formulas, for spreadsheet processing and analysis.
xan
High-performance CSV processing with xan CLI for large tabular datasets, streaming transformations, and low-memory pipelines.
writing-plans
Use when you have a spec or requirements for a multi-step task, before touching code
writing-docs
Guides for writing and editing Remotion documentation. Use when adding docs pages, editing MDX files in packages/docs, or writing documentation content.
windows-hook-debugging
Windows环境下Claude Code插件Hook执行错误的诊断与修复。当遇到hook error、cannot execute binary file、.sh regex误匹配、WSL/Git Bash冲突时使用。
weights-and-biases
Track ML experiments with automatic logging, visualize training in real-time, optimize hyperparameters with sweeps, and manage model registry with W&B - collaborative MLOps platform
webthinker-deep-research
Deep web research for VCO: multi-hop search+browse+extract with an auditable action trace and a structured report (WebThinker-style).