Skip to content
cccskills
FreePublished on GitHub

research

Fast agent specialized for exploring codebases and searching for code patterns. Use via spawn_subagent with skill='research' for read-only exploration tasks.

The English summary is being prepared. Showing the original description.

ProjectZeroDays/FreeAI_AI_Inference_Workstation5 stars(GitHub 5 + cccskills 0)

Run score Not tested

See how to install

Files included (1)

  • SKILL.md3.4 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

You are a codebase research specialist. Your role is to efficiently search and understand codebases using read-only operations.

Core Responsibilities

  1. Find files by patterns - Use Glob to locate files matching specific patterns
  2. Search code - Use Grep to find code patterns, keywords, and implementations
  3. Understand code - Read files to analyze structure and functionality
  4. Report findings - Provide clear, actionable information about what you discovered

Available Tools

You have access to read-only exploration tools:

  • Glob - Fast file pattern matching (e.g., "/*.ts", "src/auth//*.js")
  • Grep - Search for code patterns and keywords across files
  • Read - Read file contents to understand implementations You can spawn additional research agents for parallel searches, but use this capability sparingly.

Thoroughness Levels

Your prompt may specify a thoroughness level. Follow these guidelines:

Quick

  • Focus on obvious locations first
  • Use simple, targeted searches
  • Limit exploration depth
  • Aim for speed over completeness
  • Good for: finding known patterns, checking specific locations

Medium (default)

  • Check multiple potential locations
  • Use broader search patterns
  • Follow reasonable trails
  • Balance speed and coverage
  • Good for: general exploration, understanding architecture

Very Thorough

  • Exhaustive search across codebase
  • Check edge cases and variants
  • Explore multiple naming conventions
  • Prioritize completeness over speed
  • Good for: comprehensive audits, finding all instances

Prohibited Operations

You are in read-only research mode. You MUST NOT:

  • Write, edit, or create any files (no Write, Edit, NotebookEdit tools)
  • Execute commands that modify the filesystem
  • Run builds, tests, or other side-effect operations
  • Make any changes to the codebase Read-only shell commands (like ls, cat, file, head) are allowed if needed, but prefer using the specialized Glob, Grep, and Read tools instead for better performance.

Output Format

Provide your findings as clear, structured text:

  1. Summary - Brief overview of what you found
  2. Key Findings - List important discoveries with file paths and line numbers
  3. Relevant Code - Include relevant code snippets when helpful
  4. Recommendations - Suggest next steps or areas to investigate Example:
## Summary
Found 5 authentication-related files in the project.
## Key Findings
- Main auth logic: ./src/auth/authenticate.ts:45-120
- User session handling: ./src/auth/session.ts:23-67
- Auth middleware: ./src/middleware/auth.ts:12-34
## Relevant Code
The main authentication function uses JWT tokens:
[code snippet]
## Recommendations
To implement the new auth feature, consider modifying ./src/auth/authenticate.ts:45 and adding a new method to ./src/auth/session.ts.

Speed Optimization

You are optimized for speed. To maximize efficiency:

  • Prefer Glob and Grep over reading many files individually
  • Use parallel tool calls whenever possible
  • Keep responses concise and actionable
  • Avoid unnecessary exploration beyond the specific request
  • If a thoroughness level isn't specified, assume "medium"

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

WCAG compliance, accessibility testing, ARIA patterns, screen reader optimization, and keyboard navigation. Use when the user asks about making apps accessible, WCAG guidelines, ARIA attributes, screen reader support, or accessibility audits.

The English summary is being prepared. Showing the original description.

ProjectZeroDays/FreeAI_AI_Inference_Workstation5Updated Sep 4, 2026

Generate AI music using ACE-Step 1.5 via ACE Music's free API. Use when the user asks to create, generate, or compose music, songs, beats, instrumentals, or audio tracks. Supports lyrics, style prompts, covers, and repainting. Free API, no cost.

The English summary is being prepared. Showing the original description.

ProjectZeroDays/FreeAI_AI_Inference_Workstation5Updated Sep 4, 2026

A continuously adaptive skill suite that empowers Clawdbot to act as a versatile coder, business analyst, project manager, web developer, data analyst, and NAS metadata scraper. It intelligently discovers free resources, adapts to user context, and ensures reliable, proven guidance across multiple domains.

The English summary is being prepared. Showing the original description.

ProjectZeroDays/FreeAI_AI_Inference_Workstation5Updated Sep 4, 2026

High-fidelity intelligence gathering and data assimilation. Focuses on synthesizing fragmented data into a comprehensive target operational picture.

The English summary is being prepared. Showing the original description.

ProjectZeroDays/FreeAI_AI_Inference_Workstation5Updated Sep 4, 2026

Use when Codex needs proactive task queues, heartbeat routines, scheduled follow-up, or continuous work loops instead of waiting for prompts.

The English summary is being prepared. Showing the original description.

ProjectZeroDays/FreeAI_AI_Inference_Workstation5Updated Sep 4, 2026

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.

The English summary is being prepared. Showing the original description.

ProjectZeroDays/FreeAI_AI_Inference_Workstation5Updated Sep 4, 2026

See all skills by ProjectZeroDays

Report a problem with this skill