5,044,813 AI resources indexedWorking toward the world’s largest AI resource index.

DaveAI
Browse resources 12 sections

Agent skills

Reusable instructions for compatible AI agents.

How to use the library

Explore by field

Loading catalog totals…
Browse full catalog

Field counts come from the latest full-catalog snapshot. A resource can belong to several fields and platforms.

Resources

Search results
Search stays within agent skills.
Agent skill

Analysis Design

Systematic analysis and reasoning workflows. Use when performing audits, investigation, requirements analysis, risk analysis, scenario/edge-case enumeration, or design analysis that demands evidence-based, comprehensive coverage.

OpenClawData & Analytics
David-Li04060
Apache-2.0View resource
Agent skill

Code Quality

Code quality and safety standards. Activates when editing or reviewing code. Use for quality priorities, safety checks, and code correctness verification.

ClaudeCodexOpenClawDevelopment & Engineering
David-Li04060
Apache-2.0View resource
Agent skill

Coding Orchestrator

Use when performing coding tasks (implement features, fix bugs, refactor code). Orchestrates language detection, mode switching (normal/autopilot/full-auto), quality enforcement, and verification.

OpenClawDevelopment & Engineering
David-Li04060
Apache-2.0View resource
Agent skill

Heredoc File Write Workaround

Use shell heredoc syntax as a workaround when write_file fails on complex TypeScript/JSX/code files with encoding or escaping issues

OpenClawDevelopment & Engineering
AG0640
MITView resource
Agent skill

terminal-tools — foundations

Required reading whenever any shell_* tool is available. Teaches the foreground/background dichotomy (terminal_exec auto-promotes past 30s, returns a job_id you poll with terminal_job_logs), the standard envelope shape (exit_code, stdout, stdout_truncated_bytes, output_handle, semantic_status, wa...

OpenClawDevelopment & Engineering
aden-hive11,142
MITView resource
Agent skill

Safe Exec

Protect against prompt injection from shell command output. Wrap untrusted commands (curl, API calls, reading user-generated files) with UUID-based security boundaries. Use when executing commands that return external/untrusted data that could contain prompt injection attacks.

OpenClawDevelopment & Engineering
kbarbel640-del1
MITView resource

Platform labels describe intended use. Read each resource's author credits, requirements and available access methods.