asgeirtj
UserExtracted system prompts from Anthropic - Claude Fable 5, Opus 4.8, Claude Code, Claude Design. OpenAI - ChatGPT 5.5 Thinking, GPT 5.5 Instant, Codex. Google - Gemini 3.5 Flash, 3.1 Pro, Antigravity. xAI - Grok, Cursor, Copilot, VS Code, Perplexity, and more. Updated regularly.
Categories
Indexed Skills (16)
claude-api
Build, debug, and optimize Claude API / Anthropic SDK apps. Apps built with this skill should include prompt caching. Also handles migrating existing Claude API code between Claude model versions.
loop
Run a prompt or slash command on a recurring interval. Omit the interval to let the model self-pace.
schedule
Create, update, list, or run scheduled remote agents (routines) that execute on a cron schedule.
deep-research
Deep research harness — fan-out web searches, fetch sources, adversarially verify claims, synthesize a cited report.
batch
Orchestrate a large, parallelizable change across the codebase by decomposing it into independent units and spawning parallel worker agents in isolated worktrees.
code-review
Review the current diff for correctness bugs and reuse/simplification/efficiency cleanups at the given effort level.
fewer-permission-prompts
Scan your transcripts for common read-only Bash and MCP tool calls, then add a prioritized allowlist to project .claude/settings.json to reduce permission prompts.
init
Initialize a new CLAUDE.md file with codebase documentation.
keybindings-help
Customize keyboard shortcuts, rebind keys, add chord bindings, or modify ~/.claude/keybindings.json.
review
Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/PRD asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".
run-skill-generator
Teach /run and /verify how to build and launch your project by creating a per-project run skill with a driver script.
run
Launch and drive this project's app to see a change working.
security-review
Complete a security review of the pending changes on the current branch.
simplify
Review the changed code for reuse, simplification, efficiency, and altitude cleanups, then apply the fixes.
verify
Verify that a code change actually does what it's supposed to by running the app and observing behavior.
debug
Debug an issue in the current Claude Code session by enabling debug logging, reading logs, and suggesting fixes.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.