asgeirtj/system_prompts_leaks
Documented system prompts from Anthropic - Claude Fable 5.1, Opus 5.5, Claude Design, Claude Code. OpenAI - ChatGPT GPT-6-Astra, Codex. Google - Gemini 3.8 Flash, 3.1 Pro, Antigravity. xAI - Grok, Grok Bot, Cursor, Kimi and more! Updated re
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
Copy this rig
$ git clone --depth 1 https://github.com/asgeirtj/system_prompts_leaks MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ npx degit asgeirtj/system_prompts_leaks/Anthropic/claude-code/skills/artifact-capabilities .claude/skills/artifact-capabilities $ npx degit asgeirtj/system_prompts_leaks/Anthropic/claude-code/skills/artifact-design .claude/skills/artifact-design $ npx degit asgeirtj/system_prompts_leaks/Anthropic/claude-code/skills/artifact-diagramming .claude/skills/artifact-diagramming $ npx degit asgeirtj/system_prompts_leaks/Anthropic/claude-code/skills/batch .claude/skills/batch $ npx degit asgeirtj/system_prompts_leaks/Anthropic/claude-code/skills/claude-api .claude/skills/claude-api $ npx degit asgeirtj/system_prompts_leaks/Anthropic/claude-code/skills/claude-in-chrome .claude/skills/claude-in-chrome $ npx degit asgeirtj/system_prompts_leaks/Anthropic/claude-code/skills/code-review .claude/skills/code-review $ npx degit asgeirtj/system_prompts_leaks/Anthropic/claude-code/skills/consolidate-memory .claude/skills/consolidate-memory $ npx degit asgeirtj/system_prompts_leaks/Anthropic/claude-code/skills/dataviz .claude/skills/dataviz $ npx degit asgeirtj/system_prompts_leaks/Anthropic/claude-code/skills/debug .claude/skills/debug $ npx degit asgeirtj/system_prompts_leaks/Anthropic/claude-code/skills/deep-research .claude/skills/deep-research $ npx degit asgeirtj/system_prompts_leaks/Anthropic/claude-code/skills/design-sync .claude/skills/design-sync $ npx degit asgeirtj/system_prompts_leaks/Anthropic/claude-code/skills/design .claude/skills/design $ npx degit asgeirtj/system_prompts_leaks/Anthropic/claude-code/skills/docs .claude/skills/docs $ npx degit asgeirtj/system_prompts_leaks/Anthropic/claude-code/skills/doctor .claude/skills/doctor $ npx degit asgeirtj/system_prompts_leaks/Anthropic/claude-code/skills/docx .claude/skills/docx $ npx degit asgeirtj/system_prompts_leaks/Anthropic/claude-code/skills/explain-usage .claude/skills/explain-usage $ npx degit asgeirtj/system_prompts_leaks/Anthropic/claude-code/skills/fewer-permission-prompts .claude/skills/fewer-permission-prompts $ npx degit asgeirtj/system_prompts_leaks/Anthropic/claude-code/skills/google-workspace .claude/skills/google-workspace $ npx degit asgeirtj/system_prompts_leaks/Anthropic/claude-code/skills/import-memory .claude/skills/import-memory $ npx degit asgeirtj/system_prompts_leaks/Anthropic/claude-code/skills/init-new .claude/skills/init-new $ npx degit asgeirtj/system_prompts_leaks/Anthropic/claude-code/skills/init .claude/skills/init $ npx degit asgeirtj/system_prompts_leaks/Anthropic/claude-code/skills/keybindings-help .claude/skills/keybindings-help $ npx degit asgeirtj/system_prompts_leaks/Anthropic/claude-code/skills/loop .claude/skills/loop $ npx degit asgeirtj/system_prompts_leaks/Anthropic/claude-code/skills/morning .claude/skills/morning $ npx degit asgeirtj/system_prompts_leaks/Anthropic/claude-code/skills/pdf .claude/skills/pdf $ npx degit asgeirtj/system_prompts_leaks/Anthropic/claude-code/skills/plugin-authoring .claude/skills/plugin-authoring $ npx degit asgeirtj/system_prompts_leaks/Anthropic/claude-code/skills/pptx .claude/skills/pptx $ npx degit asgeirtj/system_prompts_leaks/Anthropic/claude-code/skills/run-skill-generator .claude/skills/run-skill-generator $ npx degit asgeirtj/system_prompts_leaks/Anthropic/claude-code/skills/run .claude/skills/run $ npx degit asgeirtj/system_prompts_leaks/Anthropic/claude-code/skills/schedule .claude/skills/schedule $ npx degit asgeirtj/system_prompts_leaks/Anthropic/claude-code/skills/security-review .claude/skills/security-review $ npx degit asgeirtj/system_prompts_leaks/Anthropic/claude-code/skills/session-start-hook .claude/skills/session-start-hook $ npx degit asgeirtj/system_prompts_leaks/Anthropic/claude-code/skills/setup-claude .claude/skills/setup-claude $ npx degit asgeirtj/system_prompts_leaks/Anthropic/claude-code/skills/simplify .claude/skills/simplify $ npx degit asgeirtj/system_prompts_leaks/Anthropic/claude-code/skills/skill-creator .claude/skills/skill-creator $ npx degit asgeirtj/system_prompts_leaks/Anthropic/claude-code/skills/update-config .claude/skills/update-config $ npx degit asgeirtj/system_prompts_leaks/Anthropic/claude-code/skills/verify .claude/skills/verify $ npx degit asgeirtj/system_prompts_leaks/Anthropic/claude-code/skills/workflow-authoring .claude/skills/workflow-authoring $ npx degit asgeirtj/system_prompts_leaks/Anthropic/claude-code/skills/xlsx .claude/skills/xlsx
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(rm -rf *)",
"Read(**/*.pem)",
"Bash(rm -rf /)",
"Bash(git push --force:*)",
"Bash(sudo *)",
"Read(.env)",
"Bash(rm -rf /*)",
"Read(./.env.*)",
"Read(~/.aws/**)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(sudo:*)",
"Bash(git reset --hard*)",
"Bash(git reset --hard:*)",
"Read(.env.*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(rm:*)",
"Bash(git rebase *)",
"Bash(wget *)",
"Bash(npm publish:*)",
"Bash(git commit *)",
"Bash(gh pr merge *)"
]
}
} Skills (148)
artifact-capabilitiesartifact-designartifact-diagrammingbatchclaude-apiclaude-in-chromecode-reviewconsolidate-memorydatavizdebugdeep-researchdesign-syncdesigndocsdoctordocxexplain-usagefewer-permission-promptsgoogle-workspaceimport-memoryinitinitkeybindings-helploopmorningpdfplugin-authoringpptxrun-skill-generatorrunschedulesecurity-reviewsession-start-hooksetup-claudesimplifyskill-creatorupdate-configverifyworkflow-authoringxlsx3d-objectanimated-videoclaude-api-in-prototypescreate-design-systemexport-as-pptx-editableexport-as-pptx-screenshotsflierfrontend-designhandoff-to-claude-codehi-fi-designhtml-emailinteractive-prototypemake-a-deckmake-a-docmake-tweakablemaps-geographyoptionssave-as-pdfsave-as-standalone-htmlweb-researchwireframeapple_healthkitasanabookingboxcalendlycanvadevice_datadropboxduffelevernotefacebook_clifacebookfigmaflightawareforgetfunction_healthgenerate_podcastghlgithubgmailgoalsgoogle-calendargoogle-contactsgoogle-docsgoogle-drivegoogle-formsgoogle-health-connectgoogle-sheetsgoogle-slidesgoogle-tasksgranolahealtheximage-searchinstagram-messagesinstagramklaviyolinearlovablemagic-momentmedia-librarymessengermeta-adsmeta-threadsmuse-early-accessmuse-feedbackmuse_dbnotionopentableoutlook-calendaroutlook-contactsoutlook-mailpelotonphilips-hueplaces-searchplaidpodcastprintifyquickbooksreplitself-awarenessshare-ideasshopifyshoppingslacksocial-content-performancespotifystripesubscription-statustailscaletessiethreads-messagesthreadsticketmastertodoisttravel-planningttsvercelvoice-callsvoice-designvoice-selectorwearable-device-skillswearables-commswide-researchwithingszapierzoomthreejs
Similar rigs
AceDataCloud/Skills
Agent Skills for AceDataCloud AI services — music, image, video generation, web search, and more. Compatible with Claude Code, GitHub Copilot, Gemini CLI, and all agentskills.io-compatible agents.
Skill Collector 6.5k tok ·
protoLabsAI/protoAgent
Local-first agent that drives Claude Code and Codex over ACP. Desktop app, git-URL plugins, A2A 1.0. MIT.
Skill Collector 2.3k tok ·
HybridAIOne/hybridclaw
Enterprise-ready self-hosted AI assistant runtime with sandboxed execution, secure credentials, approvals, and memory
Skill Collector 13.4k tok ·
anthropics/skills
Public repository for Agent Skills
Skill Collector 1.3k tok ·