davidondrej/skills

1

goal-loop Explain and write effective instructions for the `/goal` feature — the persistent self-checking agent loop (plan → ac…

davidondrej/skills

257

2

handoff Compact the current conversation into a single, detailed handoff message — everything that happened, why it happened,…

davidondrej/skills

227

3

agent-self-scheduling Make an AI agent run on a schedule, loop, or interval — cron, heartbeats, recurring autonomous checks. Use for "run e…

davidondrej/skills

225

4

effective-agent-skills How to write effective agent skills — what to do, what not to do, anatomy, progressive disclosure, design patterns, a…

davidondrej/skills

222

5

brain-to-docs Use when the user wants to extract project vision, decisions, and preferences from their head into clear documentatio…

davidondrej/skills

218

6

short Manually-invoked skill that forces the agent to compress its current answer — strip filler, simplify wording, and cut…

davidondrej/skills

217

7

setup-help Walk the user through setting up anything step by step. Use when the user asks for help setting up, configuring, inst…

davidondrej/skills

208

8

anti-sleep Keep the user's MacBook awake reliably with macOS caffeinate for a set duration or while a process runs. Use for "don…

davidondrej/skills

206

9

folder-specific-claude-and-agents-md Create a specialized CLAUDE.md (+ AGENTS.md symlink) inside a specific folder to give future agents folder-scoped con…

davidondrej/skills

206

10

research-prompt Write a single-paragraph Deep Research prompt to hand to a human researcher (or a deep-research AI). Use when the use…

davidondrej/skills

206

11

youtube-transcript Use whenever the user needs the transcript of a YouTube video — fetching, extracting, downloading, or pulling caption…

davidondrej/skills

203

12

fable-safe-prompt Rewrite a user's prompt to reduce the chance it trips Claude Fable 5's server-side safety classifiers (cyber/bio guar…

davidondrej/skills

202

13

pi-web-search ONLY for Pi Agents — all other agents have their own web tools. How Pi accesses the web via the pi-web-access package…

davidondrej/skills

199

14

codex-subagent Launch OpenAI Codex CLI as a subagent (ChatGPT subscription auth, no API key). Use when delegating a self-contained c…

davidondrej/skills

197

15

online-shopping Research any online purchase with DeepAPI — fair-price checks, best deals, where to buy, shop trust, and VAT/tax savi…

davidondrej/skills

197

16

teach Teach the user a new skill or concept, within this workspace.

davidondrej/skills

196

17

global-agent-guardrails One shared denylist of catastrophic shell commands (rm -rf on / or ~, dd/mkfs, sudo rm, fork bombs, curl|sh, git push…

davidondrej/skills

195

18

read-all-adrs Read every ADR markdown file in the project's docs/adr/ folder so you have full context on past decisions. Use only w…

davidondrej/skills

194

19

cmux Control the cmux macOS terminal app (CLI + socket API) — cmux workspaces, panes, surfaces, browser automation, notifi…

davidondrej/skills

193

20

distribute-skill-to-all-agents Distribute a skill across the 4 agent skill folders (Codex, Claude Code, Pi, Hermes) so all agents see it. Use when t…

davidondrej/skills

193

21

level-up Gauge the user's technical + product knowledge through 7 adaptive questions, log verbatim answers with honest ratings…

davidondrej/skills

193

22

deepapi Use DeepAPI for all regular web searches (POST /v1/search/web) and for any deep research you perform (POST /v1/resear…

davidondrej/skills

190

23

browser-harness Direct browser control via CDP. Use when the user wants to automate, scrape, test, or interact with web pages. Connec…

davidondrej/skills

188

24

prompt-me Prompt the user with pointed questions to extract what is in his head about a project — remaining work, what is being…

davidondrej/skills

188

25

run-deep-swe Score any AI model on the DeepSWE coding-agent benchmark via the OpenRouter API. Use when the user wants an independe…

davidondrej/skills

186

26

pi-custom-model Register a custom or variant model (e.g. an OpenRouter ":nitro" / ":floor" / ":exacto" slug) in the Pi Agent so it ca…

davidondrej/skills

183

27

push-skill-to-github Commit and push agent-skill changes to the user's private skills GitHub repo (<private-skills-repo>, rooted at ~/.age…

davidondrej/skills

182

28

deep-research Run a deep, source-backed research query via DeepAPI (go to deepapi.co to get an API key) POST /v1/research/deep. Bui…

davidondrej/skills

174

29

google-safe-browsing Prevent and fix Google Safe Browsing "Dangerous site" flags. Use when launching a public web app, buying/picking a do…

davidondrej/skills

166

30

create-readonly-db-role Provision a hardened SELECT-only Postgres role so AI agents can safely read a production database. Works on Supabase …

davidondrej/skills

161

31

remind Rewrite the last response simpler and shorter in plain English, prefixed with a 3-5 sentence TLDR of the conversation…

davidondrej/skills

150

32

decisions Ask the agent to list all choices it made during the current work that it is not confident of. Manual-only; invoke wi…

davidondrej/skills

138

33

launch-subagent Read this BEFORE launching any subagent (Task tool, background agents, parallel agents, best-of-N, delegating work to…

davidondrej/skills

126

34

git-worktree Use git worktrees to run multiple coding agents in parallel on one repo without collisions. Use when starting a task …

davidondrej/skills

124

35

before-building Fire the moment the user proposes a build. Instantly surface the 1-3 consequential choices hidden in the user's idea.…

davidondrej/skills

116

36

cyber-audit Read-only exposure audit of the user's MacBook (and ~/Documents/code projects) for a CVE, breach, malicious package, …

davidondrej/skills

116

37

next-decision Drill open decisions one at a time — present the most important decision not yet clarified, give the top four choices…

davidondrej/skills

115

38

fireflies-transcript Pull raw meeting transcripts from the user's Fireflies.ai notetaker via its GraphQL API, using the key saved globally…

davidondrej/skills

109

39

gpt-review Launch a GPT 5.6 Sol Max reviewer as a bb thread (default: /nagent) to do a deep, neutral senior-developer review of …

davidondrej/skills

107

40

save-idea Quickly capture an idea from any repo or chat. Everything goes to the ~/code/ideas repo: video ideas to VIDEO-IDEAS.m…

davidondrej/skills

107

41

fable-review Launch a Fable 5 Max 1M reviewer as a bb thread (default: /nagent) to do a deep, neutral senior-developer review of t…

davidondrej/skills

104

42

herdr Operate and coordinate AI agents running inside Herdr in Ghostty. Use when the user says "Use the Herdr skill," menti…

davidondrej/skills

98

43

macbook-metrics-setup Replicate the macbook-metrics setup on any Mac — a local, always-on system-metrics collector (CPU, GPU, RAM, disk, ne…

davidondrej/skills

95

44

nuke-cursor-app End-to-end Cursor IDE restart on the user's MacBook: snapshot metrics, kill ALL Cursor processes, relaunch Cursor, re…

davidondrej/skills

95

45

ask-then-build Scope a feature, change, or refactor by asking the user 3-6 pointed questions ONE at a time (options A-D, state a pre…

davidondrej/skills

74

46

stop-overthinking Manually-invoked skill that stops overthinking and forces a short, practical decision. Use only when the user explici…

davidondrej/skills

71

47

corral-launch-agents Launch new CLI coding agents through Corral Design 1, or correctly reopen existing agent sessions inside a Corral-act…

davidondrej/skills

65

48

github-outside-sandbox Run Git and GitHub CLI commands through the host context when sandboxing blocks Keychain authentication, network acce…

davidondrej/skills

64

49

vps-server-management Use when the user wants to manage their VPS servers and the AI agents running inside them — connecting, deploying, mo…

davidondrej/skills

62

50

prod-push Push to GitHub main and babysit the change until it is verifiably live in production, fixing CI and deploy failures a…

davidondrej/skills

59