incident-triage
Triage an incident or outage from evidence: timeline, ranked causes, mitigations, one note. Read-only; never touches production. A known staging bug is…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-07 00:13
General & other
53,646 results
caveman
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite,…
agile-pen
Create and maintain traceable application prototypes exclusively in Pen.dev with auditable prototype-to-code mapping, deterministic official or community…
figure-out
Figure things out together — any topic, problem, or idea. Presses relentlessly until shared understanding is reached. Use when understanding is the deliverable…
compact-chat-history
Summarize and compress the current conversation history into a structured context snapshot, then call compact_chat_history to save it. Read this skill only…
surge-manager
Surge configuration management skill, supporting operations such as rule addition, configuration editing, and Tailscale device management
estimate-proposal
Only use when the user explicitly invokes /estimate-proposal (or $estimate-proposal in Codex). Never auto-invoke.…
exposure-risk-quantification
FAIR-aligned exposure quantification: turns a pile of recon findings into a defensible 0-100 + A-F org risk score (Likelihood x Impact, three ownership-aware…
voice-mode
The voice-mode skill owns the conversation’s delivery and interaction behavior when the user needs to listen instead of look at a display. It triggers on…
modern-javascript-patterns
Master ES6+ features including async/await, destructuring, spread operators, arrow functions, promises, modules, iterators, generators, and functional…
monorepo-management
Master monorepo management with Turborepo, Nx, and pnpm workspaces to build efficient, scalable multi-package repositories with optimized builds and dependency…
good-readme
Write or improve a README.md for an open source project. Use this for any request to create, rewrite, review, or polish a README, project description, or…
simplify
This skill should be used when the user asks to "simplify", "clean up the diff", "run simplify", "simplify the changes", "review changed code for cleanup",…
icp-definition
Use when a PMM needs to define, sharpen, or validate their Ideal Customer Profile. Trigger on: 'who is our ICP', 'define our target audience', 'ICP too broad',…
launch-brief
Use when a PMM needs to turn a product spec, feature release, or initiative into a full go-to-market launch plan. Trigger on: 'launch brief', 'launch plan',…
talk-stage4-position
Generates 3-4 strategic talk angles with strength/weakness analysis, title options, CFP descriptions, and a peer feedback draft, then enforces a mandatory…
bump-dart
Do not trigger automatically; only run when a user runs /bump-dart. Bump the minimum Dart SDK version constraint across the flutter/flutter repository, update…
cardano-cli-transactions-operator
Execute transaction builds and submits. Manual invoke only—requires explicit confirmation before submit.
map-user-flow
Map an in-product flow across screens, decisions, transitions, native platform surfaces, and recovery states. Use for a feature or user journey that spans…
plan-funnel
Models business funnels with numeric targets — works backward from a revenue goal to the required traffic, conversion rates, and unit economics, with every…
portal
Choose the next skill and ticket from the tracker and current branch. Use for /portal, what next, route this issue, pick up where I left off, portal run, or…
astrill-control
Control Astrill VPN on macOS through its menu-bar GUI: status (app / tunnel / GUI menu / exit IP), connect, disconnect — all idempotent, verified by dual…
tui-uni-modules-setting
Generate pixel-precise ASCII TUI for Uni Modules Setting (u-uni-modules-setting) with strict output blocks (TUI_RENDER, COMPONENT_SPEC, PENCIL_SPEC,…
learning-assessor
Provides comprehensive guidance for learning assessment including assessment creation, evaluation methods, and assessment best practices. Use when the user…