Loading...
Loading...
Found 1,766 Skills
Guided authoring of an architectural invariant catalog entry through a 6-step interview (elicit, locate, weight, enforce, number, commit). Drives the invariants_scaffold and invariants_add orchestrate verbs — the agent supplies judgment and natural-language elicitation; the verbs own schema validation, file writing, and event emission. Defaults to mode: audit; mode: check is an advanced opt-in. Triggers: 'add an invariant', 'author an invariant', 'enforce an architectural rule', or invariants. Do NOT use for: editing workflow state, running a review, or hand-writing YAML (the verbs write it — never emit catalog YAML yourself).
Use to attribute forecast vs actual deltas and recommend remediation actions.
Environment Variables Handler - Auto-activating skill for DevOps Basics. Triggers on: environment variables handler, environment variables handler Part of the DevOps Basics skill category.
Aria Attribute Helper - Auto-activating skill for Frontend Development. Triggers on: aria attribute helper, aria attribute helper Part of the Frontend Development skill category.
Define component variants and states systematically for Figma. Use when asked to plan component variants, define states for a component, set up a Figma variant matrix, or work out what properties a component needs before building it. Produces a complete variant matrix with all properties, values, and combinations needed.
AFK adversarial code-review loop: Cursor agent CLI critic (grug + thermo-nuclear) produces structured findings; Codex validator confirms or pushbacks on regression risk; parent adjudicates and commits fixes per finding until clean. Config at ~/.config/adversarial-review/config.toml. Use for adversarial review, clean code loop, or unattended branch hardening.
The point-of-view content type — articulate, sharpen, and argue a genuinely-held contrarian stance / hot take / opinion / thought-leadership position that builds authority and real debate. Use when someone wants a POV, a hot take, an "unpopular opinion", a contrarian angle, an opinion piece, or to stop sounding like everyone else and build thought leadership. Uses the STAND framework. Reads brand-profile + voice-builder first. The agent argues the human's OWN opinion with evidence; the human owns the stance and the live debate; WoopSocial publishes. Never manufactures a stance, controversy, or ragebait; no strawmen, punching down, or defamation; opinion stays clearly opinion and factual claims must be true. Distinct from hook-writer (the opening-line mechanic this feeds), educational-content-and-how-to (teaches a process), storytelling-and-narrative (narrative vs argument), and behind-the-scenes-and-founder (personal story vs argued position).
Use when you have implemented an equivariant model and need to verify it correctly respects the intended symmetries. Invoke when user mentions testing model equivariance, debugging symmetry bugs, verifying implementation correctness, checking if model is actually equivariant, or diagnosing why equivariant model isn't working. Provides verification tests and debugging guidance.
Multi-repository codebase exploration for library internals, architecture understanding, and implementation comparisons.
Parent-child variation planning — when to merge/split, color/size variations, ranking benefits
Revisa de forma adversarial un Technical Design Document y sus ADRs, buscando activamente huecos, riesgos y decisiones débiles en vez de validarlos. Use when the user asks to challenge, stress-test, get a second opinion on, or adversarially review a technical design document, architecture decisions, or ADRs.
Adversarial code review that breaks the self-review monoculture. Use when you want a genuinely critical review of recent changes, before merging a PR, or when you suspect Claude is being too agreeable about code quality. Forces perspective shifts through hostile reviewer personas that catch blind spots the author's mental model shares with the reviewer.