Loading...
Loading...
Found 59 Skills
React to the user's Telegram message with an emoji. Use when the message evokes a genuine emotional response.
Log genuine, recurring repository friction to .agents/PAPERCUTS.md — confusing setup, a flaky repo command or script, a misleading in-repo error, stale generated files, or a non-obvious gotcha that will cost the next contributor time. Also use to review, deduplicate, and resolve existing entries. Gate hard before logging: only friction the repository itself can fix counts. Never log the agent's own sandbox/permission errors, shell-scripting mistakes, transient flakiness, or third-party tool quirks the repo can't change.
Make dense or complex information easier to understand, navigate, remember, and act on through clear layers, concrete examples, and visible progress. Use when the user explicitly invokes Focus Friendly; requests focus-oriented simplification, chunking, pacing, mapping, or reorientation; reports overwhelm, trouble reading or focusing, task-initiation difficulty, or losing their place in the current task; asks whether those difficulties prove ADHD; or asks for help navigating long, structurally complex material that genuinely needs a map. Do not invoke merely because a request mentions ADHD or asks for summarization, teaching, planning, research, or routine coding; those tasks need an explicit focus or navigation signal.
Facilitates the final step of a proven ideal-customer (ICP) method: synthesizing the working files — strengths and weaknesses, honed keystones, deal-breakers, and inciting events — into CAROL.md, the crisp definition of the ideal customer. The definition leads the file, behavioral and attitudinal, never demographic unless genuinely determinative; every marker must clear the bar that Marketing can target it, Sales can qualify against it, and Product can build features to thrill it. Brief reference sections on keystones, deal-breakers, and inciting events follow, because positioning, marketing, and feature work consume them. When keystone segments diverge, the skill forces the choice of a primary rather than averaging. Load when the user has the working files and says 'define our Carol,' 'write our ideal customer profile,' or 'who is our ICP.' Do NOT load to produce the upstream files (observations through inciting events), or to write the positioning, ads, or feature plans that start FROM this definition.
Answers "which of these?" rather than "is this right?". Builds several genuinely different versions of one piece of UI behind a picker in the real page, so you can flip between them and promote the one that wins.
Detect whether an API endpoint is backed by genuine Claude (not a wrapper, proxy, or impersonator) using 9 weighted rule-based checks that mirror the claude-verify project. Also extracts injected system prompts from providers that override Claude's identity. Fully self-contained — copy the code below and run, no extra packages beyond httpx. Use when the user wants to verify a Claude API key or endpoint, check if a third-party Claude service is authentic, audit API providers for Claude authenticity, test multiple models in parallel, or discover what system prompt a provider has injected.
Focused Signals scout for PostHog setup health. Reads the project's active health issues — the deterministic findings of PostHog's own health checks (no live events, outdated SDKs, missing reverse proxy, absent web vitals, ingestion warnings, failing data-warehouse models, and more) — and decides which are genuinely worth surfacing. Unlike a one-signal-per-issue push, it bundles kind-clusters into a single finding, weights by real blast radius (cross-referencing actual event volume and reach), and prioritizes issues an agent can resolve via the MCP. Emits only above the confidence bar; otherwise writes durable memory and closes out empty. Self-contained peer in the signals-scout-* fleet — no dependencies on other skills.
Use to write a TikTok script — a native, sound-aware short-video script optimized for TikTok's discovery engine (the FYP), built around a brutal 1-second hook, watch-time, and rewatches. Run when the user says "TikTok script," "TikTok video," "script for TikTok," "make a TikTok," "storytime," "TikTok hook," or wants short-form video for TikTok specifically. Reads brand-profile and voice first; rides a trending sound/format where it genuinely fits (live trend research goes to trend-jacking); structures for completion + rewatch; optimizes for TikTok search; outputs a production doc (shot - on-screen text - spoken - sound - timing) plus a Veo prompt pack for faceless/b-roll shots (native filming often beats AI on TikTok). For Instagram Reels use reels-script; for YouTube Shorts use youtube-shorts; for the platform-agnostic scripting craft use short-form-video-script; hands caption to caption-writer and scheduling to scheduling-and-queue.
Under genuine uncertainty with no reliable forecast, inventory means, cap downside at affordable loss, act for commitments, and let goals emerge from controllable moves.
Choose light, dark, or combined color mode deliberately based on brand tone and user context. Offer a theme selector only when user control genuinely matters — enterprise tools, data-heavy UIs, or extended-use applications. Use when defining the base color palette, designing a design system, or deciding whether to build dark mode support.
Use this skill when designing onboarding, when diagnosing why users keep getting confused, when migrating users from one product convention to another, or when the system genuinely differs from familiar comparable products. Trigger when the user mentions "users don't get it," "we keep getting the same support tickets," or "this is a new pattern they need to learn." Sub-aspect of `mental-model`; read that first.