Loading...
Loading...
Found 9,705 Skills
This skill should be used when the user asks to "write a creative brief", "build a motion brief", "the client doesn't know what they want", "turn this vague client request into a brief", "what questions should I ask the client", or "make a brief I can get sign-off on". It turns a fuzzy client ask into a structured, sign-off-ready motion design brief and the exact clarifying questions to send back.
Use when a developer wants to iterate on ONE specific Agent Observability / LLM Obs trace whose output they didn't like — re-running that trace against their LOCAL code, seeing a concise diff of the old vs new output, and looping (change code → replay → diff) until satisfied. Invoked as /agent-observability-replay-trace <trace-id> [changes to test]. Signals: "replay this trace"; "iterate on a trace"; "this trace's output is wrong, fix it and re-run"; "re-run trace <id> with <change>"; pasting a trace id from the Agent Observability UI with a description of what to fix. It fetches the trace via the datadog-llmo MCP or the pup CLI, edits code, re-runs the app to emit a NEW trace, and diffs the two — no local server, no browser. For agents traced with ddtrace / LLM Obs (Python first-class), with JSON-serializable entry input. Do NOT use for: scored Experiments or the browser "Replay" button (that's agent-observability-replay-experiment), building an experiment from a dataset/CSV, writing evaluators, root-causing failed traces, or RUM/HTTP session replay.
Local vision CLIs: glance (describe/ask/OCR an image), ground (locate a target, pixel box), detect (element inventory), trace (image to SVG geometry), crop (cut a pixel box to a file), and scripts/html_shot.py (HTML file to image). Use for any task involving an image — questions, text, splitting and transcribing long screenshots or chat histories, locating elements, comparing, rebuilding as HTML/SVG, digitizing a sketch or diagram, reading values off a chart, operating a GUI from screenshots — and to re-check an image yourself when a description you were given lacks a detail.
Scaffolds a headless agent in TypeScript using @openrouter/agent and Bun — for CLI tools, API servers, queue workers, and pipelines. No terminal UI. Use when building a headless agent, programmatic agent, CLI tool that uses AI, batch agent, pipeline agent, API agent, agent without a UI, or agent service.
Generate 6 clickbait-style LinkedIn hook variations for any topic. Two-line hooks built on the formula: a 40-char opening line, a 40-char bold contrast line. Includes digits, "How I" or "I" statements, and metrics. Use this skill whenever the user says "write me hooks", "hook ideas", "generate hooks", "I need a hook for a post about...", or pastes a topic and asks for openers. Fast output, no preamble.
Read, write, and validate Kanonak Protocol ontologies (.kan.yml files). Covers the document format, separating schema (classes and properties) from data (instances) into their own packages, the publisher/package@version/name URI scheme and how it maps to fetchable URLs, installing and driving the kanonak CLI, and where the canonical modeling and styling guides live. Use when working with .kan.yml files, authoring or reviewing a Kanonak ontology or its instance data, resolving Kanonak package imports or versions, running the kanonak CLI, publishing a Kanonak package, or styling one with the look system.
Retrieve recent local Clips Rewind context when the user says "Look at Rewind," asks what just happened, or refers to something they recently said or saw.
Track case deadlines — add, cross-case rollup report, update, complete, close. Warns at configurable thresholds (default 14/7/3/1 days); overdue items stay flagged until resolved. The operational record for a clinic workload. Use when a student or supervisor needs to add a deadline, ask what's due this week, get a deadline report, or update a case deadline.
Mechanics library for running AI coding CLIs as managed tmux workers via agent-tmux <cli> <command> (plus tmux-agent-sessions and the other bundled tools). Entry point is the using-tmux-agent-tools router skill — route through it first; read this skill for wrapper mechanics it defers to. Covers start/send-wait/status/result/stop, structured result.json completion, multi-worker watch, profiles for custom CLIs, and bounded dialogue/fanout. Not for general tmux config, theming, non-tmux headless CLI use, or human team debate.
Request cross-AI peer review of phase plans from external AI CLIs
Guide developers through creating a Slack app or agent using the Slack CLI and Bolt (JS or Python). Handles prerequisites, sandbox setup, authentication, project creation from templates, and local development.
Design or audit a model-agnostic evaluation harness for an LLM or multimodal LLM on a clinical task (radiology report generation, visual question answering, clinical text extraction/classification) — the adjudicated reference standard, clinical-efficacy metrics (RadGraph-F1 / CheXbert-F1 beyond BLEU/ROUGE), faithfulness and hallucination, pretraining-contamination of public benchmarks, prompt-sensitivity and determinism, answer-matching, and a reader study — and gate the plan for those axes. Works on a closed API or open weights. Never fabricates outputs or scores, and never reports n-gram overlap as clinical correctness.