Loading...
Loading...
Found 1,279 Skills
Emergency Triage and Symptom Screening Assistant. This skill is triggered when users describe physical discomfort, pain, sudden symptoms, or ask urgent/semi-urgent health-related questions such as "Where do I hurt?", "I feel unwell", "Which department should I register for?", "Do I need to go to the hospital?", or "Help me judge". It also applies to scenarios where users conduct preliminary symptom screening for family or friends. Core capabilities: Quickly narrow down the range of possible causes through hypothesis-elimination interactive consultation, provide a ranking of possible causes, suggestions for registration departments, and examination items to be done after arriving at the hospital. Help users prepare information before seeing a doctor and reduce communication costs in the hospital.
Package and build custom AI models with Cog for deployment on Replicate. Use when creating a cog.yaml or predict.py, defining model inputs and outputs, loading model weights at setup time, building Docker images for ML models, serving locally with cog serve or cog predict, or porting a HuggingFace, GitHub, or ComfyUI model to run on Replicate. Trigger on phrases like "build a model", "package a model", "create a Cog model", "wrap a model", "containerize an AI model", "predict.py", "cog.yaml", "BasePredictor", or "Cog container", and when referencing cog.run, github.com/replicate/cog, or github.com/replicate/cog-examples. Covers GPU and CUDA setup, pget for fast weight downloads, async predictors with continuous batching, streaming outputs, and cold-boot optimization for image, video, audio, and LLM models. For pushing built models to Replicate, see publish-models. For running existing models, see run-models.
Access Slack through the global `slack` CLI for read-only workflows. Use when asked to list chats or DMs, read message history, inspect threads, fetch exact messages, or summarize recent Slack activity.
Add a single functional spec to the ***functional specs*** section of a ***plain spec file. Use whenever exactly one new functional spec is being added — whether the user explicitly asks, or another skill/workflow (e.g. forge-plain, add-feature) needs to author a new functional spec. Every new entry under ***functional specs*** must go through either this skill or `add-functional-specs` (the bulk variant for adding multiple specs in one pass); hand-authoring functional specs without invoking one of these skills is forbidden.
Design and operate data quality programs for financial data — golden source architecture, validation rules, data lineage, exception management, profiling, and governance. Use when building validation rules for pricing or client data pipelines, designing a data quality monitoring framework, establishing golden source designations across systems, implementing data lineage for BCBS 239 or MiFID II, investigating reconciliation breaks or billing errors traced to bad data, preparing for regulatory exams on data accuracy, building data quality scorecards, or defining data stewardship roles. Trigger on: data quality, golden source, data lineage, data validation, data profiling, exception management, data governance, BCBS 239, data completeness, data accuracy, validation rules, data anomaly, data stewardship, data quality scorecard.
Drive a remote chrome-devtools-mcp server (typically on a tailnet) over HTTPS using the chrome-devtools CLI. Use this when the user wants to navigate, screenshot, inspect, or evaluate JavaScript on a browser running on another host (e.g. a Tailscale-connected Mac mini or a CI runner) — and you don't have a local Chrome to control. Examples of triggers ("open <url> on the lab mac", "take a screenshot of the browser on host X", "evaluate this on the remote browser").
Backseat gaming mode for coding — you can see exactly what's wrong and tell the user precisely what to do, but you never touch the code yourself. The user implements everything. Persistent, no exit. Activate with /backseat. Use when the user says /backseat, "coach me but don't code for me", "guide me while I implement", or wants to do the coding themselves with guidance.
Audit a live page for accessibility issues and locate each violation precisely — optionally pass a URL (e.g. `accesslint:scan https://example.com/dashboard`), otherwise ask for one. Ensures a debuggable Chrome, runs the @accesslint/core engine via CDP, and returns a worklist of live-DOM WCAG violations grounded to each violation's DOM selector and source file:line. Locates; doesn't edit — output drives fixes by Claude. Use it for "is this page accessible", or to verify a UI change. For diffing against uncommitted changes or a branch, use the `diff` skill.
Anonymize and sanitize customer-provided log files before they are committed as pipeline test fixtures or sample events. Performs a line-by-line review and replaces all sensitive values inline, preserving log structure and format exactly — never reformats, re-indents, or restructures content. Invoke manually with /anonymize-logs.
Given event_candidates YAML (output from discover-event-surfaces), generates a concrete instrumentation plan for priority-3 (critical) events. Acts as a Software Architect: discovers existing analytics patterns in the codebase, reads the hinted files to determine what variables are in scope, designs minimal chart-useful properties, and identifies the exact insertion point for each tracking call. Outputs a structured JSON trackingPlan. Use this as step 3 of the analytics instrumentation workflow, after discover-event-surfaces. Trigger whenever a user has event_candidates and wants to generate tracking code, asks "instrument these events", "generate tracking plan", "add analytics for these events", "where should I put the tracking calls", or any request to turn event candidates into concrete implementation guidance.
Use when you need to print Jetson BSP info (L4T version, board configs, rootfs state) from a Linux_for_Tegra root on the host PC. This is an example skill.
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.