Loading...
Loading...
Found 2,026 Skills
Transcribe a media file or live microphone to text or subtitles with auto-editor's whisper subcommand, then edit by spoken content — cut to keep (or drop) sections whose subtitles match a word or regex. Use when someone wants a transcript, captions, live speech transcription, or to cut a video based on what is said rather than on loudness.
Builds the search/list page in up-app loading all records via the entity service. Supports flexible capabilities: search (list), edit, and optionally delete. Use when the user asks for Day 2 step 4 of the CRUD drill, or asks to build the search/list page for up-app. Features are based on capabilities selected in d2-03.
Builds the create/update form page in up-app using ReactiveFormsModule with FormGroup/FormControl validation. Supports flexible capabilities: create (new records) and save (update records). Redeploys after changes. Use when the user asks for Day 2 step 5 of the CRUD drill, or asks to build the add/edit form page for up-app. Features are based on capabilities selected in d2-03.
Creates a main menu/navigation hub component with dynamically generated menu items based on selected capabilities (search, create, save, delete). Prompts for entity name and available actions, generates menu card and routes. Use when the user asks for Day 2 step 3 of the CRUD drill, or asks to build a main menu for up-app.
Protocol analysis skill for serial bus debugging. Use when decoding I2C/SPI/UART with logic analyzer concepts, sigrok/PulseView, or Python capture scripts. Activates on queries about logic analyzer, sigrok, PulseView, decode I2C SPI UART, or bus protocol capture.
Apply factor models to portfolio construction and fund evaluation, from CAPM through the Fama-French 3- and 5-factor models plus momentum. Use when the user asks about 'Fama-French', 'value factor', 'smart beta', 'factor tilt', 'momentum exposure', or the 'factor zoo', wants to run or interpret a factor regression (loadings, alpha after controlling for factors, R-squared, t-stats), decompose a manager's returns into factor exposures versus skill, or asks 'is my fund closet indexing'. Also trigger on SMB, HML, RMW, CMA, UMD, size/value/quality/profitability/low-vol premia, factor ETF or smart-beta product evaluation (factor purity, turnover, capacity, fees), factor cyclicality and the danger of factor timing, factor crowding, long-short academic factors versus long-only implementable tilts, and post-publication factor decay.
Hardens Dockerfiles, images, and per-container runtime settings against the CIS Docker Benchmark v1.8.0: non-root users, dropped capabilities, read-only root filesystem, seccomp and AppArmor profiles, and minimal multi-stage builds, validated with docker-bench-security, Hadolint, and Dockle. Use when preparing a container or Dockerfile for production, or auditing images and runtime flags against CIS Docker controls. Keywords: Dockerfile, USER, --cap-drop, read-only rootfs, seccomp, AppArmor, multi-stage, Hadolint, Dockle. Do not use for the Docker daemon's own configuration - use hardening-docker-daemon-configuration.
Detect and analyze covert communication channels used by malware, including DNS tunneling, ICMP exfiltration, steganographic HTTP, and other protocol abuse used for C2 and data exfiltration. Use when investigating suspicious DNS/ICMP/HTTP traffic patterns, hunting for hidden C2 channels in network captures, or attributing exfiltration traffic to a known tunneling toolset.
Keep the vault true. Two jobs in one skill: capture (fold anything from the inbox or a finished run into the right wiki pages) and health-check (hunt contradictions, stale claims, orphan pages, and propose pruning). Run when the user says "file this", "add this to the vault", "process the inbox", "clean up the vault", "health-check my notes", or when bank, research, or recall hand something over for filing. A vault nobody maintains becomes a graveyard nobody trusts.
Design the offer, price it, close it: tiers, caps, guarantees, anchors, launch timing, with operator-grade heuristics applied to the founder's real numbers. Run when the user says "price this", "design my offer", "how should I structure the price we've chosen", "build the tier structure", "add a guarantee?", "how do I launch the paid thing", or asks HOW to execute an approved pricing/packaging/monetization decision. "Should we change price?" belongs to the gauntlet. Generic pricing frameworks recalled from memory are not advice; this skill applies tested mechanics to THEIR business.
Ensure textures and decals cover all visible surfaces of a closed or extruded Blender asset, especially front/back caps and sidewalls, instead of relying on partial projected planes, curves, or linework overlays. Use when back textures do not fill the model, side textures are missing, spin/turntable views expose plain sidewalls, or a model needs separate UV treatment for caps and side surfaces.
Extract, reproduce, and locally replay a single WebGL / WebGPU / Canvas / shader / animated-3D visual effect from a web page — the GPU-rendered surface that DOM/CSS cloning is blind to. Use whenever a page has a WebGL/WebGPU/canvas shader background, animated 3D hero, generative gradient, particle field, or Unicorn Studio / Spline / Three.js effect that must be captured and rebuilt as a runnable local module. This is the GPU track of a site clone (driven by clone-site) but also stands alone. Trigger on "extract this shader", "clone the WebGL background", "port this canvas effect", "rebuild this animated hero", "reproduce this Three.js scene locally". NOT for ordinary DOM/CSS cloning (use dom-clone).