AGENT SKILLS · ÉQUIPEMENT DE MISSION
Des Agent Skills utiles classés selon leur usage réel
Comparez les Skills vérifiés par fonction, contenu, installations et fiabilité de la source avant de les ajouter.
- PÉRIMÈTRE
- VÉRIFIÉ
- Skills
- 22 433
- dépôts
- 3444
- dernière synchronisation
- 28 oct. 2026
leonvanzylstart-an-app
Interview the user in depth about what they actually want to build, then scaffold a working full-stack web app around it. Use when the user wants to start a new app, website, prototype, or SaaS; when they don't know what tech stack to pick; or when they want a solid working starting point fast. Covers requirements discovery, project setup, database (SQLite or Postgres in Docker), sign-in, transactional email, file uploads, payments, AI features, background jobs, optional agent access over MCP so
- Installations / 1h
- 1
- GitHub Stars
- 106
- Mis à jour
- 19 oct.
jakeschincarioltrader-budget
Budget Manager. Sizes every position to your budget before anything is bought: keeps a cash buffer, caps any one stock (the excess is shared out to the others), drops slices under your minimum order, rounds so every dollar is used, supports fractional or whole shares, and writes the proposed buy orders to trader/orders.json in the exact shape of Alpaca's placestockorder (notional as a string). Nothing is placed. Use when the user says "I have $5,000", "size my trades", "how much of each should I
- Installations / 1h
- 1
- GitHub Stars
- 69
- Mis à jour
- 14 oct.
jakeschincarioltrader-tax
Tax Optimizer. Tracks cost-basis lots for every position (FIFO, highest cost first, or specific lots), shows unrealized gains and losses by lot with short or long term, works out what a sale would realize before you sell, finds tax-loss harvesting candidates over a loss threshold, checks the wash sale rule (30 days before and after, GOOG and GOOGL as one family), and writes harvest sells only as proposals. Not tax advice. Use when the user says "what are my gains", "cost basis", "tax lots", "tax
- Installations / 1h
- 1
- GitHub Stars
- 69
- Mis à jour
- 14 oct.
solomondivyananthae-ai-templates
Use and write AI-native After Effects templates through the AE MCP Bridge - finished animated designs (lower third, kinetic title, word reveal, app card, bar chart, logo sting, welcome) that an agent fills from a brief with aetemplate, built as one undo step with a contact sheet to check, in 16x9, 9x16, 1x1 or 4x5; plus how to author a new template as JSON (typed slots, steps, expressions, repeats) that npm test validates. Use when asked for a lower third, title, chart, logo sting, app or UI sho
- Installations / 1h
- 1
- GitHub Stars
- 68
- Mis à jour
- 5 oct.
solomondivyananthae-camera-3d
Cameras and 3D scenes in After Effects through the AE MCP Bridge - 3D layers and depth, camera rigs on nulls (dolly, orbit, push-in, parallax), depth of field, lights and shadows, materials, choosing the 3D renderer, 3D models, camera shake, and what the 3D camera tracker needs a person for. Use when asked for a camera move, parallax, depth, a 3D scene or extrusion, lighting, shadows, bokeh, or when layers should feel like they sit in space.
- Installations / 1h
- 1
- GitHub Stars
- 68
- Mis à jour
- 5 oct.
solomondivyananthae-composition
Stage a frame in After Effects through the AE MCP Bridge - give every beat one dominant element, build scale hierarchy, use the whole frame instead of a band in the middle, vary the composition between beats, place things on a grid with real margins, crop and bleed deliberately, compose for 9x16 and 1x1, and check it with aeproof's staging checks. Use when work looks flat, generic, empty, "like a slide", "like a wireframe" or "not designed", when every beat looks the same, when nothing on screen
- Installations / 1h
- 1
- GitHub Stars
- 68
- Mis à jour
- 5 oct.
solomondivyananthae-effects
Special effects, blur and motion blur in After Effects through the AE MCP Bridge - glows, light rays and flares, fractal noise, displacement and distortion, particles, chromatic split, grain, stylized looks, paper and print finishes, stepped on-twos cadence, effects driven by map layers, and every kind of blur (Gaussian, directional, radial, lens blur, pixel motion blur, comp motion blur), with exact effect and parameter names. Use when asked for a look or an effect (glow, energy, glitch, heat h
- Installations / 1h
- 1
- GitHub Stars
- 68
- Mis à jour
- 5 oct.
solomondivyananthae-motion-proof
Proof-read motion in After Effects through the AE MCP Bridge - screen a comp with aeproof for overlapping or clipped elements, jitter, flicker, one-frame pops, keyframes off the frame grid, linear easing, text too small or too brief to read, uneven staggers, missing motion blur on fast moves, broken expressions, a solo switch left on or an empty first frame, plus staging checks for a beat with no focal point, no scale hierarchy or an unused frame, then verify each finding on a rendered frame. Us
- Installations / 1h
- 1
- GitHub Stars
- 68
- Mis à jour
- 5 oct.
solomondivyananthae-transitions
Build transitions between shots and scenes in After Effects through the AE MCP Bridge - cuts on the beat, whip pans and zoom punches with motion blur, shape and mask wipes, luma and gradient wipes, iris, block and card wipes, light and glass wipes, match cuts, and precomp-based transitions, with verified effect and parameter names. Use when asked to transition, wipe, reveal, cut between scenes, or make scene changes feel smoother or punchier.
- Installations / 1h
- 1
- GitHub Stars
- 68
- Mis à jour
- 5 oct.
solomondivyananthae-ui-motion
App and product-launch motion in After Effects through the AE MCP Bridge - soft mesh-gradient backgrounds, UI screens as layered 3D panels with perspective tilts and rim light, cards that cascade in, carousels and coverflow on one slider, glass panels, looping collaboration cursors, AI responses that stream in with a shimmer, device mockups, a logo that becomes the app header, light-to-dark theme switches for a premium tier, particle dissolves into a logo, and a light-sweep end card. Use when as
- Installations / 1h
- 1
- GitHub Stars
- 68
- Mis à jour
- 5 oct.
arize-aiarize-dataset
Creates, manages, and queries Arize datasets and examples. Covers dataset CRUD, appending examples, exporting data, and file-based dataset creation using the ax CLI. Use when the user needs test data, evaluation examples, or mentions create dataset, list datasets, export dataset, append examples, dataset version, golden dataset, or test set.
- Installations / 1h
- 1
- GitHub Stars
- 65
- Mis à jour
- 20 oct.
arize-aiarize-experiment
Creates, runs, and analyzes Arize experiments for evaluating and comparing model performance. Covers experiment CRUD, exporting runs, comparing results, and evaluation workflows using the ax CLI. Use when the user mentions create experiment, run experiment, compare models, model performance, evaluate AI, experiment results, benchmark, A/B test models, or measure accuracy.
- Installations / 1h
- 1
- GitHub Stars
- 65
- Mis à jour
- 20 oct.
arize-aiarize-migrate-langfuse
Migrates LLM observability from Langfuse into Arize AX — historical trace import via OTLP (LF output→output.value, sessionId→session.id), datasets, and prompts (latest or versions + labels). Use when migrating from Langfuse to Arize or importing Langfuse observations into AX.
- Installations / 1h
- 1
- GitHub Stars
- 65
- Mis à jour
- 20 oct.
arize-aiarize-migrate-langsmith
Migrates LLM observability from LangSmith into Arize AX — historical trace import via OTLP (LS outputs→output.value, session/thread→session.id), datasets, and Prompt Hub prompts (latest or versions). Use when migrating from LangSmith to Arize, importing LangSmith runs into AX, or replacing LangSmith with Arize.
- Installations / 1h
- 1
- GitHub Stars
- 65
- Mis à jour
- 20 oct.
arize-aiarize-phoenix-migration
Migrate existing Phoenix (PX) traces, datasets, experiments, and stored evaluation results into Arize AX and verify the imported records. Use when users ask to move or copy historical Phoenix data to AX; not for adding live instrumentation or exporting AX data alone.
- Installations / 1h
- 1
- GitHub Stars
- 65
- Mis à jour
- 20 oct.
arize-aiarize-prompt-optimization
Optimizes, improves, and debugs LLM prompts using production trace data, evaluations, and annotations. Extracts prompts from spans, gathers performance signal, and runs a data-driven optimization loop using the ax CLI. Use when the user mentions optimize prompt, improve prompt, make AI respond better, improve output quality, prompt engineering, prompt tuning, or system prompt improvement.
- Installations / 1h
- 1
- GitHub Stars
- 65
- Mis à jour
- 20 oct.
arize-aiarize-prompts
INVOKE THIS SKILL for Arize Prompt Hub and ax prompts workflows: author or import templates and save (Workflows A–B), label/promote (C), or list/get/edit/delete/duplicate (D). Use when the user mentions ax prompts, Prompt Hub, creating/editing/saving a prompt, {variable} placeholders, or production/staging labels. For improving prompt text using traces or eval scores, use arize-prompt-optimization. For running experiments, use arize-experiment.
- Installations / 1h
- 1
- GitHub Stars
- 65
- Mis à jour
- 20 oct.
manutejgolang-backend-development
Complete guide for Go backend development including concurrency patterns, web servers, database integration, microservices, and production deployment
- Installations / 1h
- 1
- GitHub Stars
- 62
- Mis à jour
- 13 juin
joshuadavidthomasenglish-please
Dude, come on. You write at the density of your own thinking and leave the reader to unpack it. Apply whenever explaining anything to a human — not just end-of-run summaries, every message.
- Installations / 1h
- 1
- GitHub Stars
- 56
- Mis à jour
- 20 juil.
joshuadavidthomasfrontend-design-principles
Use when building or reviewing frontend UI — dashboards, admin panels, landing pages, marketing sites, web apps. Drives domain-specific design decisions (typography, color world, layout, CSS token naming, depth and spacing systems) instead of generic AI defaults; routes to app.md (product/data UIs) or marketing.md (public/creative pages) by context.
- Installations / 1h
- 1
- GitHub Stars
- 56
- Mis à jour
- 20 juil.
joshuadavidthomasgrug-brained-dev
Use when reviewing PRs, simplifying over-engineered code, judging architecture, or renaming unclear concepts — inline fake helpers, delete meatless ceremony, rename lying names, merge over-split files, reject premature abstraction, say no to speculative config/modes/layers, then end with the smallest safe next change. Triggers when code is too fancy, too abstract, too clever, too many files/helpers/layers, or too well-factored but painful to change. Embody Grug brain: complexity very bad, small
- Installations / 1h
- 1
- GitHub Stars
- 56
- Mis à jour
- 20 juil.
joshuadavidthomasimprove
Survey a codebase as a senior advisor and turn the highest-value findings into implementation plans for other agents to execute — strictly read-only on source code, never implements anything itself. Use when asked to audit a codebase, find improvement opportunities (bugs, security, performance, test coverage, tech debt, architecture, migrations, DX), suggest features or roadmap direction, or generate handoff plans for another agent to implement.
- Installations / 1h
- 1
- GitHub Stars
- 56
- Mis à jour
- 20 juil.
joshuadavidthomasjj
Jujutsu (jj) — the Git-compatible version control system. Activate ONLY when a .jj/ directory is present in the project or when jj/jujutsu is explicitly mentioned. Do NOT activate for plain git repos without .jj/. Use for any VCS operations in jj-managed projects: commit, push, pull, branch, bookmark, rebase, squash, merge, diff, log, status, working copy, change ID, revset, fileset, template, configuration, workspaces.
- Installations / 1h
- 1
- GitHub Stars
- 56
- Mis à jour
- 20 juil.
joshuadavidthomasskill-authoring
Use when authoring, creating, refining, or troubleshooting agent skills — scaffold SKILL.md and frontmatter, write and optimize the trigger description, structure the body with progressive disclosure, validate structure, and test or debug activation. Also when building a new skill from scratch, when a skill won't trigger, loads incorrectly, or the agent ignores it entirely. Use when a skill misbehaved in the current session and needs adjustment based on learnings.
- Installations / 1h
- 1
- GitHub Stars
- 56
- Mis à jour
- 20 juil.