pixijs-blend-modes
Use this skill when compositing display objects with blend modes in PixiJS v8. Covers standard modes (normal, add, multiply, screen, erase, min, max), advanced…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-14 00:15
General & other
53,806 results
adapt-architecture
Execute structural metamorphosis using strangler fig migration, chrysalis phases, and interface preservation. Covers transformation planning, parallel running,…
build-coherence
AI multi-path reasoning coherence using bee democracy — independent evaluation of competing approaches, waggle dance as reasoning-out-loud, quorum sensing for…
repair-broken-references
Find and fix broken internal links, dead external URLs, stale imports, missing cross-references, and orphaned files. Ensures all project references remain…
portaly-affiliate
Set up buyer promotion on Portaly Payment so the creator's own customers earn a commission for referring other buyers — switch promotion on for the product and…
adding-product-alerting
Recommended repo-engineering guide when adding alerting to a PostHog product or extending the shared alerts platform. Routes lifecycle state machines,…
brain
Read/write brain files (Obsidian vault at brain/). Use for any task that persists knowledge — reflection, planning, or direct edits. Triggers: brain/…
dotnet-best-practices
Ensure .NET/C# code follows maintainable, modern best practices. Use when reviewing or improving C# code, solution structure, async patterns, dependency…
execute-chat
Execute work already agreed in the current chat without a plan.md. TRIGGER when: the user explicitly asks to use execute-chat.
prisma-cli-init
prisma init. Reference when using this Prisma feature.
think-concept-mapping
Builds a concept map - a non-hierarchical network of concept nodes joined by directed, labeled linking phrases so each node-link-node reads as an explicit…
file-organizer
Intelligently organize files and folders on your computer by understanding context, finding duplicates, suggesting better structures, and automating cleanup tasks. Reduce cognitive load and keep your digital workspace tidy without manual effort.
xfetch-web
Fetch and extract concrete web page URLs through Qiniu xfetch. Prefer Qiniu's path-style fetch API for markdown, JSON, or raw HTML extraction before other…
verification-before-completion
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output…
make-demo
Create or revise demos in the Remix repository. Use when adding a new demo under demos/, updating an existing demo, or reviewing demo code to ensure it…
bump-holocron-consumers
Bump @holocron.so/vite and @holocron.so/cli in Tommy's other GitHub repos. Use when asked to update holocron versions across remorses consumer sites, find…
conductor-status
Display project status, active tracks, and next actions
cost-optimization
Optimize cloud costs through resource rightsizing, tagging strategies, reserved instances, and spending analysis. Use when reducing cloud expenses, analyzing…
julia-pro
Master Julia 1.10+ with modern features, performance optimization, multiple dispatch, and production-ready practices. Expert in the Julia ecosystem including…
startup-metrics-framework
This skill should be used when the user asks about "key startup metrics", "SaaS metrics", "CAC and LTV", "unit economics", "burn multiple", "rule of 40",…
candid-chrome-qa-fix
Take a candid-chrome-qa findings JSON, let the user pick which findings to fix, and dispatch fixes — single batched PR, one PR per finding via Conductor deep…
pr-guardian
Continuously monitor a GitHub PR for merge conflicts, CI failures, and CodeRabbit review comments, then automatically fix any issues found. Polls every 5…
next-step
Change-aware next step advisor. Use when: user asks what to do next, workflow progression is unclear, session just started with dirty worktree. Not for:…
codepatrol-report
Investigate one area of the repository from a security perspective, and output a report after a critical review by Codex. Executed by a subagent launched by the codepatrol skill. It is not assumed that the user will call it directly.