decebal
- 66 skills
- 0 followers
- 1 repo stars
- 3 days ago last updated
- ▌ Skill Autoresearch · decebal bundleImprove a Codex skill through bounded autoresearch: freeze a mechanical evaluator, record a baseline, make one focused change per iteration, keep only measured improvements, and preserve experiment evidence. Use when asked to autoresearch, optimize, tune, or systematically improve a SKILL.md, skill runtime, trigger boundary, or skill eval. The bundled runner is written in Rust.
- ▌ Systematic Debugging · decebal bundleEnforce a structured diagnostic workflow before any fix — observe, hypothesize, test, diagnose, then fix and verify. Use when the user says "debug this", "why is this failing", "investigate the error", "find the bug", "troubleshoot", or "diagnose", or reports something broken, throwing, failing, or behaving unexpectedly. Covers a two-tier triage-then-deep-dive model and links reference guides for logs, network, state, and environment.
- ▌ App Store Optimization · decebal bundleResearch, validate, and improve Apple App Store and Google Play listings with current platform rules, evidence-led competitor analysis, metadata optimization, localization, review synthesis, visual planning, and controlled experiments. Use for ASO audits, store metadata, app keywords, product-page conversion, listing experiments, launches, and updates. Includes a Rust metadata and experiment validator.
- ▌ Codex Skill Development · decebal bundleCreate or update skills in the decebal-codex-skills repository using official Codex skill authoring plus repository metadata, portability, licensing, validation, and installability gates. Use for work under this repository's skills directory; use official system skill-creator directly for unrelated personal skills.
- ▌ Rust Clean Architecture · decebal bundleApply clean-architecture layering to Rust workspaces and enforce dependency direction with tests. Use when placing new files, modules, or crates; reorganizing layers; splitting large modules; setting visibility; or reviewing hexagonal and ports-and-adapters boundaries.
- ▌ Design System · decebal bundleEnforce design-token governance, responsive sizing, and white-label safety for multi-tenant interfaces. Use when modifying CSS, Tailwind classes, global styles, UI components, design tokens, colors, or shared visual patterns.
- ▌ Docker Expert · decebal bundleDocker containerization expert with deep knowledge of multi-stage builds, image optimization, container security, Docker Compose orchestration, and production deployment patterns. Use PROACTIVELY for Dockerfile optimization, container issues, image size problems, security hardening, networking, and orchestration challenges.
- ▌ Elixir Expert · decebal bundleBuild and operate Phoenix and OTP services in Elixir. Use for supervision trees, GenServer or Task design, umbrella projects, Ecto, LiveView, Rustler NIFs, Mix releases, Docker, Credo, Dialyzer, BEAM stalls, bottlenecks, or mailbox growth.
- ▌ Protobuf Grpc · decebal bundleBuild Protocol Buffers and gRPC or gRPC-Web integrations. Use for proto schemas, code generation, Buf workflows, binary and JSON serialization, encrypted envelopes over WebSockets, TypeScript browser clients, and wire-compatible schema evolution.
- ▌ Explain Module · decebal bundleExplore an unfamiliar module/component/system and explain how it works, backed by real file:line anchors and Mermaid diagrams. Use when someone asks "how does X work?", "explain the Y module", "what does Z do?", or "walk me through ...". Triggers on any request to understand, orient in, or onboard onto a piece of a codebase.
- ▌ Fastify Expert · decebal bundleBuild production-grade Node or Bun APIs with Fastify. Use for plugin encapsulation, routes, JSON Schema, TypeBox or Zod validation, lifecycle hooks, decorators, JWT auth, rate limiting, graceful shutdown, error handling, response serialization, and app.inject integration tests.
- ▌ Forge Prove It · decebal bundleRead this repository's real enforcement surface — which gates exist, which fire, which look at nothing, and which can actually block a merge — then write a prove-it feature reviewer calibrated to it. Use when a repo needs its own adversarial feature reviewer, when asked to generate, forge, bootstrap or port prove-it into a codebase, when a team keeps shipping features that pass every gate and still do not work, or when an existing prove-it has drifted from the tree it reviews. Emits a skill whose every claim is either a mechanism true in any repo or a fact this run observed, with the observing command recorded beside it.
- ▌ Bundle Analysis · decebal bundleMeasure, diff, and gate JavaScript/TypeScript bundle size. Use when the user wants to check bundle size, analyze a bundle, see a size diff, asks what's the bundle impact of a change, or wants to tree-shake a dependency. Covers raw/gzip/brotli snapshots per entry point, base-vs-branch diff reports, dependency attribution, tree-shaking validation, and CI budget enforcement. Triggers on: check bundle size, analyze bundle, size diff, bundle impact, tree-shake.
- ▌ Frontend Design · decebal bundleCreate distinctive, production-grade frontend interfaces with high design quality. Generates creative, polished code that avoids generic AI aesthetics. Use when the user asks to build web components, pages, artifacts, posters, or applications, or when any design skill requires project context.
- ▌ Monorepo Expert · decebal bundleDevelop Turborepo and Bun workspaces. Use for turbo.json pipelines, local or remote caching, package filters, shared tooling, workspace dependencies, cross-service environment and ports, affected-package CI, turbo prune, cache misses, or monorepo Docker builds.
- ▌ Security Review · decebal bundleReview web, SPA, and browser SDK code for security. Use for CSP compliance, credential exposure, XSS, SQL or command injection, WebCrypto correctness, CORS, cookie flags, SRI, WebSockets, dependency choices, vulnerability checks, security audits, and pre-release review.
- ▌ Integration Test · decebal bundleAudit integration-test coverage, find untested cross-boundary paths, and write tests matching project conventions. Use when asked to audit tests, check coverage, find gaps, or add integration tests. Tests must be time-bounded and verified to exercise the intended path.
- ▌ Teach Impeccable · decebal bundleOne-time setup that gathers design context for your project and saves it to your AI config file. Run once to establish persistent design guidelines.
- ▌ Wasm Development · decebal bundleBuild and integrate WebAssembly across both major toolchains — C/C++ via Emscripten (emcc/em++) and Rust via wasm-pack + wasm-bindgen. Covers the JS/WASM memory boundary, off-main-thread execution in Web Workers, CSP requirements, size optimization, and debugging. Use when the user wants to build WASM, compile C/C++ or Rust to WebAssembly, set up Emscripten or wasm-pack, call a WASM module from JavaScript, pass data across the JS/WASM boundary, or shrink/debug a .wasm binary. Triggers on: build WASM, Emscripten, wasm-pack, WebAssembly, wasm-bindgen, WASM module.
- ▌ Bun Testing · decebal bundleWrite and run tests with Bun's built-in bun:test runner. Use for test organization, lifecycle hooks, assertions, snapshots, coverage, mocking, Turborepo caching, flaky tests, or Jest and Vitest migrations. See references/mocking.md for mocks and references/integration.md for HTTP, database, and environment-isolation tests.
- ▌ Codex Beads · decebal bundleConvert a PRD to beads (epic plus child tasks) for Codex execution. Auto-detect the installed tracker CLI—Chronis (cn), beads-rust (br), or beads (bd)—and create one epic with a child task per user story. Use when asked to create beads, convert a PRD to beads, or prepare Chronis work for Codex.
- ▌ Find Skills · decebal bundleHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
- ▌ MCP Builder · decebal bundleGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
- ▌ Perf Review · decebal bundleApplication-level performance review of a code change — hot paths, allocations, main-thread blocking, batching, caching, and worker offloading. Use when the user asks to "review for performance", "check perf", "is this efficient", wants a "hot path review" or a "performance audit", or before shipping code on a render loop, event handler, streaming pipeline, or request handler. Reviews app/runtime behaviour, not language semantics — the sibling typescript skill covers language-level tuning.
- ▌ Create Plans · decebal bundleCreate hierarchical project plans optimized for solo Codex development. Use for briefs, roadmaps, phase plans, tasks, verification criteria, and context handoffs. When Chronis or another tracker already owns the queue, use this skill only for per-task execution detail, stored in the task description or .planning/phases/[task-id].md.
- ▌ GCP Cloudrun · decebal bundleDeploy and operate containerized services on Google Cloud Run. The build → push → deploy → verify → rollback loop with real gcloud commands, plus config gotchas (env vars vs Secret Manager, concurrency vs CPU, cold starts, request timeout). Use when the task involves "deploy to cloud run", "cloud run config", "rollback deployment", "cloud build", or "terraform cloud run". Terraform lives in references/terraform.md; cold-start / OOM / timeout / logging debugging lives in references/diagnostics.md.
- ▌ Rust Quality · decebal bundleSet up workspace-level Rust quality gates with Clippy, rustdoc, cargo-sort, and unsafe-code policy. Use when starting or hardening a Cargo workspace, configuring workspace lints, wiring CI, denying broken documentation links, or reducing noisy pedantic lint output.
- ▌ Semantic Isa · decebal bundleDesign a typed Semantic Instruction Set Architecture for an agent or MCP workflow, with deterministic admission, provenance, scoped verification and refusal tests; or explain Arbiter-K accurately. Use for semantic ISA, agent execution kernels, tool-call taint tracking and governance contracts, rather than ordinary API design or a general security audit.
- ▌ Brainstorming 2 · decebal bundleYou MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
- ▌ Codex Browser · decebal bundleRoute browser interaction to Codex's bundled in-app Browser or connected Chrome while preferring purpose-built connectors for semantic work. Use for navigation, visual inspection, forms, screenshots, logged-in browser state, and local web UI verification. Replaces legacy dev-browser workflows without a repository-local runtime.
- ▌ Onboard · decebal bundleDesigns and improves onboarding flows, empty states, and first-run experiences to help users reach value quickly. Use when the user mentions onboarding, first-time users, empty states, activation, getting started, or new user flows.
- ▌ Quieter · decebal bundleTones down visually aggressive or overstimulating designs, reducing intensity while preserving quality. Use when the user mentions too bold, too loud, overwhelming, aggressive, garish, or wants a calmer, more refined aesthetic.
- ▌ Typeset · decebal bundleImproves typography by fixing font choices, hierarchy, sizing, weight, and readability so text feels intentional. Use when the user mentions fonts, type, readability, text hierarchy, sizing looks off, or wants more polished, intentional typography.
- ▌ Colorize · decebal bundleAdd strategic color to features that are too monochromatic or lack visual interest, making interfaces more engaging and expressive. Use when the user mentions the design looking gray, dull, lacking warmth, needing more color, or wanting a more vibrant or expressive palette.
- ▌ Critique · decebal bundleEvaluate design from a UX perspective, assessing visual hierarchy, information architecture, emotional resonance, cognitive load, and overall quality with quantitative scoring, persona-based testing, and actionable feedback. Use when the user asks to review, critique, evaluate, or give feedback on a design or component.
- ▌ Optimize · decebal bundleDiagnoses and fixes UI performance across loading speed, rendering, animations, images, and bundle size. Use when the user mentions slow, laggy, janky, performance, bundle size, load time, or wants a faster, smoother experience.
- ▌ Pr Proof · decebal bundleBuild the HTML evidence report a PR ships — the claim, before/after anchored to commit SHAs, screenshots with provenance, copy-paste manual test steps, and what was NOT checked. Use when a PR changes a user-visible surface, when a reviewer asks to be shown, or when someone says prove it, proof, evidence report, PR report, before and after, or hand-check. Produces one self-contained file under docs/, committed in the branch and linked from the PR body.
- ▌ Codex Prd · decebal bundleGenerate a Product Requirements Document (PRD) for Codex task orchestration. Create PRDs with user stories, two-tier quality gates, and a testing-trophy plan that the codex-beads skill can convert into tracked work. Use when asked to create a PRD, plan a feature, write requirements, or spec out work.
- ▌ Codex SEO · decebal bundleAudit, plan, and improve technical SEO, on-page content, structured data, sitemaps, hreflang, local or ecommerce visibility, and AI-search citability using evidence-first Codex workflows and a safe Rust static-analysis CLI. Use for SEO audits, page reviews, traffic or ranking investigations, content plans, schema, crawlability, indexation, migration drift, competitor research, and GEO. Never invent search, analytics, backlink, or performance data.
- ▌ Normalize · decebal bundleAudits and realigns UI to match design system standards, spacing, tokens, and patterns. Use when the user mentions consistency, design drift, mismatched styles, tokens, or wants to bring a feature back in line with the system.
- ▌ Overdrive · decebal bundlePushes interfaces past conventional limits with technically ambitious implementations — shaders, spring physics, scroll-driven reveals, 60fps animations. Use when the user wants to wow, impress, go all-out, or make something that feels extraordinary.
- ▌ Web Video · decebal bundleOptimize a screen recording (mp4/mov/webm) into a web-ready demo video — H.264, faststart, audio stripped — with optional poster frame and looping GIF. Use when the user has a demo/screen recording to prepare for a website, blog, or social post.
- ▌ Blog Image · decebal bundleTurn a screenshot into a web-optimized blog hero or 1200x630 OG/social image (WebP), or generate a branded OG card from a title. Use when the user wants a blog hero image, social/OG share card, an optimized/resized image for the web, or to shrink a PNG to WebP.
- ▌ Typescript · decebal bundleThis skill should be used when the user asks to "optimize TypeScript performance", "speed up tsc compilation", "configure tsconfig.json", "fix type errors", "improve async patterns", or encounters TS errors (TS2322, TS2339, "is not assignable to"). Also triggers on .ts, .tsx, .d.ts file work involving type definitions, module organization, or memory management. Does NOT cover TypeScript basics, framework-specific patterns, or testing.
- ▌ Arch · decebal bundleGenerate architecture diagrams as MermaidJS using the C4 model — System Context (L1), Container (L2), Component (L3), Code (L4, usually skipped), plus a data-flow sequence diagram. Use when the user asks to "draw architecture", "create a diagram", "document system structure", "diagram the system", "show how the components fit together", or wants a C4 / architecture / data-flow diagram embedded in Markdown.
- ▌ Adapt · decebal bundleAdapt designs to work across different screen sizes, devices, contexts, or platforms. Implements breakpoints, fluid layouts, and touch targets. Use when the user mentions responsive design, mobile layouts, breakpoints, viewport adaptation, or cross-device compatibility.
- ▌ Audit · decebal bundleRun technical quality checks across accessibility, performance, theming, responsive design, and anti-patterns. Generates a scored report with P0-P3 severity ratings and actionable plan. Use when the user wants an accessibility check, performance audit, or technical quality review.
- ▌ Bolder · decebal bundleAmplify safe or boring designs to make them more visually interesting and stimulating. Increases impact while maintaining usability. Use when the user says the design looks bland, generic, too safe, lacks personality, or wants more visual impact and character.
- ▌ Harden · decebal bundleImprove interface resilience through better error handling, i18n support, text overflow handling, and edge case management. Makes interfaces robust and production-ready. Use when the user asks to harden, make production-ready, handle edge cases, add error states, or fix overflow and i18n issues.
- ▌ Polish · decebal bundlePerforms a final quality pass fixing alignment, spacing, consistency, and micro-detail issues before shipping. Use when the user mentions polish, finishing touches, pre-launch review, something looks off, or wants to go from good to great.
- ▌ Animate · decebal bundleReview a feature and enhance it with purposeful animations, micro-interactions, and motion effects that improve usability and delight. Use when the user mentions adding animation, transitions, micro-interactions, motion design, hover effects, or making the UI feel more alive.
- ▌ Arrange · decebal bundleImprove layout, spacing, and visual rhythm. Fixes monotonous grids, inconsistent spacing, and weak visual hierarchy. Use when the user mentions layout feeling off, spacing issues, visual hierarchy, crowded UI, alignment problems, or wanting better composition.
- ▌ Clarify · decebal bundleImprove unclear UX copy, error messages, microcopy, labels, and instructions to make interfaces easier to understand. Use when the user mentions confusing text, unclear labels, bad error messages, hard-to-follow instructions, or wanting better UX writing.
- ▌ Delight · decebal bundleAdd moments of joy, personality, and unexpected touches that make interfaces memorable and enjoyable to use. Elevates functional to delightful. Use when the user asks to add polish, personality, animations, micro-interactions, delight, or make an interface feel fun or memorable.
- ▌ Distill · decebal bundleStrip designs to their essence by removing unnecessary complexity. Great design is simple, powerful, and clean. Use when the user asks to simplify, declutter, reduce noise, remove elements, or make a UI cleaner and more focused.
- ▌ Extract · decebal bundleExtract and consolidate reusable components, design tokens, and patterns into your design system. Identifies opportunities for systematic reuse and enriches your component library. Use when the user asks to create components, refactor repeated UI patterns, build a design system, or extract tokens.
- ▌ Ralph Tui Prd · decebalGenerate a Product Requirements Document (PRD) for ralph-tui task orchestration. Creates PRDs with user stories that can be converted to beads for automated execution. Triggers on: create a prd, write prd for, plan this feature, requirements for, spec out.
- ▌ Ralph Tui Cn Prd · decebalGenerate a Product Requirements Document (PRD) for ralph-tui task orchestration using chronis (cn CLI). Creates PRDs with user stories that can be converted to beads for automated execution. Triggers on: create a prd, write prd for, plan this feature, requirements for, spec out, cn prd.
- ▌ Rust Perf · decebal bundleDetect and fix performance issues in Rust projects using a modern 2026 toolchain. Use when the user asks to "profile rust", "optimize rust binary", "make it faster", "flamegraph", "pgo", "bolt", "find hotspots", "why is this slow", or mentions latency/throughput regressions in Rust code. Adapts to what's already in the repo (hotpath, criterion, custom allocator) before suggesting new tools. Covers CPU sampling, in-process pprof, deterministic benchmarks, heap profiling, causal profiling, and the PGO+BOLT pipeline.
- ▌ Ralph Tui Cn Beads · decebalConvert PRDs to beads for ralph-tui execution using chronis (cn CLI). Creates an epic with child beads for each user story. Use when you have a PRD and want to use ralph-tui with chronis as the task source. Triggers on: create beads, convert prd to beads, beads for ralph, ralph beads, cn beads, cn create.
- ▌
- ▌ Brainstorming · decebalYou MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
- ▌ Pr Review Coach · decebalCompanion to the `pr-atom-reviewer` skill. Reads the review history stored in AllSource Prime (the `prime_*` MCP tools) and turns it into actionable improvements to how the reviewer works. Three jobs — (1) ingest post-merge outcomes for past reviews (was the split followed? did the PR cause a revert?), (2) cluster the repo's actual atom vocabulary so the calibration table reflects this team's work instead of generic examples, (3) surface contradictions across past reviews so the user can decide what to harden into the SKILL.md. Use this skill when the user asks "what have we learned from reviews", "audit my past reviews", "what should I tighten in the reviewer skill", "did my recommended splits get followed", "how is the reviewer doing", "weekly review retro", or runs a periodic skill-improvement pass. Trigger also on phrases like "PR retro", "review postmortem", "calibrate my reviewer", or when the user mentions wanting to update the calibration table or the SKILL.md for the reviewer.
- ▌ Verify DB Change · decebalEnd-to-end verification of a database change (new tables, columns, indexes, writers/projectors) against real Postgres before review or merge. Replaces vibes-only "looks fine" sign-off with a structured proof block — schema applied per tenant, behavioural SQL exercised inside BEGIN…ROLLBACK on the live dev DB, app booted with the new wiring, and migration reversibility proved against a throwaway schema clone. Produces a PR-ready markdown excerpt with real captured output. Use this skill whenever the user asks to verify a migration, test a migration, prove a schema change works, verify a projector / writer / repository, "run any manual test needed to prove completion", or anything that means "show me the database actually works, not just the unit tests". Also use proactively when reviewing a PR that touches migrations or DB writers and the existing description has no real-Postgres proof. Designed for TypeORM + Nest + Postgres monorepos with multi-tenant DBs and Docker-Compose local infra, but the principles app
- ▌ Pr Atom Reviewer · decebalReview a local git branch as a pull request with a bias toward minimum disruption and minimum reviewer scope. Splits sprawling PRs into independently-mergeable atoms of work — each one a single end-to-end behaviour describable in 2-3 sentences, each shippable to the trunk on its own without any other atom in the plan being merged first — and demands a screenshot/video/recording proving the verifiable acceptance criterion. If the AllSource Prime MCP server is available (`prime_*` tools), the skill recalls prior reviews of the same repo to calibrate its judgement and records the current review for the next one. Use this skill whenever the user asks to review a PR, review a branch, prep a PR for review, check if a branch is ready to merge, or mentions "this PR is too big", "split this PR", "atomic commits", "scope creep in PR", "PR review checklist", or anything about getting a branch in shape before peers look at it. Trigger even if the user just says "look at my branch" in a code review context.
- ▌ Ralph Tui Create Beads Rust · decebalConvert PRDs to beads for ralph-tui execution using beads-rust (cn CLI). Creates an epic with child beads for each user story. Use when you have a PRD and want to use ralph-tui with beads-rust as the task source. Triggers on: create beads, convert prd to beads, beads for ralph, ralph beads, br beads, cn beads.