plan-orchestrator
Route hierarchical-planning intents to the correct backing script. Use when the user invokes /aura-frog:plan (with or without subcommand), mentions plan verbs (expand/next/replan/promote/archive/freeze/thaw/undo/status/conflicts), or types a plan-vocabulary bare word with .claude/plans/active.json present. Owns verb table, intent classifier, and 3-stage routing pipeline.
KtUI Components
Use this skill when working with [KtUI](https://ktui.io)âfree Tailwind UI components by Keenthemes. It ensures correct package usage, initialization, and reference to official docs.
dryui
Use when building UIs with DryUI (@dryui/ui) Svelte 5 components. Teaches correct patterns for compound components, theming, forms, and accessibility. Use the CLI as the default entry point; MCP mirrors the same workflow when available.
SuperBrain Distiller
You are SuperBrain's distiller, running headless and detached. You receive session events + salient markers (including `pushback` markers) and the current user-preferences doc. Many sessions are low-signal â emitting nothing is the correct outcome for those.
NexAU Agent Builder
This skill provides the procedural knowledge and reference material needed to implement NexAU agents correctly and efficiently.
checking-docs-correctness
Audits all Markdown files in a repository for internal inconsistencies, contradictions, stale CLI commands/flags, and broken cross-references. Returns a structured findings report. Use when asked to check, audit, or verify docs for correctness or consistency.
ctf-testing
Deploy and test Linux CTF challenges across cloud providers (AWS, Azure, GCP). Use when testing CTF setup, validating challenges work correctly, running the full test suite, verifying services survive VM reboots, or after creating new challenges.
openrouter-rs-release
Prepare and publish a new openrouter-rs or openrouter-cli release with consistent version updates, release notes, PR-first branch-protected workflow, and correct SDK-before-CLI sequencing when the CLI depends on a fresh SDK version. Use when asked to cut a release, bump crate versions, publish to crates.io, update changelog entries, refresh README installation versions, or update the README release history.
alfworld-appliance-navigator
Navigates the agent to a target appliance (microwave, stove, fridge, or sinkbasin) needed for object processing. Use when you are holding an object that needs heating, cooling, or cleaning and must move to the correct appliance station. Identifies the required appliance from the task context and executes the movement action.
convex-doctor
Run convex-doctor static analysis, interpret findings, and fix issues across security, performance, correctness, schema, and architecture categories. Use when running convex-doctor, fixing convex-doctor warnings or errors, improving the convex-doctor score, or when asked about Convex code quality, static analysis, or linting Convex functions.
Verify Composite Expansion
Verify the correctness of composite action expansion by comparing CLI output with actual GitHub Actions logs.
fict-best-practices
Fict compiler and runtime engineering guide for correctness and reliability. Use when implementing or reviewing Fict compiler transforms, runtime reactivity behavior, SSR/resume flow, devtools/playground integration, or release CI gates in Fict repositories.
magpie
Performs GPU kernel correctness and performance evaluation and LLM inference benchmarking with Magpie. Analyzes single or multiple kernels (HIP/CUDA/PyTorch), compares kernel implementations, runs vLLM/SGLang benchmarks with profiling and TraceLens, and runs gap analysis on torch traces. Creates kernel config YAMLs, discovers kernels in a project, and queries GPU specs. Use when the user mentions Magpie, kernel analyze or compare, HIP/CUDA kernel evaluation, vLLM/SGLang benchmark, gap analysis, TraceLens, creating kernel configs, or discovering GPU kernels.
backpack-code-review-checklist
Comprehensive code review checklist for Backpack design system components. Use when: (1) Reviewing PRs for new or modified Backpack components, (2) Validating component compliance with Constitution and design system rules, (3) Checking if component follows Backpack conventions before merge, (4) Identifying violations in API design, token usage, accessibility, or documentation. Covers Constitution principles (I-XIII), decisions/ guidelines, API encapsulation rules, private token restrictions, design approval workflow, icon alignment helpers, hover mixin usage, token semantic correctness, and snapshot currency. Essential for maintaining Backpack quality standards and catching non-obvious violations like className props in new components, wrong icon alignment wrapper, raw :hover instead of bpk-hover mixin, or cross-component private token usage.
meta-ads-analyzer
Provides expert-level analysis and diagnosis for Meta Ads campaigns. Use this skill to interpret performance data, identify root causes of issues, and generate actionable recommendations, with a special focus on correctly handling the 'Breakdown Effect'. Use when the user mentions Meta Ads analysis, campaign diagnosis, ad performance, CPA analysis, ROAS analysis, or asks to analyze exported data from Meta Ads Manager.
dotnet-advisor
Routes .NET/C# requests to the correct domain skill and loads coding standards as baseline for all code paths. Determines whether the task needs API, UI, testing, devops, tooling, or debugging guidance based on prompt analysis and project signals, then invokes skills in the right order. Always invoked after [skill:using-dotnet] detects .NET intent. Do not use for deep API, UI, testing, devops, tooling, or debugging implementation guidance.
exploring-llm-traces
ABSOLUTE MUST to debug and inspect LLM/AI agent traces using PostHog's MCP tools. Use when the user pastes a trace URL (e.g. /llm-observability/traces/<id>), asks to debug a trace, figure out what went wrong, check if an agent used a tool correctly, verify context/files were surfaced, inspect subagent behavior, investigate LLM decisions, or analyze token usage and costs.
review-comet-pr
Review a DataFusion Comet pull request for Spark compatibility and implementation correctness. Provides guidance to a reviewer rather than posting comments directly.
analysis-process
Turn the idea for a feature into a fully-formed PRD/design/specification and implementation-plan. Use when you have a spec or requirements that needs implementation. Use in pre-implementation (idea-to-design) stages to make sure you understand the spec/requirements and ensure you have a correct implementation plan before writing actual code.
au-review
Reviews AudioUnit v2/v3 plugin implementations for spec compliance, thread safety, and correctness. Use when the user asks to review an AudioUnit plugin, check an AUv3 app extension, audit property or parameter handling, or asks "is my AUComponent thread-safe?" or "why does my AU crash in Logic?". Trigger on phrases like "review my AudioUnit", "check my AUv3", "is my render block safe?", or when you see AURenderCallback, internalRenderBlock, kAudioUnitProperty_*, or AUAudioUnit in the code.
Get API Docs via chub
When you need documentation for a library or API, fetch it with the `chub` CLI rather than guessing from training data. This gives you the current, correct API.
Demo (from spiral/skills-demo)
This skill belongs to a donor whose vendor (`spiral/*`) is in the plugin's built-in trusted list. Acceptance tests use it to prove that `trusted-replace: true` correctly disables the built-in defaults.
claude-reflect
Self-learning system that captures corrections during sessions and reminds users to run /reflect to update CLAUDE.md. Use when discussing learnings, corrections, or when the user mentions remembering something for future sessions.
runaway-context
Use this skill when working in a project that has a RunawayContext v3 install. It loads the project's brief from the auto-generated Tier 3 markdown, queries `knowledge.db` for relevant lessons and chunks, and routes writes through the contract-enforced Client (HR-2 / HR-3 / HR-9). Trigger when the conversation enters a new project directory, when the user asks for context on a slug, when correcting AI behavior to capture as a draft, or when the user invokes `/runaway:*` commands.
01-paper-review
Review academic papers for correctness, quality, and novelty using OpenJudge's multi-stage pipeline. Supports PDF files and LaTeX source packages (.tar.gz/.zip). Covers 10 disciplines: cs, medicine, physics, chemistry, biology, economics, psychology, environmental_science, mathematics, social_sciences. Use when the user asks to review, evaluate, critique, or assess a research paper, check references, or verify a BibTeX file.
event-tracking-skill
Use when the request is end-to-end, spans multiple workflow phases, or the correct tracking-workflow entry point is still unclear.
ego-rsi
Use when an agent should check its own quality in ego and correct itself - reads ego's findings over MCP, changes the agent, registers the correction and waits for ego's verification.
click-target
Find and click a target object in XR. Use when testing UI interactions, clicking buttons, or verifying interactable elements work correctly.
key-amnesia hygiene
This skill is advisory: it describes the same detection vocabulary as the blocking `secret_guard` PreToolUse hook, so you can catch and avoid secret leaks *before* the hook (if installed) would deny the tool call â and so you still behave correctly if the hook isn't installed.
audit-fsm
Audit open-autonomy FSM apps for correctness and safety
wanxiang-skin-maintainer
Use when modifying the restructured Wanxiang keyboard under ResourceforHamster, especially for Custom.libsonnet config changes, button behavior changes, layout updates, toolbar updates, function-button order changes, or README/MODULES synchronization. This skill operates on one user-specified keyboard root, emphasizes minimal edits, correct file targeting, and Jsonnet validation after every change.
code-change-verification
Verify code changes by identifying correctness, regression, security, and performance risks from diffs or patches, then produce prioritized findings with file/line evidence and concrete fixes. Use when reviewing commits, PRs, and merged patches before/after release.
swift-concurrency-pro
Reviews Swift code for concurrency correctness, modern API usage, and common async/await pitfalls. Use when reading, writing, or reviewing Swift concurrency code.
onlyswitch-deeplink
Invoke OnlySwitch built-in switches or buttons via deeplink. Use when the user asks to toggle or trigger an OnlySwitch action (e.g. empty trash, keep awake, dark mode, mute, hide desktop, clear clipboard, eject discs, Xcode derived data, and any other built-in switch or button). Resolve the request to the correct switch id and open the onlyswitch deeplink.
critical-review
4-phase adversarial review protocol: pre-flight analysis, adversarial execution check, self-correction loop, and [VALIDATION] report
compare-erb-js
Compare ERB and JavaScript template outputs for the offline scoring SPA. Use when working on ERB-to-JS conversion, debugging template parity issues, or verifying that changes to scoring views work correctly in both ERB and SPA modes.
mcp-inspector
Test Model Context Protocol (MCP) servers using the MCP Inspector CLI with correct syntax
changeset-pr
Create or update a `.changeset/*.md` file for the current branch or PR in this repository, choose the correct package scope and release type, and verify the result against repo-specific Changesets config. Use when a publishable package changed, when a PR is missing a changeset, when an existing changeset needs correction, or when Codex needs to confirm whether a branch should have a changeset at all.
academic-pdf-to-gfm
Convert academic PDF papers to GitHub-renderable GFM markdown with inline figures and correctly formatted math equations. Use this skill when converting research papers, technical reports, or math-heavy PDFs for display on GitHub or GitLab. Also use it when GFM math equations are broken or not rendering on GitHub, when someone asks about the $$-vs-```math decision, when equations look garbled on GitHub, when KaTeX validation is needed, or when investigating why LaTeX renders locally but not on GitHub. Also use when comparing GitHub vs GitLab math rendering, when asking about self-hosting GitLab for math documents, or when looking for a platform that requires less LaTeX workarounds. Covers PDF type detection (Word vs LaTeX vs scanned), tool selection (pymupdf4llm/pdftotext/marker-pdf), image extraction, GitHub math rendering rules ($$-vs-```math decision), GitLab native math support (no workarounds needed), KaTeX validation, and multi-agent adversarial equation verification.
autosar-swc
AUTOSAR SWC expert. Defaults to Classic AUTOSAR (SWCs, RTE, ARXML, C) and operates in five modes: (1) Component design â decompose a feature into SWC types, define port interfaces, specify runnables and ExclusiveAreas, produce a plain-text composition diagram; (2) Interface definition â SenderReceiver / ClientServer / ModeSwitch / Parameter interfaces with correct AUTOSAR data types, scaling, InitValues, and AliveTimeout, as an ARXML sketch plus C typedef header; (3) SWC development â production-ready SWC skeleton (.c + .h + ARXML) with correct RTE API calls and MISRA-aligned style; (4) Diagram generation â plain-text component / sequence diagrams and ASCII state machines with AUTOSAR layer boundaries and ASIL notes; (5) Integration review â audit C and ARXML for port-interface alignment, RTE API naming, runnable-to-event mapping, and MCAL abstraction violations. Targets EB Tresos and Vector DaVinci. Handles Adaptive AUTOSAR (ara::com proxy/skeleton services) and legacy bring-up in smallest safe steps.
jzero-skills
Comprehensive knowledge base for jzero framework (enhanced go-zero). Use this skill when working with jzero to understand correct patterns for REST APIs (Handler/Logic/Context architecture), RPC services (service discovery, load balancing), Gateway services, database operations (sqlx, MongoDB, caching), resilience patterns (circuit breaker, rate limiting), and jzero-specific features (git-change-based generation, flexible configuration, custom templates). Essential for generating production-ready jzero code that follows framework conventions.
happier-diagnose
Diagnose a problem with a Happier session, the daemon, a provider (Claude/Codex/OpenCode), auth, or connectivity. Pulls the correct logs, finds a true root cause from evidence only, presents findings, and optionally uploads a private diagnostics bundle to Happier developers and/or files a sanitized public GitHub issue (the two are complementary). Use when the user reports a bug, says Happier is broken/stuck/misbehaving, asks to debug/diagnose/triage/troubleshoot Happier, or shares a Happier session ID and asks what went wrong.
3dgs-code-reviewer
Review 3D Gaussian Splatting implementation code for correctness, performance bugs, and best practices. Covers CUDA kernels, rendering pipeline, training loop, loss functions, and common pitfalls. Detects 42+ known bug patterns.
add-reference-tests
Add pytest tests to validate reference implementations in flashinfer_trace against FlashInfer or SGLang ground truth. Use when validating kernel definitions, adding tests for new op_types, or verifying reference implementations are correct.
migration-creator
Creates EF Core migrations for master or tenant databases. Use when adding new entities, modifying existing ones, or changing relationships. Follow the workflow to ensure correct migration generation and application.
signum
Use when the user wants a contract-first implementation workflow, asks to define correctness before coding, wants multi-stage execution with verification and audit, or needs a proof-style artifact for a code change. Codex should run a CONTRACT -> EXECUTE -> AUDIT -> PACK pipeline.
checklist.day Registry
Registry of Python AI/ML libraries: correct imports, quickstart code, and known footguns.
domainprimitive-builder
Helps create and implement DomainPrimitive types correctly using the AltaSoft DomainPrimitives framework. Guides the agent to generate generator-compatible primitives, add proper validation logic, apply normalization when needed, and follow all structural and domain invariant rules required for safe DomainPrimitive design.
distilly
Build and use evidence-grounded local person profiles with Distilly's exact five-tool workflow. Use when a user asks to research, ingest, distill, update, correct, retrieve, or recall a real or fictional person's profile, voice, boundaries, or evidence.
squirrel-session
Load behavioral corrections from Squirrel memory at session start. Use when starting a new coding session.