Answer questions about ECC by reading the live repo surface — agents, skills, commands, hooks, rules, install profiles, and docs — instead of memory. Use when the user asks what ECC includes, how to install or reset it, which skill or command fits a task, or how project onboarding works.

Generates Angular code and provides architectural guidance. Trigger when creating projects, components, or services, or for best practices on reactivity (signals, linkedSignal, resource), forms, dependency injection, routing, SSR, accessibility (ARIA), animations, styling (component styles, Tailwind CSS), testing, or CLI tooling.

Coordinate frontend/backend or service-to-service work through one authoritative machine-checkable contract (OpenAPI, AsyncAPI, Protocol Buffers, or JSON Schema), with generated consumer types and contract-verified integration. Use when parallel consumer and provider work must evolve an API or event schema without field drift, mock/production shape mismatch, or one side silently redefining the interface.

Score a scoped competitor set into comparable profile cards: nine weighted dimensions (positioning, voice, visual craft, offer packaging, evidence, enterprise-readiness, thought leadership, pricing, client tension) with 1-5 evidence-anchored rubrics and a tension 2x2 plot. Use when benchmarking or scoring competitors, building a competitive comparison matrix, or grading rival positioning before assembling the report; runs after competitive-platform-analysis and before competitive-report-structure.

Produce cited research reports from multiple web sources using firecrawl and exa MCP tools — plan sub-questions, search and deep-read sources, then synthesize findings with inline citations and confidence levels. Use when the user asks to research a topic in depth, run a deep dive or investigation, or do competitive analysis, technology evaluation, market sizing, or due diligence on a company.

Statically review MCP configuration for mutable package references before approval or CI, without executing discovered MCP servers. Use when reviewing .mcp.json, Cursor, VS Code, Claude, Windsurf, or other repo-scoped MCP config.

Analyses a video — usually a bug screen recording from a file, URL, or Linear ticket — with ffmpeg keyframes plus optional OCR and transcription, extracting errors, UI state, and repro steps. Triggers on "analyse this video", "analyze this recording", "what does this video show", "/video-analyser".

Writes the plan artifact in `.agent/{branch}/` — `plan.md` as a brief (task, guardrails, definition of done, turn cap, file changes) plus `checks.yaml`, its executable acceptance checks, sealed for `run-checks.mjs`. Use after planning and on every plan iteration; triggers on create plan, write plan artifact, regenerate plan, iterate on plan.

Use when the user wants an elicitative interview — reaching alignment on a plan, decision, or idea by drawing out their decisions, unstated opinions, silent assumptions, and thoughts they find hard to put into words, through rounds of pointed questions. Triggers: "grill me", "interview me about this", "make sure we're aligned", "make sure you understand what I want", "help me pin down the decisions", "what am I assuming", "help me figure out what I actually want".

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.

dd-trace-py integration development guide. Use when creating, modifying, or debugging contrib integrations in the Python tracer. Covers the patch module system, context_with_data, context_with_event (new), registration, testing through the repository test runner, and common anti-patterns. LLM/AI integrations should use this skill for APM-side workflow only; use llmobs-integrations for LLMObs-specific lifecycle, extraction, streaming, and VCR guidance. Pin is DEPRECATED. Triggers: "dd-trace-py", "ddtrace", "contrib", "integration", "patch.py", "trace_handlers", "PATCH_MODULES", "context_with_data", "context_with_event", "TracingEvent", "VCR", "cassette", "generative-ai", "LLM integration", "run-tests", "suitespec", "new integration", "wrap", "unwrap", "manifest.yaml", "integration manifest".

Use when the user asks to discover, browse, search, suggest, recommend, or install agents and agentic resources. Author, validate, or import OASF records; push, sign, and publish records; discover, search, browse, suggest, or recommend agents like MCP servers, A2A agents, or agent skills; claim and prove record ownership or identity (DNS, HTTPS, DID, SPIFFE, ANS); verify signatures, ownership claims, or security scans; list running agent workloads; configure node content policies and prune jobs; synchronize data between servers; or install/uninstall agents and agentic resources into coding agents like VS Code Copilot, Claude Code, or Cursor.

Use this skill to interact with an AGNTCY Directory (DIR) instance. This is a bootstrap: it installs the complete agntcy-dir skill (setup, authoring, publishing, discovery, verification, sync, install workflows) from the AGNTCY Directory GitHub repository, then defers to it.

Trains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies. Use when training models >1B parameters, need maximum GPU efficiency (47% MFU on H100), or require tensor/pipeline/sequence/context/expert parallelism. Production-ready framework used for Nemotron, LLaMA, DeepSeek.

AI DevKit · Orchestrator for structured SDLC phase skills. Use when the user wants to run the full lifecycle or choose the next phase across requirements, design, planning, implementation, testing, and review.

De novo enzyme design by catalytic-motif scaffolding — build a transition-state motif, generate scaffolds with AlphaProtein Novo, fold every mechanistic state, and triage with mechanism-inspired filters (catalytic geometry, multi-state H-bonds, multi-resequence backbone scoring). Use for designing enzymes for a named reaction, scoring or filtering existing designs, or deciding which designs to order.

Kotlin Multiplatform source-set rules for Meshtastic-Android - where commonMain ends, how expect/actual is bridged, and the networking, database and platform-integration boundaries. Use this whenever you add a file to a KMP module, move code between source sets, or hit a compile error that appears on only one target.

Create a GitHub pull request from current working changes. Handles all git states - uncommitted changes, no branch, unpushed commits, etc. Analyzes diffs and changesets to generate a PR with filled-in template. Opens the PR in the browser when done. Use when the user asks to create a PR, open a PR, submit changes, or push for review.

Turn workflows from your MemSearch memory into reusable skills. Use when the user asks to make/create/extract/distill a skill from what they just did or from past work, review skill candidates, install a distilled skill, or 'turn this into a skill'. Manages MemSearch procedural-memory candidates under .memsearch/skill-candidates/, not the host agent's own skills system.

Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.