Loading...
Loading...
Found 529 Skills
Connect to local LLM endpoints (Ollama, llama.cpp, vLLM) with automatic provider fallback. Use when: (1) you need to run LLM inference locally for privacy/cost, (2) you want to use models not available via cloud APIs, (3) you need offline capability, (4) you want automatic fallback to cloud providers when local fails.
Tracks cumulative LLM costs across DAG execution and makes real-time decisions to stay within budget. Downgrades models, skips optional nodes, or stops early when cost exceeds thresholds. Use when managing execution budgets, analyzing cost breakdowns, or optimizing model routing for cost. Activate on "cost budget", "too expensive", "reduce cost", "cost optimization", "model downgrade", "budget exceeded". NOT for LLM model selection logic (use llm-router), pricing comparisons across providers, or billing/invoicing.
Nooks platform help — AI-native sales engagement workspace with parallel dialer, multi-channel sequencing, real-time coaching, and waterfall enrichment. Use when SDR team needs to increase connect rates with parallel dialing, reps are getting numbers flagged as spam during cold calling, setting up multi-channel sequences across calls email SMS and social in Nooks, configuring AI coaching scorecards or roleplay scenarios, evaluating Nooks vs Orum vs Koncert for parallel dialing, prospects complain about awkward delay when answering parallel dialer calls, or setting up waterfall enrichment across multiple data providers. Do NOT use for building a general coaching program (use /sales-coaching) or general outbound cadence strategy (use /sales-cadence).
Generate and manage provider-backed video renders for short-form production. Use this when approved upstream assets or prompt plans already exist and you need local render manifests, downloaded video files, and replaceable routes for talking-head or Seedance generation without losing continuity across concepts and personas.
Single-image generation skill for posters, key art, and editorial illustrations. Defaults to gpt-image-2 but is provider-agnostic — the same workflow drives Flux, Imagen, or Midjourney via the active upstream tooling. Output is one or more PNG/JPEG files saved to the project folder.
Validates practitioner credentials and license status against the NPI registry. Cross-references specialties, credentials, and practice addresses against official records. Returns Verified / Partially Verified / Unverified / Flagged per practitioner with mismatch details and source URLs. Triggers: "verify these doctors", "check provider credentials", "validate licenses", "verify NPI numbers", "cross-check credentials against NPI", "compliance audit on providers", "are these practitioners still licensed", "validate my provider list". Accepts CSV, Google Sheet URL, or pasted data. Do NOT use for extracting providers from practice URLs — use healthcare-providers-extract instead. Do NOT use for filling data gaps — use healthcare-providers-enrich instead. Do NOT use for discovering practices — use market-finder or local-places instead. Do NOT use for general extraction — use nimble-web-expert instead.
This skill should be used when the user wants to check whether an agent skill is portable across providers. Common triggers include "is this skill cross-provider safe", "will my skill work in cursor", "audit skill compatibility", "check if this loads in codex", and "which providers support this skill". Spawns one agent per provider in parallel using bundled provider-doc snapshots (refreshed on cadence — never fetched at runtime) and produces a compatibility matrix plus a COMPAT.md report. Skip when authoring a new skill (use skill-creator) or rerunning baselines (use skill-eval).
Tests Android inter-process communication (IPC) through intents for vulnerabilities including intent injection, unauthorized component access, broadcast sniffing, pending intent hijacking, and content provider data leakage. Use when assessing Android app attack surface through exported components, testing intent-based data flows, or evaluating IPC security. Activates for requests involving Android intent security, IPC testing, exported component analysis, or Drozer assessment.
Implement account linking using StackOne Connect Sessions and the Hub React component. Use when user asks to "connect a provider", "embed the integration picker", "add BambooHR to my app", "create a connect session", "set up auth links", or "handle account webhooks". Covers the full flow from session creation to webhook handling. Do NOT use for making API calls after linking (use stackone-platform) or building AI agents (use stackone-agents).
Guide agents through using the OpenShell CLI (openshell) for sandbox management, gateway registration, provider configuration, policy iteration, BYOC workflows, and inference routing. Covers basic through advanced multi-step workflows. Trigger keywords - openshell, sandbox create, sandbox connect, logs, provider create, policy set, policy get, image push, forward, port forward, BYOC, bring your own container, use openshell, run openshell, CLI usage, manage sandbox, manage provider, gateway add, gateway select.
Create lean-spec style GitHub issues as specs for human-AI aligned implementation on the current repo. Use when asked to "create a spec", "write a spec issue", "spec this feature", "spec this", or when planning work that needs a specification before implementation. Follows the lean-spec SDD methodology — small focused specs (<2000 tokens), intent over implementation, context economy. Creates GitHub issues with Overview, Design, Plan, Test, Alignment, and Notes sections. Repo-specific area taxonomy, sister-skill names, custom body sections (e.g. Provider impact / Schema impact / Reach), and additional principles are overlaid by the consumer repo's CLAUDE.md and its `*-dev-process` / `*-pre-push` / `*-pr-lifecycle` sister skills — read those first when the repo isn't obvious.
Use whenever the user mentions LLM prompt/prefix cache misses, cached_tokens=0, cache_read_input_tokens/cache_creation_input_tokens, prompt_cache_key, cache_control/cachePoint placement, stable prefixes, tool/schema stability, TTFT/prefill latency, OpenAI/Claude/Bedrock/OpenRouter routing, vLLM/SGLang KV reuse, or LLM cost/speed regressions on repeated long prompts. Use when reviewing LLM request shape changes: prompt text, message order, request builders, tools, schemas, response_format, provider API surface, model/router settings, agent loop structure, context compaction, or inference deployment. Use for speeding up agents only when prompt-cache stability, TTFT, or cache cost is central. Do not use for generic prompt writing, generic RAG design, token counting, or non-LLM performance.