Use when structuring a FastAPI application, designing dependency injection chains, defining Pydantic v2 schemas, adding JWT authentication, or writing async route tests with httpx.
This skill should be used when the user reports "macstack lint fails", "prototype does not resolve", "env keys missing", "scaffold broke my files", "cross-stack reference does not work", or any macstack-dev skill errors out. Diagnoses the common failure modes of the macstack.json toolchain.
Use when structured YouTube data is needed: pasted video/channel/playlist links, transcripts for analysis, video metadata, channel upload history, search results, or playlist contents — without Google API quotas or OAuth. Triggers on YouTube URLs, creator names, topic research, or any request needing YouTube content, even if not mentioned explicitly. Not for uploads, account management, or written-source-only research.
Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it. Use for /arena, 'arena this', 'throw it in the arena', or when one attempt at a non-trivial artifact would lock in the wrong shape.
Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6× speedup), reducing latency for real-time applications, or deploying models with limited compute. Covers draft models, tree-based attention, Jacobi iteration, parallel token generation, and production deployment strategies.
Expert patterns for Segment Customer Data Platform including Analytics.js, server-side tracking, tracking plans with Protocols, identity resolution, destinations configuration, and data governance best practices.
Design rate-limit and quota Redis/memory keys for JavaScript/Node APIs: identity selection (API key, tenant, user, IP, route), dual-key patterns, normalization, cardinality safety, and anti-bypass. Use for owned services — not to evade third-party rate limits.
Operator toolkit for nf-core/pacsomatic matched tumor-normal workflows from BAM inputs. Use this skill when the user needs to validate run inputs, generate pacsomatic-compliant samplesheets, prepare reproducible Nextflow launch artifacts, run locally or submit to schedulers (LSF/Slurm/PBS/SGE), and triage execution failures. Triggers on requests to run pacsomatic, prepare launch commands/scripts, perform dry-run checks, or troubleshoot pipeline startup and scheduler submission errors.
Guide for BOOTSTRAP.md (first-run setup ritual) and BOOT.md (gateway restart checklist) in OpenClaw. Use this skill whenever the user is setting up a new agent for the first time, configuring onboarding flows, creating first-run discovery processes, or defining what should happen on gateway restart. Even questions like "what should happen when the agent starts for the first time", "how do I initialize a fresh agent", or "what runs on reboot" need this skill.
Use when Power BI outputs need executive commentary for monthly close, sales review, O2C review, supply chain review, plant performance, service review, quality review, or board reporting.
Lab-oriented notes for Rubeus (Kerberos abuse toolkit) on owned/authorized Active Directory labs: common verbs (asktgt, asktgs, s4u, ptt, harvest, kerberoast-related flows), opsec caveats, and defensive detections. Not for unauthorized AD attacks. Triggers: Rubeus.exe, asktgt, s4u2self, pass-the-ticket lab, kerberoast lab.
Review and critique existing designs, websites, or frontend code against design principles. Checks for common anti-patterns like generic fonts, poor contrast, inconsistent spacing, and lack of visual hierarchy. Use when the user asks to "review my design", "what's wrong with this layout", "critique my website", "how can I improve the design", "audit the UI", "check my frontend", "make it look more professional", or "why does this look off". Produces actionable feedback with specific fix suggestions referencing other skills.