E2E gate — verifies that applied patches produce a working, numerically sane end-to-end inference through the OpenVINO plugin. Handles HuggingFace/optimum-intel, native OV conversion (ovc/convert_model), and ONNX. Used by orchestrators as the mandatory gate before any PR is published.

Use this skill when the user wants to build tool/scripts or achieve a task where using data from the Hugging Face API would help. This is especially useful when chaining or combining API calls or the task will be repeated/automated. This Skill creates a reusable script to fetch, enrich or process data.

Run evaluations for Hugging Face Hub models using inspect-ai and lighteval on local hardware. Use for backend selection, local GPU evals, and choosing between vLLM / Transformers / accelerate. Not for HF Jobs orchestration, model-card PRs, .eval_results publication, or community-evals automation.

Set up an isolated Python environment for SageMaker / AWS work, with the right Python version and current boto3. Use this skill whenever Python code will be executed for a SageMaker deployment, training job, or any AWS automation — including when about to run `pip install`, when about to invoke `boto3`, when creating or activating a virtualenv, or when the user asks to "set up the environment". Never use system Python and never `pip install` into it. Always isolate. This skill prevents the most common failure modes: wrong Python version, dependency conflicts, and stale SDKs.

Kubernetes network root cause analysis skill powered by Kubeshark MCP. Use this skill whenever the user wants to investigate past incidents, perform retrospective traffic analysis, take or manage traffic snapshots, extract PCAPs, dissect L7 API calls from historical captures, compare traffic patterns over time, detect drift or anomalies between snapshots, or do any kind of forensic network analysis in Kubernetes. Also trigger when the user mentions snapshots, raw capture, PCAP extraction, traffic replay, postmortem analysis, "what happened yesterday/last week", root cause analysis, RCA, cloud snapshot storage, snapshot dissection, or KFL filters for historical traffic. Even if the user just says "figure out what went wrong" or "compare today's traffic to yesterday" in a Kubernetes context, use this skill.

Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Use whenever the task produces or modifies anything a user will see rendered — websites, landing pages, web apps, dashboards, React/HTML/Vue components, artifacts with visual output, style overhauls, or "make this look better" requests — even if the user never says the word "design". Covers aesthetic direction, typography, environment constraints (fonts, Tailwind, assets), and when to converge on convention instead of chasing distinctiveness.

Validate whether an analysis is accurate, well-supported, and ready to share or use for a decision. Use when reviewing methodology, calculations, comparisons, visuals, caveats, or conclusions.

Diagnose why a metric changed or differs from expectation. Use when the task is to identify likely drivers of a metric movement, anomaly, gap, or discrepancy.

Prepare KPI readouts, scorecards, WBR/MBR/QBR updates, and executive summaries from quantitative business or product metrics; use when the task is to report status, compare against targets, explain validated drivers, and state operating implications.

Assess whether structured data, query results, dashboards, or analytical evidence are trustworthy enough to use. Use when the task is to check data quality, reconcile conflicting sources or metric definitions, or decide whether evidence is safe to cite.

Review a GitHub pull request from its link, read the PR description, inspect the code locally only when useful, and judge whether the change is safe to run from a security and runtime-safety perspective. Use only after the user pastes a PR URL. Handle one PR at a time, make a clear merge/close/supersede recommendation, and keep all GitHub review and merge actions with the user.

Guide for contributing to Trellis documentation and marketplace. Covers adding spec templates, marketplace skills, documentation pages, and submitting PRs across both the Trellis main repo and docs repo. Use when someone wants to add a new spec template, add a new skill to the marketplace, add or update documentation pages, or submit a PR to this project.

Guide for contributing to Trellis documentation and marketplace. Covers adding spec templates, marketplace skills, documentation pages, and submitting PRs across both the Trellis main repo and docs repo. Use when someone wants to add a new spec template, add a new skill to the marketplace, add or update documentation pages, or submit a PR to this project.

Plan and orchestrate multi-slide PowerPoint creation from scratch. Use before generating a full deck with subagents: classify each slide type, enforce visual variety, set typography/spacing rules, and run text-based QA to catch content issues.

Codex-only writing and layout overlay for AI Berkshire investment research reports. Use whenever Codex creates, rewrites, revises, or critiques company/industry/fund research reports, especially long-form Markdown reports that need financial rigor, readable business mechanics, contrarian analysis, valuation-to-action guidance, investor-specific recommendations, restrained typography, and clear buy/hold/sell signals. Do not use this to modify Claude Code slash-command sources.

Best practices for designing reproducible ML experiments. Use when planning ablations, baselines, or controlled experiments.

Best practices for reinforcement learning policy optimization. Use when working on RL agents, PPO, SAC, or reward design.

Use when the user wants Cursor to learn from recent local sessions, asks for an offline sleep or dream cycle, wants to consolidate recurring work into a Cursor skill, or requests SkillOpt-Sleep status, harvest, dry-run, run, scheduling, review, or adoption. Drives the validation-gated skillopt_sleep engine with Cursor transcripts and the optional Cursor Agent CLI backend.

Use when the user wants Codex to self-improve from past usage, asks about a nightly/offline 'sleep' or 'dream' cycle, wants Codex to review past sessions, learn preferences, consolidate memory/skills, run dry-run/run/adopt/status for SkillOpt-Sleep, or schedule background self-optimization. Drives the skillopt_sleep engine: harvest past sessions -> mine recurring tasks -> replay through a selected backend -> consolidate validated memory + skills behind a held-out gate.

Use when the user wants their Claude agent to self-improve from past usage, asks about a nightly/offline 'sleep' or 'dream' cycle, memory/skill consolidation, or says things like 'make my agent better the more I use it', 'review my past sessions', 'learn my preferences', 'consolidate what you learned', 'run the sleep cycle', or wants to schedule background self-optimization. Drives the skillopt_sleep engine: harvest past sessions -> mine recurring tasks -> replay through a selected backend -> consolidate validated CLAUDE.md/SKILL.md behind a held-out gate.