Install, set up, verify, update, pin, uninstall, or troubleshoot the ToolUniverse plugin on Google Antigravity (AGY / Antigravity IDE / Antigravity 2.0). ALWAYS consult this skill for any of those — don't answer from memory, because the exact CLI name (agy), the "agy plugin install <path>" flow, the uvx tooluniverse MCP server, and the API-key env vars are easy to get wrong. Use it whenever someone wants to get ToolUniverse (or "the 1000+ scientific tools" / "the harvard tools") working on Antigravity, says the Antigravity plugin or its tools/skills won't load, hits a uvx or MCP-server startup error, asks how Antigravity updates it, wants to pin or remove it, or finds it running an old tool version. Not for the Codex plugin (use tooluniverse-codex-plugin) or Claude Code plugin (use tooluniverse-claude-code-plugin), for running research with the tools, or for authoring new tools or skills.

Pharmacokinetic (PK) analysis of concentration-time data — non-compartmental analysis (NCA) for Cmax, Tmax, AUC (0-t and 0-∞), terminal half-life, clearance (CL), volume of distribution (Vd), MRT, and absolute bioavailability (F). Also one-compartment fitting. Use when you have plasma/serum drug concentrations over time after a dose and need PK parameters, or to compute bioavailability from IV + oral AUCs. NOT for ADMET property prediction from structure (use tooluniverse-admet-prediction).

Cross-ancestry / cross-biobank phenome-wide association (PheWAS) and replication. Given ONE variant (rsID) or ONE gene, look up every phenotype it associates with across European/UK (UKB-TOPMed), Finnish (FinnGen), Japanese (BioBank Japan), and Taiwanese (TPMI) biobanks, plus exome-wide gene-burden PheWAS (Genebass), then judge whether an association replicates across ancestries or is population-specific. Use whenever the user asks "what else is this variant/gene associated with", "does this association replicate in other ancestries / biobanks", "is this effect East-Asian-specific", "pleiotropy of rsXXX", "phenome scan", or wants to compare effect sizes/allele frequencies of a variant across populations. NOT for the forward direction (trait → which SNPs: use the gwas-* skills), NOT for fine-mapping a locus (use tooluniverse-gwas-finemapping), and NOT for single-SNP mechanism tracing in one population (use tooluniverse-gwas-snp-interpretation).

When the user wants to plan, script, produce, or optimize App Store Preview videos or Google Play promo videos — the autoplay videos that show in App Store/Play Store search and product pages. Use when the user mentions "App Preview", "preview video", "app store video", "promo video", "Play Store video", "video poster frame", "YouTube promo for Play Store", "30 second app video", "video script", "video specs", or "should I add a preview video". For static screenshots, see screenshot-optimization. For A/B testing the video, see ab-test-store-listing. For broader creative briefs, see screenshot-optimization (covers stills).

Guided journey from a stalled, plateaued business to one with an honest diagnosis, a working operating rhythm, and offers repriced to real value. Orchestrates eight skills phase by phase - good-strategy-bad-strategy, traction-eos, high-output-management, team-topologies, drive-motivation, lean-analytics, negotiation, monetizing-innovation - asking the user questions at every decision point and recording results in the project docs/ folder (STRATEGY.md, OPERATIONS.md, METRICS.md, IMPROVE-BUSINESS-PLAN.md) so the journey resumes across sessions. Use when the user wants to fix a business that has plateaued, diagnose why growth stalled, tighten strategy and execution, re-motivate a team, or says 'revenue is flat and I do not know why'. Starting from scratch with no customers: use create-business. Once the fundamentals work and the goal is expansion: use grow-business. When the product itself drags the business down: use improve-app. For one framework in isolation, invoke that skill directly.

Guided journey from a website with traffic it under-converts to a research-driven growth engine that captures more leads, persuades more buyers, sells a sharper offer, and earns referrals. Orchestrates eight skills phase by phase - cro-methodology, scorecard-marketing, storybrand-messaging, made-to-stick, influence-psychology, hundred-million-offers, contagious, one-page-marketing - asking the user questions at every decision point and recording results in the project docs/ folder (WEBSITE.md, OFFER.md, MARKETING.md, GROW-WEBSITE-PLAN.md) so the journey resumes across sessions. Use when the user wants to raise conversion on a site that already has traffic, capture more leads, sharpen a weak offer, add referral loops, or says 'my site gets visitors but nobody buys'. If a broken funnel or usability friction is the real blocker, run improve-website first; if there is no site yet, use create-website; for one leaking flow, conversion-optimization. For one framework in isolation, invoke that skill directly.

Explore an existing PostgreSQL database before answering questions about its data or writing SQL. Use this skill whenever a user asks for a query or a data-backed answer against an unfamiliar schema (counts, missing or failed records, recent changes), asks where a business concept lives, or asks how tables, joins, views, routines, triggers, RLS, or extensions work. Find the relevant objects with read-only pg_catalog queries, then request approval before inspecting data-derived statistics or rows. Not a schema-design or migration guide.

Creates ToolHive release PRs by analyzing commits since the last release, categorizing changes, recommending semantic version bump type (major/minor/patch), and triggering the release workflow. Use when cutting a release, preparing a new version, checking what changed since last release, or when the user mentions "release", "version bump", or "cut a release".

Use this skill when adding a new optimized kernel or operator to veomni/ops/. Covers the full lifecycle: understanding VeOmni's ops architecture (KERNEL_REGISTRY + OpSlot dispatch, with a thin function-pointer shim for a few legacy global ops), implementing the kernel, registering it, adding tests, and documenting it. Trigger: 'add op', 'new kernel', 'add attention variant', 'new fused op', 'add triton kernel', 'optimize operator'.

Create a pull request for the current branch. Handles uncommitted changes, generates a PR title matching the `[{modules}] {type}: {description}` format enforced by CI, and fills in the PR description template. Trigger: 'create pr', 'open pr', 'submit pr', 'make pr'.

Builds generative AI applications on Amazon Bedrock. Covers model invocation (Converse API, InvokeModel), RAG with Knowledge Bases, Bedrock Agents, Guardrails, and AgentCore (including the Harness managed agent loop). Applies when invoking models, setting up Knowledge Bases, creating agents, applying guardrails, deploying to AgentCore, migrating/porting/converting a Bedrock Agent (including inline agents) to an AgentCore Harness, troubleshooting Bedrock errors (ThrottlingException, AccessDeniedException), or choosing models (Claude, Llama, Nova, Titan). Also for prompt caching, quota and throttling diagnosis, cost tracking, migrating between Claude model generations (4.5 to 4.6 to 4.7), chunking strategies, API selection (Converse vs InvokeModel), guardrail capabilities, and model selection. Also covers AgentCore Payments (x402, microtransactions, Payment Manager, Connector, Instrument, Coinbase CDP, Stripe Privy, paid endpoints, agent payments). NOT for custom model training, Rekognition, or Comprehend.

Pull AWS Security Agent findings (penetration tests and code reviews) and drive remediation. Use this whenever the user mentions Security Agent, security findings, pentest or penetration test results, code review findings, vulnerabilities found in their AWS account, "what did the security scan find", remediating or triaging security risks, or wants to start fixing reported vulnerabilities — even if they don't name the service explicitly. Trigger it for phrases like "get my security findings", "what vulnerabilities do we have", "let's fix the pentest results", or "triage the security report". The skill discovers scans, exports findings to a gitignored local directory (so sensitive exploit detail is never committed), produces a prioritized triage summary, and offers to start fixing the highest-risk issues.

Survey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on source code — never implements, fixes, or refactors anything itself. Use when asked to audit a codebase, find improvement opportunities (bugs, security, performance, test coverage, tech debt, migrations, DX), suggest features or where to take the project next (roadmap, product direction), or generate handoff plans for another agent to implement.

Authors, refactors, and consolidates Agent Skills PRP-style. Use when the user wants to "create a skill", "write a new skill", "trim a SKILL.md", "split a skill into references", "consolidate workflow skills", "replace duplicated skill logic with composition", redesign a skill workflow, or invokes $prp-meta-skill.

Write a hermetic "tiny" model-saving test for an mflux model — a fast twin of the slow save/load test that runs the real ModelSaver/WeightLoader/WeightApplier seam on real component classes at toy dimensions, with no downloads or image generation. Use when asked to "make tiny test for <model>".

Search and recall relevant memories from past sessions via memsearch. Use when the user's question could benefit from historical context, past decisions, debugging notes, previous conversations, or project knowledge -- especially questions like 'what did I decide about X', 'why did we do Y', or 'have I seen this before'. Also use when you see `[memsearch] Memory available` hints injected via SessionStart or UserPromptSubmit. Typical flow: search for 3-5 chunks, expand the most relevant, optionally deep-drill into original transcripts via the anchor format. Skip when the question is purely about current code state (use Read/Grep), ephemeral (today's task only), or the user has explicitly asked to ignore memory.

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.

Recommend the right trading workflow, skillset, API profile, and setup path from a natural-language goal. Use this as the on-ramp when a user expresses a trading or investing goal and needs to know which skill/workflow to use, where to start, or whether something works without paid API keys — e.g. "where do I start", "which skill should I use", "I want to swing trade only when the market is favorable", "what works without API keys", "どれを使えばいい", "API キー無しで 使えるものは". Routes and explains only; it never executes trades or auto-runs other skills, and it is honest when no workflow has shipped yet.

Separate a strategy return series into declared baseline exposure and residual edge with returns-based OLS attribution, HAC inference, rolling stability, alternate-baseline sensitivity, and regime breakdowns. Use when evaluating whether backtest, out-of-sample, or live returns contain independent alpha beyond market, equal-weight, momentum, sector, or user-supplied factor returns; when explaining whether a drawdown came from baseline exposure or strategy-specific behavior; or when a strategy needs an attribution quality gate after backtesting. Do not use for holdings-based Brinson attribution, feature-level Shapley explanations, or analysis from summary metrics without a dated return series.

Group a session-metrics session's turns into higher-level SEMANTIC TASKS ("what was I actually trying to do") and render a Tasks companion page (*_tasks.html + *_tasks.md) with a worth-it / mixed / likely-waste verdict per task. Trigger when the user runs /task-breakdown, when session-metrics suggests a task breakdown after a JSON export, or when the user asks to "group my turns into tasks", "what tasks did this session cover", "which work was worth it vs wasted", or "break this session into tasks". Consumes the deterministic per-request breakdown (request_units) from a session-metrics JSON export — it never re-derives cost or token numbers. Args: $ARGUMENTS[0] = path to a session-metrics JSON export (optional; if omitted, generate one first).