Skills

rill-connector

Detailed instructions and examples for developing connector resources in Rill

subagent-driven-development

Use when executing implementation plans with independent tasks in the current session

boltz-small-molecule-screen

Screen existing small-molecule libraries with Boltz. Use when docking, scoring, or ranking a supplied SMILES or compound library against a target; also returns free Tier-1 ADME/ADMET (solubility, permeability, lipophilicity/logD) per molecule. Not for de novo molecule design, one-off docking, or ADM

testdino-manual-runs

Use when the user wants to manage a manual execution run or update case-level results inside a run — listing runs, creating runs for a release, inspecting a run, assigning cases, or marking case results (passed/failed/blocked/skipped/retest/untested). Accepts counter-style IDs like RUN-12 and TC-156

scrape-codegen

Generate web-poet page object code from an extraction spec

miro-diagram

Use when the user wants to create or update a diagram on a Miro board.

claims-authorization

Claims transformation and profile service patterns for Duende IdentityServer — IProfileService, IClaimsTransformation, claim type mapping, token claim filtering, extension grant validators, and dynamic claims loading.

explicit-checker

Scans lyrics for explicit content and verifies that explicit flags match actual content. Use before Suno generation or release to ensure accurate content ratings.

identityserver-upgrade-v7-to-v8

Migrating Duende IdentityServer from v7.4 to v8.0: breaking changes, API replacements (ICache→HybridCache, IClock→TimeProvider), CancellationToken additions, EF migrations, and step-by-step upgrade guide.

finetuning-technique

Selects a fine-tuning technique (SFT, DPO, RLVR, or RLAIF) for the user's use case and validates it against the selected model's available recipes. Use when the user has decided to finetune and needs to choose a technique, or when the technique needs to be validated against a model. Requires a base

you-free

Use the free You.com MCP profile for unauthenticated basic web search with `you-search` only.

together-sandboxes

Remote Python execution in managed sandboxes on Together AI with stateful sessions, file uploads, data analysis, chart generation, and notebook-like runs via the Sandboxes API. Reach for it whenever the user wants managed remote Python execution instead of local execution, raw clusters, or full mode

on-demand-cluster

Use when the user wants to create, list, describe, or delete an on-demand (Vector Lake / VectorLake) cluster. On-demand clusters auto-suspend after an idle TTL and are intended for ad-hoc query workloads against a Vector Lake.

recommend-contacts

Get AI-powered contact recommendations at a target company based on your ZoomInfo interaction history. Provide a company name or domain and optionally a use case.

cryptography

Cryptanalysis techniques — lattice attacks, padding oracles, weak-RNG exploitation, signature forgery, secret-sharing recovery.

you-web

Use You.com MCP tools for current web search, URL content extraction, cited web synthesis, and x402-aware web access.

design-md

Create and manage DESIGN.md files. Useful for capturing design direction, tokens, and visual rules in a single source of truth.

finding-deleted-feature-flags

Find feature flags that were soft-deleted in the active project within a recent time window. Use when the user asks "what flags were deleted in the last N days", "show me recently deleted feature flags", "who deleted flag X", "audit recent flag deletions", or anything similar. Handles the non-obviou

you-discover

Route You.com integration planning through the you-discover MCP tool, Docs MCP, and direct API options.

known-bad

A test fixture that intentionally fails Pass-2 checks.

vector

Use when the user wants to search, query, insert, upsert, get, or delete vectors in a Milvus collection.

algorithmic-art

Create generative art using p5.js with seeded randomness so every render is reproducible. Useful for procedural posters, motion-style stills, and artistic frame studies.

check-usage

Reports the Hunter account's plan, remaining credits, and usage. Use when the user asks how many credits they have left, what plan they're on, or how much of their quota they've used.

dispatching-parallel-agents

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies