AI ワークフローに合うスキルを見つけよう。
bio-imaging-mass-cytometry-interactive-annotation
Interactive cell annotation and image QC for IMC/MIBI using napari, napari-imc, Mantis Viewer, and cytomapper, covering the pixels-to-cell-table bridge, overlaying masks to catch segmentation/spillover artifacts, inter-annotator variability as the accuracy ceiling, contrast-as-threshold, and building class-balanced ground-truth label sets. Use when manually…
bio-analytical-validation
Treats a ctDNA assay as a molecule-counting experiment at the Poisson edge and builds its analytical-validation case the measurement-science way. Covers the genome-equivalent currency (~330 haploid copies/ng), the lambda = input_GE x VAF sampling ceiling (lambda>=3 for ~95% detection), the error-suppression ladder (raw NGS ~1e-3 -> single-strand UMI ~1e-4/1…
bio-metabolomics-pathway-mapping
Maps metabolomics results to biological pathways via over-representation (ORA), metabolite-set enrichment (MSEA/QEA), mummichog/PSEA on raw m/z peaks, and network-diffusion enrichment (FELLA), with correct background-set construction and honest interpretive ceilings. Use when interpreting differential metabolites or an untargeted LC-MS feature table in path…
wendy-security-baselines
Security invariants every Wendy interop change must respect, distilled from the AAA contract. Use when: (1) reviewing or writing any code touching pki-core, wendy-auth, cloud, wendy-proxy, or wendy-agent interop, (2) designing auth, tokens, or credentials, (3) questions about the platform cap or policy ceilings, (4) SSF/CAEP events or revocation, (5) PATs, …
agent-cost-modeling
Model the cost of an LLM agent before it ships, and after. Use when the user is planning a deployment, comparing patterns, choosing a model tier, or justifying a budget and mentions tokens per task, cost per task, unit economics, cost ceiling, cache hit rate, ReAct cost, multi-agent cost, or asks "how much will this cost?" / "is this economical at scale?".
load-testing
Measures how a system behaves under load and finds where it breaks — throughput ceilings, latency under concurrency, and failure modes at saturation. Use this whenever the user mentions load testing, stress testing, benchmarking, capacity planning, an upcoming traffic spike, or asks how many users the system can handle. For making already-identified slownes…
agentprivacy-dragon
Root equation and complete Privacy Value Model V4 overview for 0xagentprivacy. Activates when discussing V(π,t), the sovereignty value equation, proven bounds (reconstruction ceiling R<1), conjectured properties (golden ratio φ optimality), or any foundational question about how privacy creates measurable value. Use when the user needs the complete model, e…
paid-performance-marketer
Senior Paid Performance Marketer (15+ yr calibration · Google Ads + Meta Ads + LinkedIn Ads). Owns paid-channel strategy across the 4 Nexus brands (DR · NRPG · RestoreAssist · CARSI) within Phase 1.2 80/20 risk posture and pilot-scale capital ceilings ($1–3k DR · $500–1k NRPG · $500 RA cold-search · CARSI feed-only). Produces single-variable paid-test desig…
aihive-en-batch-video-production-planner
Use for batch video production, content production workflow, video pipeline. Organize a video backlog into dependency-aware production batches with asset requirements, review gates and budget ceilings. An AI-HIVE workflow; use supported model-powered steps when needed. Website: https://ai-hive.iclip.cn/chat
automatic-triton-programming
Train specialized LLMs to generate optimized Triton GPU kernels using RL with dual rewards for correctness and syntax compliance. 8B model achieves parity with Claude-Sonnet and DeepSeek-R1 by combining supervised fine-tuning on curated code pairs with RL exploration beyond imitation learning ceilings.
brightdata-rate-limits
Analyze and design Bright Data concurrency and backoff controls from observed provider signals and owned budgets instead of invented global limits. Use when handling 429 responses, dataset job ceilings, or uneven proxy pressure. Trigger with: "tune Bright Data concurrency", "handle Bright Data 429", "set a dataset job budget".
brightdata-rate-limits
Analyze and design Bright Data concurrency and backoff controls from observed provider signals and owned budgets instead of invented global limits. Use when handling 429 responses, dataset job ceilings, or uneven proxy pressure. Trigger with: "tune Bright Data concurrency", "handle Bright Data 429", "set a dataset job budget".
building-services
Comprehensive building services knowledge for architects covering HVAC system selection and spatial impact, plumbing and drainage design, electrical systems and power distribution, vertical transportation (elevators and escalators), fire protection systems (sprinklers, detection, smoke control), and MEP coordination strategies including ceiling void allocat…
convergence-monitoring
Detecting whether agent iterations are converging toward a stable solution or hitting a ceiling. Covers convergence signals, ceiling detection, non-convergence diagnosis, test pass rate as a convergence metric, and forward progress tracking for large projects. Trigger phrases: "convergence", "is the agent converging", "ceiling detection", "when to stop iter…
cpi-escalation-calculator
Calculates CPI rent escalations per lease-specific clause definitions, handles year-over-year, cumulative-from-base, and compounded methods, applies floor/ceiling logic, generates tenant notification letters and projected rent schedules.
doordash-spend-guard
Hard spending policy for agent-driven DoorDash ordering through the DoorDash CLI (dd-cli). Per-order ceiling, daily/weekly/monthly caps, cooldown between orders, and blocked hours — enforced deterministically by routing every cart-mutation and checkout through the dd-guard wrapper script, which prices the cart, checks the policy against a persistent spend l…
dynamic-pricing-ecommerce
Design a controlled dynamic-pricing or repricing system for ecommerce products. Use when a seller asks for demand-based, inventory-based, competitor-responsive, or time-based price rules; SKU eligibility; price floors and ceilings; automation approvals; simulations; monitoring; or rollback plans across Amazon, Shopify, TikTok Shop, Walmart, eBay, or other c…
ectheory-submission
Use when running the final pre-submission preflight for Econometric Theory (ET) via ScholarOne / Manuscript Central — single embedded-font PDF, single-anonymous (no double-blind anonymization), APA author-date references, the 50-page ceiling, the optional cover letter, and the Supplementary Material file.
An independently imported catalog with original authors, licenses and source links. Classification is not a security audit.
Sources and import coverage