Loading...
Loading...
Found 2,435 Skills
Performs gap analysis on NVIDIA TAO Visual ChangeNet (VCN) Classify experiments by invoking the data-services container (`tao_toolkit.data_services` from `versions.yaml`) directly via `docker run … gap_analysis vcn_aoi …` — picks the optimal decision threshold, ranks per-sample weakness, and emits a top-K weakest parquet expanded per-lighting for downstream augmentation. Use when analyzing VCN classification failures, picking SDA augmentation targets, auditing PASS/NO_PASS boundary cases, or running DEFT gap analysis on an AOI ChangeNet model.
Evidence-based assessment of whether an SAP API/interface usage scenario aligns with the SAP API Policy (v.4.2026a). Use whenever someone asks whether a way of calling SAP is allowed/compliant — e.g. Published API vs internal/private/"confidential" API status, "Documented Use", whether a third-party tool / iPaaS / middleware / RPA bot / AI agent / MCP server may call SAP APIs, agentic or generative-AI access to SAP, bulk data extraction or replication into a lake/warehouse, custom Z/Y OData or RFC/BAPI wrappers and Clean Core, ADT/developer-tooling boundaries, ODP-RFC and other "not permitted" interfaces, partner Integration Certification, or RISE integration remediation. Trigger even when the policy is not named, e.g. "are we allowed to…", "is it compliant to…", "can we connect X to SAP…", "will this break under the new API policy". Produces a sourced technical assessment with a confidence level — explicitly NOT legal advice and NOT a final SAP compliance decision.
How to develop Lightboard modules for Risuai. Also includes Miniboard renderer development process.
Entry point for evals. Use when the user asks for help with evals, does not know where to begin, or asks for something no other skill in this plugin matches. Do NOT use when a more specific skill in this plugin already matches; load that skill directly.
Iteratively improve any output until measurable criteria are met. Use when the user wants to refine existing work against specific standards — whether it's code, prose, data, config, or any other artifact. Triggers on phrases like "improve this", "make it better", "iterate", "refine", "keep improving", "not good enough yet", "optimize this", "polish this", "tighten this up", or when the user provides criteria and wants repeated improvement until they're satisfied. Also use when the user gives feedback on output and expects you to keep refining, even if they don't say "improve" explicitly.
Analyze lending products including mortgages, HELOCs, and personal loans with amortization and comparison tools. Use when the user asks about mortgage comparison, fixed vs ARM rates, loan qualification, amortization schedules, extra payments, or buying points. Also trigger when users mention 'monthly payment calculation', '15-year vs 30-year mortgage', 'PMI', 'APR vs interest rate', 'HELOC', 'home equity', 'should I buy down the rate', 'biweekly payments', or ask how much house they can afford.
Behavioral classification, performance analysis, and trading style detection for Solana wallets
Run an iterative code-improvement hill-climb against real Datadog LLM-Obs data, locally, with Claude Code as the agent. Establishes a baseline eval, makes one focused change, re-scores with the same harness, keeps the change if it improves the score in the goal's direction (labeling within-noise gains tentative), and repeats. Use when the user says "run an auto experiment", "hill-climb this code", "iteratively improve X and measure the delta", "optimize this prompt/file against my traces", "auto-optimize against LLM-Obs", or wants the local equivalent of the auto_experiments worker. Works from a local dataset file, an ml_app, a dataset_id, or a list of trace_ids.
Check real capabilities before recommending a solution.
Create, edit, and refine agent skills through co-development and eval loops. Use for ANY question about skills or request to create/modify them.
Turn a real agent failure into one reproducible eval-harness case plus the smallest knowledge change — failing case first, one knowledge owner, semantic assertions, before/after evidence through the repo's configured harness commands. Use for "add harness case", "agent got this wrong", "extend the harness", "rozszerz harness".
Fan out N parallel workers on slices of a job or on a race, collect every result, and return one evidence-backed report. Use for wide coverage, audits, races between approaches or exploration, or for /ds-swarm, 'swarm this', 'split this across workers'.