Loading...
Loading...
Found 61 Skills
Guide for Convex backend development fundamentals including function types (queries, mutations, actions), layered architecture, HTTP actions, and the core mental model. Use when building Convex backends, creating queries/mutations/actions, implementing HTTP webhooks, or understanding Convex's reactive data model. Activates for Convex project setup, function definition, API design, or backend architecture tasks.
Switch model profile for kata agents (quality/balanced/budget). Triggers include "set profile", "set profile".
Meta-skill for internal codebase exploration at varying depths (quick/deep/architecture)
Track and analyze US government shutdown liquidity impacts by monitoring TGA (Treasury General Account), bank reserves, EFFR, and SOFR data from FRED API. Use when user wants to (1) analyze current or past government shutdown effects on financial markets, (2) track liquidity conditions during fiscal policy disruptions, (3) assess "stealth tightening" effects, (4) compare shutdown episodes across different monetary policy regimes (QE vs QT), or (5) generate liquidity stress reports with historical context. Recommended usage frequency is weekly on Wednesdays after TGA/reserve data releases.
Unified paper audit skill supporting Chinese & English academic papers. Supports LaTeX (.tex), Typst (.typ), and PDF (.pdf) input formats. Three modes: self-check (pre-submission), review (peer review simulation), gate (quality gate pass/fail). Use when user mentions: audit, review, check paper, paper quality, pre-submission check, score paper, or any paper auditing task, polish paper, deep polish, adversarial review, refine writing.
Deploys infrastructure components via Helm charts on TrueFoundry. Supports any public or private OCI Helm chart including databases (Postgres, MongoDB, Redis), message brokers (Kafka, RabbitMQ), and vector databases (Qdrant, Milvus). Uses YAML manifests with `tfy apply`. Use when installing Helm charts or deploying infrastructure on TrueFoundry.
Implements the NOWAIT technique for efficient reasoning in R1-style LLMs. Use when optimizing inference of reasoning models (QwQ, DeepSeek-R1, Phi4-Reasoning, Qwen3, Kimi-VL, QvQ), reducing chain-of-thought token usage by 27-51% while preserving accuracy. Triggers on "optimize reasoning", "reduce thinking tokens", "efficient inference", "suppress reflection tokens", or when working with verbose CoT outputs.
Use when deploying ANY machine learning model on-device, converting models to CoreML, compressing models, or implementing speech-to-text. Covers CoreML conversion, MLTensor, model compression (quantization/palettization/pruning), stateful models, KV-cache, multi-function models, async prediction, SpeechAnalyzer, SpeechTranscriber.
Professional network reconnaissance and port scanning using nmap. Supports various scan types (quick, full, UDP, stealth), service detection, vulnerability scanning, and NSE scripts. Use when you need to enumerate network services, detect versions, or perform network reconnaissance.
Develops resources for FiveM using the Qbox Project (qbx_core). Covers the exports-based API, bridge compatibility, Ox integration (ox_lib, ox_inventory), and best practices. Use when the user works with FiveM, Qbox, qbx_core, or mentions `exports.qbx_core`, `QBX.PlayerData`, or `ox_lib`.
Coordinates 3 specialized audit workers (query efficiency, transaction correctness, runtime performance). Researches DB/ORM/async best practices, delegates parallel audits, aggregates results into single Linear task in Epic 0.
Comprehensive knowledge of all 23 Gang of Four design patterns with progressive disclosure (Quick/Practical/Deep), pattern recognition for problem-solving, and philosophy-aligned guidance to prevent over-engineering.