productivity▌

Analyze natural language text for tokenization, part-of-speech tagging, named entity recognition, sentiment analysis, language identification, and word/sentence embeddings. Translate text between languages with the Translation framework. Targets Swift 6.3 / iOS 26+.

Skill by ara.so — Daily 2026 Skills collection.

cowork-plugin-customizer

Type and scope are examples only; adjust to fit the repo and changes.

Verify that requests to your server come from a genuine Apple device running your unmodified app. DeviceCheck provides per-device bits for simple flags (e.g., "claimed promo offer"). App Attest uses Secure Enclave keys and Apple attestation to cryptographically prove app legitimacy on each request.

Stage, commit, and push git changes with conventional commit messages. \n \n Automatically stages all changes, generates conventional commits, and pushes to the remote branch using a provided bash script \n Supports custom commit messages or auto-generates them based on changes \n Includes Claude footer in commits and uses the -u flag to set upstream tracking on first push \n Activates when users request commits, mention pushing to remote, or ask to save work \n

Follow these guidelines when reviewing code for Sentry projects.

Backtesting strategy parameter optimization with VectorBT, generating performance heatmaps and benchmark comparisons. \n \n Accepts strategy name, symbol, exchange, and interval; creates optimization script in backtesting/{strategy}/ directory \n Loads market data from OpenAlgo via .env configuration or directly from DuckDB; uses TA-Lib for all indicators with OpenAlgo ta for specialty indicators like Supertrend and Donchian \n Tests parameter combinations across sensible ranges (e.g., EMA 5-50

Parallel multi-topic research with independent agents generating structured knowledge bases from any input material. \n \n Launches dedicated research agents for each topic in parallel, each conducting 4–6 rounds of deep retrieval with deduplication checks to avoid keyword overlap \n Accepts three input modes: file-based ( /multi-search @path.md ), direct paste, or explicit topic specification with custom research directions \n Generates structured output with a research overview document, indiv

Analyzes conversation patterns and tool usage to propose targeted skill improvements or user preferences. \n \n Reviews conversation history and tool failures to identify gaps in skill definitions or recurring user preferences \n Proposes one change at a time (either a skill update shown as a diff or a preference addition to CLAUDE.md ) for focused review \n Requires explicit user confirmation before applying any changes to skills or preference files \n Prioritizes failure analysis and user corr