Showing 25891–25920 of 77202 skills
Implement backend async and background processing patterns — event-driven architectures, message queues, async task runners, and worker pools.
a5c-ai/babysitter
Implement reliable background job processing systems — queue management, retry policies, dead-letter handling, and distributed workers.
a5c-ai/babysitter
Integrate database drivers and connectors — connection pooling, query builders, ORM configuration, and multi-database abstraction layers.
a5c-ai/babysitter
Implement email and push notification delivery systems — transactional email, notification templates, delivery tracking, and bounce handling.
a5c-ai/babysitter
Work with Rust async runtimes — Tokio, async-std, executor internals, pinning, wakers, and building high-performance async Rust services.
a5c-ai/babysitter
Implement secure webhook verification — HMAC signature validation, replay attack prevention, idempotency keys, and webhook payload processing.
a5c-ai/babysitter
Implement compression and archiving workflows — gzip, zstd, bzip2, tar, zip, streaming compression, and efficient large-file handling.
a5c-ai/babysitter
Handle date and time manipulation — timezone conversions, duration calculations, date formatting, and internationalization-aware temporal operations.
a5c-ai/babysitter
Demonstrate fluency in code editors and IDEs — keybindings, refactoring tools, debugging workflows, and productivity extensions for VS Code, Vim, or JetBrains.
a5c-ai/babysitter
Transform and manipulate JSON data — jq queries, schema validation, nested object traversal, and JSON-to-CSV or flat-file conversions.
a5c-ai/babysitter
Implement Python functions and modules following best practices — type hints, error handling, testing, and idiomatic Python patterns.
a5c-ai/babysitter
Extract structured data from images and documents using vision models — OCR, layout analysis, table extraction, and visual document parsing.
a5c-ai/babysitter
Implement blockchain consensus protocols — Proof of Work, Proof of Stake, PBFT, Tendermint, and distributed agreement mechanisms.
a5c-ai/babysitter
Analyze and decide between batch and stream processing architectures — latency requirements, cost modeling, and hybrid Lambda/Kappa patterns.
a5c-ai/babysitter
Test ETL pipelines for data completeness, transformation accuracy, schema validation, and end-to-end data flow integrity.
a5c-ai/babysitter
Develop, optimize, and deploy Apache Spark jobs for large-scale batch processing, streaming, and machine learning workloads.
a5c-ai/babysitter
Benchmark and optimize ML model inference — latency, throughput, memory usage, and hardware-specific performance profiling.
a5c-ai/babysitter
Design and train reinforcement learning agents — environment setup, reward shaping, policy gradient methods, and evaluation.
a5c-ai/babysitter
Ensure ML experiment reproducibility — seed management, environment pinning, artifact versioning, and deterministic training validation.
a5c-ai/babysitter
Human-feedback-driven model optimization — preference data collection, reward modeling, policy updates, and alignment evaluation.
a5c-ai/babysitter
Apply statistical hypothesis testing, significance analysis, A/B test evaluation, and distribution comparisons for data science workflows.
a5c-ai/babysitter
Analyze and model time-series data — forecasting, anomaly detection, trend decomposition, and temporal feature engineering.
a5c-ai/babysitter
Validate ML training datasets for quality, bias, completeness, label consistency, and distribution coverage.
a5c-ai/babysitter
Test and validate data visualizations for correctness, accessibility, and rendering consistency across chart libraries and dashboards.
a5c-ai/babysitter
Clean up the local workspace after a dev branch has been merged into main. Verifies the current dev branch is fully merged into origin/main, then switches to main, pulls the latest, deletes the local dev branch, and deletes the remote dev branch if it still exists. STOPS and warns the user if the current branch is not yet merged. Triggers: cleanup workspace, cleanup branch, delete merged branch, finish dev branch, post-merge cleanup
mrc4tt/CS2_VibeSignatures
Convert an existing find-XXXX SKILL.md into a preprocessor Python script, updating configs/<GAMEVER>.yaml and removing the old SKILL.md. Covers xref-string-based and LLM_DECOMPILE-based discovery patterns.
mrc4tt/CS2_VibeSignatures
Create an Agent SKILL.md fallback for an existing find-XXXX finder that relies on a fragile discovery foundation — above all LLM_DECOMPILE (patterns C/D/E), which matches the decompiled shape of a predecessor function against a stored reference and breaks when a symbol is inlined or de-inlined in a way the reference does not cover. The generated fallback coexists with the preprocessor and runs only when it returns failure, recovering every target robustly by decompiling the predecessor and following the inline/de-inline boundary with semantic anchors. Use when a finder broke on a game update, or you want to durably backstop one before it does. The recipe generalizes to any finder foundation. Triggers: create agent skill fallback, add SKILL.md fallback, robust fallback for finder, backstop LLM_DECOMPILE finder, final guarantee skill
mrc4tt/CS2_VibeSignatures
Create a new cpp_tests entry for validating a C++ interface vtable layout against binary reference YAMLs. Creates the .cpp test file in cpp_tests/ and appends a configs/<GAMEVER>.yaml entry under cpp_tests:. Use when a user asks to add vtable layout validation for a new hl2sdk_cs2 interface class.
mrc4tt/CS2_VibeSignatures
Create a GitHub pull request from staged task changes or an already-committed current branch. Deliver source/config/ reference changes together with their computed source-owned `bin_artifacts` closure. PR validation routing is owned by the default-branch trusted workflow; snapshots, gamedata, and manifests are Release-derived only.
mrc4tt/CS2_VibeSignatures
Create a new find-XXXX preprocessor Python script from scratch (no existing SKILL.md), add configs/<GAMEVER>.yaml skill and symbol entries. Covers xref-string-based and LLM_DECOMPILE-based discovery patterns. Use when a GitHub issue or user instruction specifies a new function to find.
mrc4tt/CS2_VibeSignatures