Loading...
Loading...
Found 455 Skills
Systematic 6-phase analysis of external repositories for ideas worth adopting: clone, parallel deep-read, self-inventory, synthesize gaps, targeted audit of affected subsystems, reality-grounded report. Use when evaluating whether an external repo provides value, analyzing repos for useful patterns, or comparing approaches. Do NOT use for general codebase exploration (use explore-pipeline instead).
Dispatch independent subagents in parallel for unrelated problems spanning different subsystems. Use when 2+ failures have independent root causes, multiple subsystems are broken independently, or user requests concurrent investigation. Use for "parallel", "multiple failures", "independent bugs", "fix these concurrently". Do NOT use for related failures, shared-state problems, or exploratory debugging where root cause is unknown.
Access SETI (Space Exploration Telecommunications Infrastructure) APIs. This skill provides Ruby SDK examples.
Use when the user needs ML pipelines, statistical analysis, data preprocessing, feature engineering, model selection, experiment tracking, or data visualization. Triggers: dataset exploration, model training, feature engineering, hyperparameter tuning, experiment tracking setup, statistical hypothesis testing, visualization creation.
Audit a codebase for handcrafted code that duplicates functionality already available in the project's dependencies. Reads package.json, launches parallel exploration agents, verifies replacement feasibility, and produces a structured refactor plan. Audit only -- does not execute changes.
Time-boxed technical investigation with structured output. Use for feasibility studies, architecture exploration, integration assessment, performance analysis, or risk evaluation. Creates spike tasks in ohno, enforces time-boxing, generates spike reports, and creates actionable follow-up tasks.
This skill should be used when finding, tracing, or understanding code in a repository with SymDex available. Trigger it for requests like "where is this defined?", "who calls this?", "what route handles this path?", "show me the file outline", "search this codebase by intent", or any task that would otherwise rely on broad Read/Grep/Glob exploration.
PR-backed and current-main optimization manual for `moonshotai/Kimi-K2*` and `moonshotai/Kimi-K2.5*` in SGLang. Use when Codex needs to recover, extend, or audit Kimi optimizations, including K2 router/MoE fast paths, K2 thinking Marlin paths, K2.5 wrapper/multimodal/runtime plumbing, W4AFP8/W4A16 quant tracks, parser contracts, LoRA coverage, and backend-specific validation.
Story brainstorming capture — minimal notes that preserve creative freedom. Use when exploring narrative ideas, discussing characters, planning chapters, or thinking through story possibilities. Supports interactive conversation and autonomous report mode for fan-out exploration.
Use when adding or updating Go CLI E2E coverage for one `tests/cli_e2e/{domain}` domain of the compiled `lark-cli`, especially when the work requires live `--help` or `schema` exploration, scenario-based `clie2e.RunCmd` workflows, and per-domain `coverage.md` maintenance.
Build explorative, interactive learning experiences as Next.js apps using the Geist design system. Use when creating tutorials, explorable explanations, interactive lessons, code sandboxes, quizzes, or any educational UI. Covers the Learning Loop pedagogy, 23+ learning component patterns, progress tracking, spaced repetition, and Bret-Victor-style interactive exploration — all with Geist's dark-first minimal aesthetic.
Use when "training LLM", "finetuning", "RLHF", "distributed training", "DeepSpeed", "Accelerate", "PyTorch Lightning", "Ray Train", "TRL", "Unsloth", "LoRA training", "flash attention", "gradient checkpointing"