Loading...
Loading...
Found 1,906 Skills
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate exte...
Use when raising startup capital (pre-seed through Series C+): decide raise vs bootstrap, size a round, build a deck + data room, run investor targeting/outreach, negotiate SAFEs/term sheets, manage diligence, and set investor reporting cadence post-close.
Extract tacit engineering knowledge through guided interviews and generate structured steerings. Use when user mentions "steerings", "tacit knowledge", "conventions", "engineering practices", "interview", or wants to document team/project knowledge. Also activates when user asks for "steerings for X", "document X conventions", "continue steerings", "resume interview", or wants to extract knowledge about a specific topic. Supports reviewing and transforming existing steerings to standard format. Auto-detects existing sessions and offers to continue incomplete ones.
Comprehensive code review criteria covering correctness, readability, maintainability, security, performance, and testing. Reference when reviewing code changes or preparing code for review.
Use when making decisions under uncertainty with quantifiable outcomes, comparing risky options (investments, product bets, strategic choices), prioritizing projects by expected return, assessing whether to take a gamble, or when user mentions expected value, EV calculation, risk-adjusted return, probability-weighted outcomes, decision tree, or needs to choose between uncertain alternatives.
Help the user systematically identify and categorize failure modes in an LLM pipeline by reading traces. Use when starting a new eval project, after significant pipeline changes (new features, model switches, prompt rewrites), when production metrics drop, or after incidents.
Use when you need hard pass fail eval gates for generated projects and skills; pair with addon-decision-justification-ledger and addon-human-pr-review-gate.
Parallel 3-reviewer code review orchestration: launch Security, Business-Logic, and Architecture reviewers simultaneously, aggregate findings by severity, and produce a unified BLOCK/FIX/APPROVE verdict. Use when reviewing PRs with 5+ files, security-sensitive changes, new features needing broad coverage, or when user requests "parallel review", "comprehensive review", or "full review". Do NOT use for single-file fixes, documentation-only changes, or when systematic-code-review (sequential) is sufficient.
Use when starting a new project with Maestro or when no .maestro.md context file exists yet. Run once per project.
AscendC Operator End-to-End Development Orchestrator. Used when users need to develop new operators, implement custom operators, or complete the full process from requirements to testing. Keywords: operator development, end-to-end, full process, workflow orchestration, new operator creation.
Maintain JSONL-only profiler performance test cases under csrc/ops/<op>/test in ascend-kernel. Collect data using torch_npu.profiler (with fixed warmup=5 and active=5), aggregate the Total Time(us) from ASCEND_PROFILER_OUTPUT/op_statistic.csv, and output a unified Markdown comparison report (custom operator vs baseline) that includes a DType column. Do not generate perf_cases.json or *_profiler_results.json. Refer to examples/layer_norm_profiler_reference/ for the reference implementation.
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch for Claude Code or Cursor, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.