Post-merge learning extraction. Reads the completed artefact chain for a merged story or feature, identifies reusable patterns, decisions, and standards that emerged during delivery, classifies them, and writes them back to the permanent knowledge base. Produces updates to standards/, decisions log, or copilot-instructions.md. Use after /definition-of-done is complete and a PR is merged. Run when someone says "levelup", "extract learnings", "update standards", "what did we learn from this", "pattern extraction", or "post-merge review". Requires a merged PR and completed DoD artefact.

heymishy0

Machine Learning

Mungers Lattice

Multidisciplinary analytical engine using Charlie Munger's latticework of mental models. Applies cross-disciplinary thinking (math, physics, biology, psychology, economics) to dissect life and business decisions. Use when user presents a decision problem, investment question, or complex analysis request requiring deep rational analysis.

hexbee0

Machine Learning

Xlinsist Perspective

Xlinsist（周旭林）式决策与表达视角。用于把复杂选择收敛为“唯一主线 + 长短期协同 + 可承受风险”的可执行方案。适用场景：学业/科研/职业选择、时间分配、合作决策、写作表达优化、高压下优先级排序。触发词示例：「用xlinsist视角」「主线思维」「先call住再看牌」「低空滑行」「长期规划+短期计划」「补强与留白」。

xlinsist0

Machine Learning

Research Creative

For goal-directed research tasks with creative freedom. Use this skill when the task spec defines a goal and evaluation metric but gives latitude on how to achieve it — e.g. "train the best probe you can", "find a good architecture for this task", "maximise this metric using whatever approach you think works". The user has defined success; your job is to find the best path to it. Always use alongside the autonomous-execution skill.

xycoord0

Machine Learning

Research: Specified Experiments

For executing well-defined research experiments specified in a task spec. Use this skill when the task spec defines exactly what experiments to run — hyperparameter sweeps, probe training on specific layers, activation collection, evaluation on specific benchmarks, or any research task where the experimental design is already determined. The user has decided what to do; your job is to execute it correctly, efficiently, and thoroughly. Always use alongside the autonomous-execution skill.

xycoord0

Machine Learning

Bmad Wds Workflow Suggest

bmad-wds-workflow-suggest skill

Hexalith0

Machine Learning

Ai Reliability

Use this skill when tasked with ensuring quality, scalability, or reliability of an AI system. Covers testing strategies (unit, integration, model quality), scaling patterns, monitoring and observability setup, model drift detection, incident response, and production QA checklists.

HemantSudarshan0

Machine Learning

Data Pipeline

Use this skill when tasked with data preprocessing, cleaning, transformation, dataset creation, model evaluation, metric computation, building evaluation harnesses, or performance/load testing of AI systems and APIs.

HemantSudarshan0

Machine Learning

Purpose

Make targeted, surgical fixes to an existing skill based on observed failure modes — tightening vague language, fixing routing misses, removing bloat, or covering missed edge cases. Use this when a skill produces inconsistent output, triggers incorrectly, or real usage revealed problems not covered. Do not use for complete rewrites (use skill-authoring), trigger-only fixes (use skill-trigger-optimization), adapting to a different context (use skill-adaptation), or when the skill is working correctly.

merceralex397-collab0

Machine Learning

Purpose

Compare skill variants or before-and-after versions using pass rate, token usage, latency, and qualitative win rate. Use this when choosing between multiple skill variants, measuring whether a refinement helped, or justifying skill maintenance investment. Do not use for evaluating a single skill in isolation (use skill-evaluation) or for building test infrastructure (use skill-testing-harness).

merceralex397-collab0

Machine Learning

Purpose

Evaluate whether a skill routes correctly and produces better output than a baseline — measuring precision, recall, output quality, and win rate against no-skill runs. Use this when validating a new skill before promotion, verifying a refinement worked, or auditing whether an existing skill still adds value. Do not use for building the test harness itself (use skill-testing-harness), benchmarking multiple variants head-to-head (use skill-benchmarking), or debugging a skill that is obviously broken (fix it first with skill-refinement).

merceralex397-collab0

Machine Learning

Purpose

Determine when a broad skill should be split into focused variants and execute the split — creating specialized skills by stack, platform, scope, or domain axis. Use this when a skill has multiple disjoint "For X" / "For Y" sections, triggers on unrelated inputs, or its procedure is full of conditional branches. Do not use for focused skills that work well, minor variations handled by overlays, or trigger-only problems (use skill-trigger-optimization).

merceralex397-collab0

Machine Learning Skills | Skills Pool