Add bias/risk-of-bias assessment fields to an extraction table and populate them consistently. **Trigger**: bias, risk-of-bias, RoB, evidence quality, 偏倚评估, 证据质量. **Use when**: systematic review 已生成 `papers/extraction_table.csv`，需要在 synthesis 前补齐偏倚/质量字段。 **Skip if**: 不是 systematic review，或还没有 `papers/extraction_table.csv`。 **Network**: none. **Guardrail**: 使用简单可复核刻度（low/unclear/high）+ 简短 notes；保持字段一致性。
Bind addressable evidence IDs from `papers/evidence_bank.jsonl` to each subsection (H3), producing `outline/evidence_bindings.jsonl`. **Trigger**: evidence binder, evidence plan, section->evidence mapping, 证据绑定, evidence_id. **Use when**: `papers/evidence_bank.jsonl` exists and you want writer/auditor to use section-scoped evidence items (WebWeaver-style memory bank). **Skip if**: you are not doing evidence-first section-by-section writing. **Network**: none. **Guardrail**: NO PROSE; do not invent evidence; only select from the existing evidence bank.
Writing self-loop for surveys: run the strict section-quality gate, then rewrite only the failing `sections/*.md` files until the report is PASS. **Trigger**: writer self-loop, writing loop, quality gate loop, rewrite failing sections, 自循环, 反复改到 PASS. **Use when**: per-section files exist but C5 is FAIL/BLOCKED (thin sections, missing leads/front matter, citation-scope violations, generator voice). **Skip if**: you are still pre-C2 (NO PROSE), or evidence packs are incomplete (fix C3/C4 first). **Network**: none. **Guardrail**: do not invent facts; only use citation keys present in `citations/ref.bib`; keep citations in-scope per `outline/evidence_bindings.jsonl`; do not add/remove citation keys during rewrites.
Verifies code quality including naming conventions, function size, and DRY principles. SUGGESTION gate that offers polish items during /own:done flow.
Expert LLM architect specializing in large language model architecture, deployment, and optimization. Masters LLM system design, fine-tuning strategies, and production serving with focus on building scalable, efficient, and safe LLM applications.
Expert Scrum Master specializing in agile transformation, team facilitation, and continuous improvement. Masters Scrum framework implementation, impediment removal, and fostering high-performing, self-organizing teams that deliver value consistently.
Automated machine learning with hyperparameter optimization using Optuna, Hyperopt, or AutoML libraries. Activates for "automl", "hyperparameter tuning", "optimize hyperparameters", "auto tune model", "neural architecture search", "automated ml". Systematically explores model and hyperparameter spaces, tracks all experiments, and finds optimal configurations with minimal manual intervention.
JavaScript and TypeScript best practices covering naming conventions, control flow, state management, TypeScript patterns (avoid any/enum, prefer type over interface), safety (input validation, assertions, error handling), performance optimization (reduce branching/looping, memoization, defer await, cache property access, storage API caching, avoid needless allocations, currying for hot paths), and documentation (JSDoc, comment markers). Use when writing JS/TS functions, refactoring code for performance, reviewing code quality, fixing type errors, optimizing loops or conditionals, adding validation, or improving error messages.
Generates Babel configuration for JavaScript transpilation in tests. Creates babel.config.js file.
This skill should be used when writing or refactoring TypeScript/JavaScript code. It provides coding patterns and best practices aligned with the user's preferred development style, typescript language usage patterns, and library-specific tips.
Leverage React's event delegation system for optimization and custom event behavior.
Standards for creating redteam plugins and graders. Use when creating new plugins, writing graders, or modifying attack templates.
Systematically deconstruct written content into verifiable claims, validate each using search/documentation, and facilitate informed discussion through structured interviewing.
Perform structured, actionable code reviews for Python code with clear findings and suggestions.
Critical patterns for cross-platform path handling in this VS Code extension. Windows vs POSIX path bugs are the #1 source of issues. Use this skill when reviewing or writing path-related code.
Code review practices with technical rigor and verification gates. Use for receiving feedback, requesting code-reviewer subagent reviews, or preventing false completion claims in pull requests.
Self-reflect on the current session to identify mistakes and propose improvements to .claude configuration (CLAUDE.md, hooks, skills).
Validates production readiness through performance benchmarking, accessibility audits, security reviews, and code quality checks. Use after implementation phase completes, before deployment, or when conducting quality gates for features. (project)
Summarize Google Docs documents, plan structured revisions, and help with edit-in-place writing through connected Google Docs data. Use when the user wants to inspect document structure, outline or summarize content, draft rewrites, convert notes into prose, or apply explicit edits while preserving headings and organization.