Loading...
Loading...
Found 82 Skills
Extract study data into a structured table (`papers/extraction_table.csv`) using the protocol’s extraction schema. **Trigger**: extraction form, extraction table, data extraction, 信息提取, 提取表. **Use when**: systematic review 在 screening 后进入 extraction(C3),需要把纳入论文按字段落到 CSV 以支持后续 synthesis。 **Skip if**: 还没有 `papers/screening_log.csv` 或 protocol 未锁定。 **Network**: none. **Guardrail**: 严格按 schema 填字段;不要在此阶段写 narrative synthesis(那是 `synthesis-writer`)。
Select the most appropriate pipeline for a user goal, lock it in `PIPELINE.lock.md`, and route checkpoint questions into `DECISIONS.md`. **Trigger**: pipeline router, choose pipeline, workflow selection, PIPELINE.lock.md, 选择流程. **Use when**: 用户目标/交付物不清晰,需要在 snapshot/survey/tutorial/systematic-review/peer-review 中选一个并设置最小 HITL 问题集。 **Skip if**: pipeline 已锁定(`PIPELINE.lock.md` 存在)且所需问题已回答/签字完成。 **Network**: none. **Guardrail**: 尽量一次性提问;信息不足就写 `DECISIONS.md` 并停下等待。
Evidence-grounded to-be design (ADRs + design doc) and an implementation orchestration plan (a machine-readable task ledger). Activates when the user asks to design a target state, plan the work, or produce a task plan for a goal.
Generate lightweight section/subsection transitions (NO NEW FACTS) to prevent “island” subsections; outputs a transition map that merging/writing can weave in. **Trigger**: transition weaver, weave transitions, coherence, 过渡句, 承接句, 章节连贯性. **Use when**: `outline/subsection_briefs.jsonl` exists and you want coherent flow before/after drafting (typically Stage C5). **Skip if**: `outline/transitions.md` exists and is refined (no placeholders). **Network**: none. **Guardrail**: do not add new factual claims or citations; transitions may only refer to titles/RQs/bridge terms already present in briefs.
Write structured notes for each paper in the core set into `papers/paper_notes.jsonl` (summary/method/results/limitations). **Trigger**: paper notes, structured notes, reading notes, 论文笔记, paper_notes.jsonl. **Use when**: survey 的 evidence 阶段(C3),已有 `papers/core_set.csv`(以及可选 fulltext),需要为后续 claims/citations/writing 准备可引用证据。 **Skip if**: 还没有 core set(先跑 `dedupe-rank`),或你只做极轻量 snapshot 不需要细粒度证据。 **Network**: none. **Guardrail**: 具体可核对(method/metrics/limitations),避免大量重复模板;保持结构化字段而非长 prose。
Synthesize evidence into a structured narrative (`output/SYNTHESIS.md`) grounded in `papers/extraction_table.csv`, including limitations and bias considerations. **Trigger**: synthesis, evidence synthesis, systematic review writing, 综合写作, SYNTHESIS.md. **Use when**: systematic review 完成 screening+extraction(含 bias 评估)后进入写作阶段(C4)。 **Skip if**: 还没有 `papers/extraction_table.csv`(或 protocol/screening 尚未完成)。 **Network**: none. **Guardrail**: 以 extraction table 为证据底座;明确局限性与偏倚;不要在无数据支撑时扩写结论。
Run this repo’s Units+Checkpoints research pipelines end-to-end (survey/综述/review/调研/教程/系统综述/审稿), with workspaces + checkpoints. **Trigger**: run pipeline, kickoff, 继续执行, 自动跑, 写一篇, survey/综述/review/调研/教程/系统综述/审稿. **Use when**: 用户希望端到端跑流程(创建 `workspaces/<name>/`、生成/执行 `UNITS.csv`、遇到 HUMAN checkpoint 停下等待)。 **Skip if**: 用户明确要手工逐条执行(用 `unit-executor`),或你不应自动推进到 prose 阶段。 **Network**: depends on selected pipeline (arXiv/PDF/citation verification may need network; offline import supported where available). **Guardrail**: 必须尊重 checkpoints(无 Approve 不写 prose);遇到 HUMAN 单元必须停下等待;禁止在 repo root 创建 workspace 工件。
Compile a LaTeX project and run basic QA (missing refs, bib errors, broken citations), producing `latex/main.pdf` and a build report. **Trigger**: latex compile, build PDF, LaTeX errors, missing refs, 编译PDF, 引用错误. **Use when**: 已有 `latex/main.tex`(通常来自 `latex-scaffold`),需要确认可编译并输出失败原因报告。 **Skip if**: 还没有 LaTeX scaffold(先跑 `latex-scaffold`)。 **Network**: none. **Guardrail**: 编译失败也要落盘 `output/LATEX_BUILD_REPORT.md`;不做“内容改写”,只做编译/QA。
Remove repeated boilerplate across sections (methodology disclaimers, generic transitions, repeated summaries) while preserving citations and meaning. **Trigger**: redundancy, repetition, boilerplate removal, 去重复, 去套话, 合并重复段落. **Use when**: the draft feels rigid because the same paragraph shape and disclaimer repeats across many subsections. **Skip if**: you are still drafting major missing sections (finish drafting first). **Network**: none. **Guardrail**: do not add/remove citation keys; do not move citations across subsections; do not delete subsection-specific content.
Rewrite `outline/claim_evidence_matrix.md` as a projection/index of evidence packs (NO PROSE), so claims/axes are driven by `outline/evidence_drafts.jsonl` rather than outline placeholders. **Trigger**: claim matrix rewriter, rewrite claim-evidence matrix, evidence-first claim matrix, matrix index, 证据矩阵重写, 从证据包生成矩阵. **Use when**: `outline/subsection_briefs.jsonl` + `outline/evidence_drafts.jsonl` are ready and you want a clean claim→evidence index for QA/writing. **Skip if**: `outline/claim_evidence_matrix.md` is already refined and consistent with evidence packs. **Network**: none. **Guardrail**: NO PROSE; do not invent facts; only cite keys present in `citations/ref.bib`; if evidence is abstract/title-only, claims must be provisional.
Apply systematic performance optimization techniques when writing or reviewing code. Use when optimizing hot paths, reducing latency, improving throughput, fixing performance regressions, or when the user mentions performance, optimization, speed, latency, throughput, profiling, or benchmarking.
Setup TypeScript best practices and code style rules in CLAUDE.md