科研 Skill
研究计划任务执行
executing-research-plan
Executes a ready research plan task by task, gating acquisition before ingest and dispatching analysis. Use after writing-research-plan to run the planned work.
SKILL.md
Executing a Research Plan
Run a pre-registered plan task by task. Dispatch the right subagent per task, review each result (spec + quality), and only mark done when both reviews pass. Deviations are logged, not hidden.
Announce at start: "Using executing-research-plan to run <slug>-plan.md."
If unmet: explain to the user which condition is missing, ask for a short
reason, write it to knowledge/_meta/gate-overrides.log, and start the
task.
A task is "done" only when the type-specific review passes (see "Review by methodology" below). Never silently rewrite a hypothesis mid-run — deviations go into the deviation log.
Checklist
- Load the plan — read
input/ideas/<slug>-plan.mdend-to-end - Verify the plan is ready (methodology-aware):
methodology: hermeneutic→ frontmatterstatus: readyis enough (no frozen hypothesis);methodology: quantitative/mixed(or a task block markedpre-registered: true) →status: pre-registered+ user confirmation of the hypothesis - Create task-list items — one per task in the plan (use the plan's own wording)
- Personal-data check (before any task that reads
input/data/orinput/notes/) — interviews, questionnaires, field notes or excavation diaries naming living people, correspondence, unpublished data shared by colleagues. Ask once: does this material contain personal or confidential data, and do the consent forms / data agreements allow processing by the AI provider this session uses? If not, or unknown: stop that task and say so — the options are anonymising first (remove names, places, identifiers before the file is read), or running the task with a local / institution-hosted model (e.g. KISSKI/GWDG, a local Ollama or LM Studio model). Record the answer in the plan's task block (personal_data: none | anonymised | local-model-only) so the next session does not ask again. Published scholarship and the user's own non-personal notes need no check - Acquisition gate (before any ingest task) — guarantee the originals are on disk first; run the Acquisition gate algorithm below.
literature-reviewonly searches — without this gate everysource-ingesterhard-stops on a missing PDF. - Route each task to the right subagent:
- Ingest task →
source-ingester(seeagents/source-ingester.md) - Analysis task →
analyst(runs Python/R inoutput/data-analysis/) - Synthesis task → main conversation, not subagent (high context integration) — follow Writing a synthesis
- Draft task → invoke
drafting-manuscriptskill (which may dispatchdrafter)
- Ingest task →
- Two-stage review per task:
- Spec reviewer (fresh subagent): does the output match the task spec exactly?
- Quality reviewer (fresh subagent): is the code/page/result methodologically sound?
- Any "no" → route back to the executing subagent with reviewer feedback
- Log deviations — if findings force change, append to
knowledge/_meta/log.mdand mark subsequent analyses as exploratory - Run wiki-lint after every ingest and synthesis task
- After all tasks done: check plan's Verification section; only green on all boxes means complete
- Transition: if plan output target is book/article →
drafting-manuscript; if grant →grant-finder; if done →finishing-a-research-project
Acquisition gate (before any ingest task)
literature-review searches but downloads nothing; source-ingester hard-stops
on a missing original. This gate sits between them: it guarantees every ingest
task's PDF is on disk (or explicitly deferred) before the first source-ingester
is dispatched — so you get one clean acquisition step instead of a wall of
per-source hard-stops.
- Collect required originals — from every ingest task in the plan, derive the
expected library path
<library>/pdf/<bibkey>.pdf(the naming conventionacquire-sourceswrites andingest-sourcereads). - Scan the library —
<library>/pdf/*.pdf(resolve withscripts/library.py; never in subfolders). If every required original is present → skip the gate, go to routing. - Attempt acquisition — run
acquire-sourceson the A+B set (dispatch thesource-acquirersubagent for ≥ ~8 missing items). It auto-downloads the Open-Access copies into the library and (re)generatesinput/bibliography/acquisition-todo.md. - If
acquisition-todo.mdis non-empty (originals still missing), enter the interactive resume loop — do NOT silently skip:- a. Offer the list. Present the missing sources from
acquisition-todo.mdplus the manual-download instruction (university VPN / library proxy; save each into<library>/pdf/under the exact<bibkey>.pdffilename). Mark the dependent ingest tasks as blocked and pause — do not dispatch those ingests. - b. On the user's resume signal, re-scan
<library>/pdf/for the newly added PDFs and reconcile — re-runacquire-sourcesin reconcile mode: resolved rows drop out of (are checked off)acquisition-todo.md. - c. Ask the branch: "Search for alternatives (open-access substitutes
via
literature-review) for what's still missing, or continue with what's present?"- Alternatives → loop back to
literature-review/literature-scoutto find OA alternatives for the gaps, grade them into the guide table, then re-runacquire-sourceson the new candidates → back to step 4. - Continue → proceed to routing with the acquired subset.
- Alternatives → loop back to
- d. Loop a–c until the user says to move on to ingest.
- a. Offer the list. Present the missing sources from
- Proceed to routing — dispatch
source-ingesteronly for tasks whose original is now on disk; any still-missing stayblocked/deferred per the user's choice. Non-blocked downstream work (analysis on existing data, etc.) is not held up by a blocked ingest.
"Alternativen" = a different open-access source on the same topic, NOT a preprint/prior-version/review substitute for the same paper. Substituting one edition for another remains
ingest-source's consent-gated decision and is out of scope for this gate.
Process Flow
digraph executing {
"Load plan" [shape=box];
"Pre-registered & signed?" [shape=diamond];
"Back to writing-research-plan" [shape=box];
"Create task list from plan" [shape=box];
"Acquisition gate: scan the library" [shape=box];
"All originals present?" [shape=diamond];
"Run acquire-sources" [shape=box];
"Worklist empty?" [shape=diamond];
"Offer manual list, block ingests, pause" [shape=box];
"User resumes" [shape=box];
"Reconcile (re-scan + re-run)" [shape=box];
"Alternatives or continue?" [shape=diamond];
"literature-review for OA alternatives" [shape=box];
"Next task" [shape=box];
"Route by task type" [shape=diamond];
"Dispatch source-ingester" [shape=box];
"Dispatch analyst" [shape=box];
"Handle synthesis inline" [shape=box];
"Invoke drafting-manuscript" [shape=box];
"Spec review" [shape=box];
"Quality review" [shape=box];
"Both pass?" [shape=diamond];
"Route back with feedback" [shape=box];
"Mark task done" [shape=box];
"More tasks?" [shape=diamond];
"Verify against plan checklist" [shape=box];
"All green?" [shape=diamond];
"Transition" [shape=doublecircle];
"Load plan" -> "Pre-registered & signed?";
"Pre-registered & signed?" -> "Back to writing-research-plan" [label="no"];
"Pre-registered & signed?" -> "Create task list from plan" [label="yes"];
"Create task list from plan" -> "Acquisition gate: scan the library";
"Acquisition gate: scan the library" -> "All originals present?";
"All originals present?" -> "Next task" [label="yes"];
"All originals present?" -> "Run acquire-sources" [label="no"];
"Run acquire-sources" -> "Worklist empty?";
"Worklist empty?" -> "Next task" [label="yes"];
"Worklist empty?" -> "Offer manual list, block ingests, pause" [label="no"];
"Offer manual list, block ingests, pause" -> "User resumes";
"User resumes" -> "Reconcile (re-scan + re-run)";
"Reconcile (re-scan + re-run)" -> "Alternatives or continue?";
"Alternatives or continue?" -> "literature-review for OA alternatives" [label="alternatives"];
"literature-review for OA alternatives" -> "Run acquire-sources";
"Alternatives or continue?" -> "Next task" [label="continue"];
"Next task" -> "Route by task type";
"Route by task type" -> "Dispatch source-ingester" [label="ingest"];
"Route by task type" -> "Dispatch analyst" [label="analysis"];
"Route by task type" -> "Handle synthesis inline" [label="synthesis"];
"Route by task type" -> "Invoke drafting-manuscript" [label="draft"];
"Dispatch source-ingester" -> "Spec review";
"Dispatch analyst" -> "Spec review";
"Handle synthesis inline" -> "Spec review";
"Invoke drafting-manuscript" -> "Spec review";
"Spec review" -> "Quality review";
"Quality review" -> "Both pass?";
"Both pass?" -> "Route back with feedback" [label="no"];
"Route back with feedback" -> "Next task";
"Both pass?" -> "Mark task done" [label="yes"];
"Mark task done" -> "More tasks?";
"More tasks?" -> "Next task" [label="yes"];
"More tasks?" -> "Verify against plan checklist" [label="no"];
"Verify against plan checklist" -> "All green?";
"All green?" -> "Next task" [label="no, fix"];
"All green?" -> "Transition" [label="yes"];
}
Task Type Routing
| Plan keyword | Subagent / Skill | Output landing zone |
|---|---|---|
| "Acquire / fetch PDFs / besorge Quellen" | acquire-sources skill (→ source-acquirer for ≥8) | <library>/pdf/*.pdf, input/bibliography/acquisition-todo.md |
| "Ingest X" | source-ingester | knowledge/sources/, knowledge/entities/, output/bibtex/ |
| "Analyze / compute / run" | analyst | output/data-analysis/, output/data-analysis/results/ |
| "Synthesize / integrate / write synthesis" | inline (main conversation) | knowledge/synthesis/ |
| "Draft chapter / section / article" | drafting-manuscript skill | output/**/*.md |
Writing a synthesis
A synthesis is where the project says what its sources add up to, and it is where model-written text is weakest. The typical failure is not a false statement but an empty one: "a complex picture emerges", "the evidence must be assessed in a differentiated way", "cult centralisation played an important role", "further research is needed". Each sentence is true of almost any topic, so it says nothing about this one. Such sentences are the model's safe default when it integrates many sources at once: the averaged position, hedged on all sides. The rules below make the specific conclusion the easier one to write.
-
Re-read before concluding. Write the conclusions from the source pages (and their focus blocks) re-read now — not from the ingest summaries still in the conversation, which are compressed already. A synthesis written at the end of a long ingest run is a summary of summaries.
-
The author's conclusion first. Before writing the conclusions, ask the user what they think the material shows, in their own words (rough is fine) — the same discipline as
drafting-manuscriptSTOP 0, for the same reason: approving a polished machine conclusion is not drawing one. Do not offer a candidate in that message. If the user asks you to propose, mark the conclusionagent-proposedin the page until they restate it. -
Each conclusion is a claim block, not a paragraph of summary:
### C1 — <short label> - **Claim:** <one sentence that could turn out wrong> - **Kind:** finding (what the sources report) | reading (an interpretation in the literature — whose) | own thesis (the project's inference — marked as such) - **Carried by:** [[source-a]] (p. 61), [[source-b]] (p. 12–14) — n independent sources - **Concrete anchor:** <the named site / passage / stratum / dating / dataset the claim is about> - **Against:** <the strongest counter-position, cited — or "none found in the wiki"> - **Would be wrong if:** <the finding or argument that would overturn it>A conclusion with no concrete anchor, or nothing that could make it wrong, is not finished: narrow it until it has both, or move it to
What stays open. -
Specificity test. For every sentence in the conclusions, swap the topic words for a neighbouring topic (another site, another text, another period). If the sentence is still true, it says nothing here — cut it or make it specific. Typical offenders, in both languages: komplexes / vielschichtiges Bild, differenziert zu betrachten, spielt eine wichtige / zentrale Rolle, im Spannungsfeld von, weitere Forschung ist nötig, a nuanced picture emerges, plays a crucial role, highlights the importance of, multifaceted, it remains to be seen.
-
Disagreement is a finding, not a conclusion. "Scholars disagree" says something about the literature. Say who holds what, on which evidence, since when (see the research chronology) — and what the project concludes from that: one side, a third reading, or an explicit bracket with the reason.
-
Open questions are specific too.
What stays opennames the question and what would settle it (a source not yet read, an excavation report, a test) — not "further research is needed". -
Keep the hedges the sources give, and add none of your own. A conclusion is as strong as its sources carry; the hedge goes on the claim where the evidence is thin, not across the whole page as insurance.
Critical Thinking — Cross-Cutting Checklist
Walk through this on every method choice and before every subagent dispatch:
- Claim first, then evidence — what exactly is being claimed? State the claim precisely, then ask what evidence would support it.
- Evidence type — primary data, secondary synthesis, expert opinion, theoretical argument. Drives the method choice.
- Framework matched to discipline:
- GRADE — causal / quantitative claims
- Cochrane ROB — experimental designs
- Source-critical (Quellenkritik) — textual-historical sources
- Stratigraphic reliability — archaeological claims
- Reproducibility audit — computational / DH
- Name confounders explicitly — what gets overlooked, what could explain the finding otherwise
- Check logical fallacies — ad hominem, affirming the consequent, equivocation, cherry-picking, post hoc
- Falsifiability — what would refute the claim?
If the answer to any of these is "I don't know," that belongs in the quality review or gets resolved before dispatch.
Review by Methodology
The review tiering depends on the methodology field in the project
frontmatter (CLAUDE.md) or in the task-block frontmatter.
Quantitative Tasks — Two-Stage Review
For tasks under methodology: quantitative or task blocks with
pre-registered: true: dispatch two fresh subagents (minimal context:
just task spec + output):
Spec reviewer prompt template:
You are a spec compliance reviewer. Task spec: . Output: . Does the output match the spec exactly? Report mismatches. Do not assess quality.
Quality reviewer prompt template:
You are a methodological quality reviewer. Output: . Methodological context: . Is this sound? Check: (1) are assumptions stated, (2) are limitations named, (3) does the script contain control checks with known answers, and do they pass, (4) does the load-bearing result agree across the independent recomputation, (5) is each procedure's choice justified by the plan rather than by its result, (6) would a peer reviewer accept this? Report issues.
Both "yes" → task done. Any "no" → feedback back to the executing subagent.
Hermeneutic Tasks — Synthesis Review
For tasks under methodology: hermeneutic (no pre-registration):
single-stage review in the main context, focused on plausibility and
source fidelity rather than spec compliance.
Synthesis reviewer prompt template (in main context, no subagent needed):
Output: . Method sketch: . (1) Is the argument actually supported by the cited sources (spot-check 3 central citations)? (2) Are alternative readings named where they suggest themselves? (3) Is the hermeneutic position transparent (which pre-understanding horizon, which method is applied)? (4) Is every conclusion specific? Apply the specificity test from "Writing a synthesis" to each sentence of the conclusions and quote the ones that would hold for a neighbouring topic just as well. (5) Is every conclusion a complete claim block — concrete anchor, carrying sources with pages, kind (finding / reading / own thesis), a counter-position, and what would make it wrong?
Return findings as correction notes, not as a pass/fail gate. The user decides final acceptance.
Mixed Projects
The plan marks per task which review mode applies. Pre-registered tasks run through two-stage; hermeneutic tasks run through synthesis review.
Deviations
If a task surfaces a result that contradicts the pre-registered hypothesis, or if the method must change:
- Stop. Do not rewrite the hypothesis.
- Append to
knowledge/_meta/log.md:- YYYY-MM-DD · deviation · plan=<slug> · <what changed and why> - Mark any analysis downstream of the deviation as exploratory in its frontmatter (
status: exploratory). - Surface to user — "The plan said X, the data shows Y. Continuing as exploratory. OK?"
Red Flags
| Thought | Reality |
|---|---|
| "Just start ingesting — the PDFs are probably there" | No — run the acquisition gate first; otherwise every source-ingester hard-stops on a missing original, one source at a time. |
| "Some originals are still missing, I'll just skip them quietly" | No — surface the worklist, block those ingests, and let the user fetch them or pick alternatives. Silent skipping hides gaps. |
| "The hypothesis doesn't fit, I'll tweak it slightly" | No — log entry, result becomes exploratory. |
| "Review is overkill for such a small task" | Small tasks are exactly where errors slip past. Always both reviews. |
| "I'll just do it myself instead of dispatching a subagent" | Subagent isolation protects context and forces prompt clarity. |
| "The synthesis is stable now" | Only the user sets stable. |
| "A complex picture emerges — that's an honest conclusion" | It is true of every topic. Name who holds what, on which evidence, and what the project concludes. |
| "I just ingested all the sources, I can write the synthesis from that" | You have their summaries in context, already compressed. Re-read the source pages before concluding. |
| "I'll hedge the conclusions to be safe" | Hedge the claim whose evidence is thin, with the reason. A blanket hedge makes every conclusion unfalsifiable. |
Key Principles
- Acquire before ingest — the acquisition gate guarantees originals are on disk (or explicitly deferred) before any
source-ingesterruns - The plan is law — anything outside the plan is scope creep or deviation
- One subagent per task — fresh context, no context collapse
- Two-stage review — spec THEN quality, not mixed
- Deviation > revision — divergent findings get flagged, not absorbed
- Verification is a list, not a feeling — the plan's checkboxes are the completion test
示例提示词
帮我按已生成的研究计划逐项执行任务,先获取原始文献再入库。
所属插件
安装该插件会一并获得同领域的 62 个 Skill / MCP。
同插件的其他科研 Skill
- 学术文献获取下载Auto-downloads open-access PDFs for graded sources and writes a manual worklist for paywalled items. Use after literature-review, before ingest-source.
- 单篇文献入库管理Adds one verified PDF to a shared bibliography library, computing its citation key and keywords. Use to register a single document outside the full workflow.
- 数字人文计算方法Surveys computational DH methods: text mining, NLP, corpus linguistics, archive standards, GIS, network analysis, and OCR. Use for an overview of available DH tools.
- 考古地理信息系统分析Runs archaeological GIS analysis with GeoPandas: catchment analysis, viewshed, kernel density, spatial statistics. Use for mapping archaeological site locations.
- 论证结构提取可视化Extracts and visualizes argument structure: Toulmin reconstruction, support/attack graphs, circularity detection. Use to diagram an argument’s logical structure.
- 考古遗物类型学分析Performs artifact analysis: typological classification, ceramic attribute coding, lithic reduction analysis. Use when classifying excavated artifacts statistically.
- 引文与出处核查Checks citations, quotations, page numbers, and bibliography entries for accuracy and source fit. Use before submission to verify source-supported claims.
- 研究选题构思设计Explores research intent, field state, methodology, and ethics, then writes an approved design doc. Use before starting a new research question or chapter.
- 术语译名一致性检查Audits a manuscript for terms, translations, abbreviations, and names whose forms must stay stable. Use when terminology drift could undermine an argument.
- 计算语用学分析Runs computational pragmatics: speech act classification, implicature detection, discourse coherence, politeness analysis. Use for language-use-and-meaning studies.
- 文献综述学术对话构建Turns verified sources into a structured scholarly conversation among positions, not a chronological summary. Use when synthesizing literature into a debate narrative.
- 语料库语言学分析Performs corpus analysis with NLTK/spaCy: collocation, keyword analysis, KWIC concordance, word2vec, diachronic trends. Use for quantitative text-corpus research.
- 数字档案馆资源检索Queries digital archive REST APIs: Europeana, Chronicling America, Internet Archive, HathiTrust, DPLA, OAI-PMH. Use when searching or harvesting heritage metadata.
- 学术手稿章节撰写Drafts a chapter or article section by section from synthesized wiki content, agreeing each section’s argument first. Use to turn stable research synthesis into prose.
- 研究项目漂移状态检测Checks a shared source library and registered projects for drift: un-indexed PDFs, unmerged keywords, bibkey collisions. Use to audit a multi-project research setup.
- EMI课堂语料转写分析Segments and annotates classroom transcripts, coding language choice and discourse function with anonymised output. Use to quantify classroom talk or translanguaging.
- 人工智能伦理分析Analyzes AI ethics: algorithmic fairness metrics, bias auditing, value alignment, moral philosophy reasoning. Use to evaluate an AI system’s ethical dimensions.
- 研究项目结项清单Runs the final completion checklist: rendering, bibliography, wiki, data, reproducibility, archiving. Use when a manuscript is finalized and ready to publish.
- 形式逻辑自动推理Applies formal logic tools: Z3 SMT solver, modal logic S5, SAT encoding, Lean4 proof verification. Use to formalize or mechanically check a logical argument.
- 研究问题凝练构建Turns a broad topic or intuition into a precise, contestable, researchable question. Use at the start of a project when no defensible question yet exists.
- 历史地理信息系统分析Performs historical GIS work: georeferencing old maps, digitizing boundaries, temporal territory overlays, population interpolation. Use for historical spatial analysis.
- 历史语言学比较分析Analyzes historical linguistics in Python: sound correspondences, cognate detection, phylogenetic trees, Swadesh lists. Use when reconstructing language relationships.
- 历史社会网络分析Builds historical network analyses: correspondence networks, prosopography, temporal community detection, Gephi export. Use to map relationships among historical actors.
- 历史文献OCR识别Transcribes printed and handwritten historical documents with Tesseract/Kraken OCR, confidence filtering, spell correction. Use for digitizing scanned historical text.
常见问题
研究计划任务执行能做什么?
Executes a ready research plan task by task, gating acquisition before ingest and dispatching analysis. Use after writing-research-plan to run the planned work。
如何安装研究计划任务执行?
在科搭 Codar 左侧点击「插件」,在「组件」页签搜索「研究计划任务执行」并安装;在 Claude Code 或 Codex 中可以发送本页的安装提示词,或下载 Skill 包后解压到 ~/.claude/skills 或 ~/.codex/skills。
研究计划任务执行需要哪些权限?
该科研 Skill没有声明额外权限;执行具体操作时仍由 Agent 按自身规则请求确认。
研究计划任务执行经过官方审核吗?
是。SpeedSkills 收录的每个版本都会记录内容摘要与权限声明,当前版本已通过安全审核。