math-history-researcher
Skill17 starsChanged 7 months agoMITView on GitHub
Rigorous, source-traceable research workflow for History of Mathematics questions. Use this whenever the user asks for mathematician biography, chronology, attribution, historical significance, origin of concepts, conflicting historical claims, or paper-ready claim verification with citations/BibTeX candidates. Prefer this skill even for short factual answers. Run a serial 4-agent workflow (search -> verify -> write -> citation QA), with recursive and parallel sub-agent search in the retrieval stage.
In this repository9 other files it gives its agents.
- .github/copilot-instructions.mdCopilot instructions
- citation-managementSkill
- find-skillsSkill
- latex-paper-enSkill
- openalex-databaseSkill
- paper-auditSkill
- skill-creatorSkill
- web-accessSkill
- writing-clearly-and-conciselySkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
59 rules. About 0 are common, 40 are distinctive, and 19 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈40
Distinctive · estimate
This author's own choices. Worth a look.
19
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 16
Use serial stages end-to-end, and allow parallelism only inside search.
- Distinctive: line 21
Use recursive branching when evidence is weak.
- Distinctive: line 28
Keep claims conservative and traceable.
- Very specific: line 41
Tri-vector fan-out per claim (parallel): run Vector A/B/C for each claim concurrently.
- Distinctive: line 42
Depth-2 recursive fan-out (conditional, parallel): only for weak/conflicting claims, spawn focused sub-queries (edition year, translation …
- Very specific: line 45
Keep A2/A3/A4 strictly serial after A1 merge.
- Very specific: line 52
Every key factual claim must have at least 1 high-quality source.
- Very specific: line 56
If an external web image is necessary and cannot be reliably generated by AI drawing, add an explicit marker: TODO: add external web image …
- Distinctive: line 58
Never let drafting/process artifacts, or anything that may imply the use of AI appear in final manuscript output (e.g., prompt scaffolds, …
- Distinctive: line 60
Every formal artifact must be explained: define symbols/variables, state what the formula or figure demonstrates, and connect it to the …
- Distinctive: line 61
Prefer historically faithful notation and proof style when presenting historical mathematics.
- Distinctive: line 65
Use this skill when requests involve any of the following:
- Distinctive: line 74
Do not use this skill for pure creative writing or opinion-only brainstorming with no factual verification requirement.
- Distinctive: line 89
Run three retrieval vectors in parallel whenever possible:
- Distinctive: line 110
Depth 2 (conditional): if evidence is weak/contradictory, spawn focused sub-queries (edition year, translation metadata, attribution …
- Distinctive: line 112
Stop recursion when either:
- Distinctive: line 114
no higher-quality source can be found after one refinement round.
- Distinctive: line 135
Prefer higher-ranked evidence when conflicts occur.
- Distinctive: line 139
If at least 2 sources materially conflict on a key claim:
- Distinctive: line 144
avoid collapsing unresolved disputes into one "fact"
- Distinctive: line 148
When resolving conflicts, compare each candidate claim with these checks:
- Very specific: line 155
Prefer the variant that wins more high-priority checks.
- Distinctive: line 169
If metadata is incomplete, mark explicit TODO fields.
- Distinctive: line 173
Always output with this structure:
- Distinctive: line 211
If the section would materially benefit from a non-AI-drawable external web image, include:
- Distinctive: line 229
When downstream automation is expected, add a machine-readable block containing:
- Distinctive: line 239
When the target subsection discusses concrete mathematical work (not just context/history), include:
- Very specific: line 253
If exempted, explicitly mark: Formalism exemption: historical/context-only subsection.
- Very specific: line 255
When a subsection uses modernized notation/proof for accessibility, add an explicit disclosure sentence such as: For simplicity, we use …
- Distinctive: line 259
Use strict claim-source binding:
- Distinctive: line 270
if metadata is incomplete, keep explicit TODO fields instead of guessing
- Distinctive: line 276
Every key claim has >=1 high-quality source.
- Distinctive: line 277
Every priority/first-use claim has >=2 independent sources.
- Very specific: line 279
If conflicts exist, Disagreements & Variants is present.
- Very specific: line 281
If an external web image is judged necessary and not AI-drawable, a TODO: add external web image marker is present with placement + …
- Distinctive: line 288
Keep language precise, neutral, and academically conservative.
- Distinctive: line 290
Avoid overclaiming certainty when evidence is thin.
- Distinctive: line 295
Use graded failure levels:
- Distinctive: line 301
If external retrieval fails completely (Level C):
- Distinctive: line 315
Before drafting, load only a concise style checklist (active voice, concrete language, omit needless words).
- Distinctive: line 316
Do not run full polishing before claim verification.
- Distinctive: line 324
When available in this workspace, use capabilities in this order:
- Very specific: line 327
Use @websearch / #websearch for current-info discovery and candidate URL collection.
- Very specific: line 330
Use the fetch MCP (mcp-server-fetch) to read selected URLs and recursively fetch relevant linked pages.
- Distinctive: line 331
Prefer this for citation-safe extraction from static pages, docs, and article-style sources.
- Very specific: line 333
Use openalex-database skill to find related works/DOIs and citation graph context.
- Very specific: line 335
Use citation-management skill to convert verified metadata into BibTeX-ready entries.
- Very specific: line 337
Use web-access only when needed: dynamic rendering, login-required pages, or interactive workflows.
- Distinctive: line 338
Do not use browser automation by default when lighter retrieval layers already satisfy evidence needs.
- Very specific: line 340
Use latex-paper-en for section drafting polish.
- Very specific: line 341
Use paper-audit for reviewer-style sanity checks.
- Very specific: line 343
Use writing-clearly-and-concisely to reduce robotic phrasing and improve sentence rhythm while preserving factual claims and citations.
- Very specific: line 347
Use a single primary retrieval path per claim by default: websearch -> fetch -> openalex.
- Distinctive: line 349
Do not run multiple retrieval stacks redundantly for the same claim unless conflict verification requires a second pass.
- Distinctive: line 359
If one capability is unavailable, continue with remaining ones and mark the gap explicitly.
- Distinctive: line 363
Use this gate to prevent visible drafting/tool artifacts from leaking into final PDF output.
- Very specific: line 372
Run from manuscript root (main.tex directory):
- Distinctive: line 378
Use a two-tier strategy:
- Distinctive: line 392
If the user asks for "human-like" prose, interpret this as readability/disciplinary tone improvement, not authorship concealment.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Math History Researcher
Purpose
Produce an English, citation-safe Research Pack for History of Mathematics tasks with claim-level traceability.
This skill is designed for workflows where factual errors are costly (course papers, claim ledgers, bibliography building, section drafting in LaTeX manuscripts).
Execution Topology (Serial 4-Agent Pipeline)
Use serial stages end-to-end, and allow parallelism only inside search.
- Agent A1 — Search Orchestrator
- Decompose the task into claim units.
- Launch tri-vector retrieval in parallel.
- Use recursive branching when evidence is weak.
- Agent A2 — Evidence Verifier
- Rank source quality.
- Resolve/flag conflicts with explicit rubric.
- Reject weak or uncitable claims.
- Agent A3 — Research-Pack Writer
- Produce the human-readable English Research Pack.
- Keep claims conservative and traceable.
- Agent A4 — Citation Binder & QA
- Bind claims to source IDs.
- Validate citation completeness and BibTeX readiness.
- Emit TODO markers for unresolved metadata.
Stage gate rule: A2 cannot start before A1 completes; A3 cannot start before A2; A4 is the final gate before output.
A1 Parallel Dispatch Blueprint (Explicit Multi-Agent Search)
Within A1, use parallel fan-out with deterministic merge points:
- Claim fan-out (parallel): split user request into claim units (
C1...Cn). - Tri-vector fan-out per claim (parallel): run Vector A/B/C for each claim concurrently.
- Depth-2 recursive fan-out (conditional, parallel): only for weak/conflicting claims, spawn focused sub-queries (edition year, translation lineage, archival anchor, DOI mapping).
- A1 merge barrier: normalize all evidence into one claim-evidence map before handing off to A2.
Keep A2/A3/A4 strictly serial after A1 merge.
Non-Negotiable Rules
- Search first for factual historical claims. Do not rely on memory alone for dates, attributions, chronology, first-use claims, publication timelines, and historiographic disputes.
- Never fabricate citations, quotes, metadata, or page numbers.
- Keep output in English.
- Every key factual claim must have at least 1 high-quality source; if missing, mark as
TODO: missing high-quality source. - Trigger a dispute section only when there are at least 2 materially conflicting sources.
- For priority / first-use claims, require at least 2 independent sources.
- For web sources, always include
urlandurldate(repository bibliography norm). - If an external web image is necessary and cannot be reliably generated by AI drawing, add an explicit marker:
TODO: add external web image(include intended placement, why the image is needed, and source-attribution requirements). - Prose polishing is for clarity and academic quality only; do not use this workflow to conceal authorship provenance or misrepresent intellectual contribution.
- Never let drafting/process artifacts, or anything that may imply the use of AI appear in final manuscript output (e.g., prompt scaffolds, placeholder markers, model disclaimers, markdown/render artifacts).
- For mathematically substantive content (theorem/method/proof/derivation/conclusion about specific mathematical work), include meaningful formal artifacts (equations, derivation blocks, geometric or analytical figures, or compact technical tables) with sufficient density for real technical rigor, but never force a numeric quota that harms explanation quality.
- Every formal artifact must be explained: define symbols/variables, state what the formula or figure demonstrates, and connect it to the historical claim.
- Prefer historically faithful notation and proof style when presenting historical mathematics. If a modernized notation or streamlined proof is used, explicitly disclose this in the prose (e.g., "for simplicity" or "simplified treatment") and state that it differs from the historical notation/proof style.
Trigger Conditions
Use this skill when requests involve any of the following:
- Mathematician life timeline (birth/death, schools, institutions, major periods)
- Priority/attribution claims ("who first", "earliest known", "invented by")
- Historical development of a theorem, method, notation, or concept
- Comparison of competing historical narratives
- Source-backed writing for paper sections, especially when citations are needed
- Claim ledger support and BibTeX candidate generation
Do not use this skill for pure creative writing or opinion-only brainstorming with no factual verification requirement.
Search and Verification Workflow
Step 1 — Decompose into Claims
Break the user request into discrete, testable claims.
Examples:
- "X was born in year Y"
- "Notation Z first appeared in work W"
- "Method A influenced B through C"
Step 2 — Run Tri-Vector Retrieval (Parallel by Default)
Run three retrieval vectors in parallel whenever possible:
- Vector A: Primary / Authoritative
- Primary texts, critical editions, authoritative historical repositories, high-authority encyclopedic references.
- Vector B: Scholarly Secondary
- Peer-reviewed articles, scholarly monographs, chapter-level historical analysis.
- Vector C: Institutional Context
- University, academy, museum, or similarly authoritative institutional summaries.
For subsection-scale writing (one mathematician section), parallelize at least:
- Track 1: biography and timeline evidence
- Track 2: one major work/contribution evidence
Then merge before synthesis.
Step 2.1 — Recursive Parallel Search Policy (A1)
Inside A1, use recursive sub-agents when needed:
- Depth 0: top-level claims extracted from the user request.
- Depth 1: for each claim, run Vector A/B/C in parallel.
- Depth 2 (conditional): if evidence is weak/contradictory, spawn focused sub-queries (edition year, translation metadata, attribution lineage, etc.).
Stop recursion when either:
- evidence reaches Definition-of-Done thresholds, or
- no higher-quality source can be found after one refinement round.
Step 2.2 — Parallel Search Lanes for Section Writing
For one \subsubsection target, run at least these lanes in parallel inside A1:
- Lane L1 (Biography/Chronology): dates, institutions, timeline claims.
- Lane L2 (Technical Contribution): theorem/method/notation claims.
- Lane L3 (Attribution/Dispute): priority claims, historiographic conflicts.
Merge L1/L2/L3 before A2 verification.
Step 3 — Source Quality Ranking
Rank source quality before synthesis:
- Primary/critical editions and direct historical scholarship
- Peer-reviewed scholarly secondary sources
- Institutional references (universities/academies/museums)
- General web references
Prefer higher-ranked evidence when conflicts occur.
Step 4 — Conflict Handling
If at least 2 sources materially conflict on a key claim:
- open
Disagreements & Variants - state each variant explicitly
- identify which variant is better supported and why
- avoid collapsing unresolved disputes into one "fact"
Step 4.1 — Conflict Arbitration Rubric (A2)
When resolving conflicts, compare each candidate claim with these checks:
- Is it directly grounded in a primary source / critical edition?
- Is it supported by peer-reviewed scholarship?
- Does it provide verifiable bibliographic anchors (edition/page/DOI/archival reference)?
- Is it accepted by authoritative institutional or scholarly consensus?
Prefer the variant that wins more high-priority checks; if still unresolved, mark Disputed.
Step 5 — Metadata and Citation Readiness
For each cited source, capture what is available:
- author/editor/translator
- title
- publication year / edition year
- source type (
primary,peer-reviewed,institutional,web) - DOI or URL
- access date for web sources
- candidate BibTeX key
If metadata is incomplete, mark explicit TODO fields.
Output Contract (Research Pack v1)
Always output with this structure:
1) Direct Answer
A concise answer to the user’s main question.
2) Core Claims and Evidence
Claim-by-claim bullets:
- Claim
- Evidence summary
- Best source(s)
- Citation marker(s)
3) Disagreements & Variants (Conditional)
Include only when conflict threshold is met (>=2 conflicting sources).
4) Citation-Ready Source Table
A compact table with:
- source id
- author/title/year
- source type
- DOI/URL + access date (if web)
- candidate BibTeX key
- metadata completeness (
complete/partial)
5) Claim Ledger Suggestions
Provide rows that can be copied into claim-ledger workflows:
- claim text
- supporting source ids
- confidence
- TODOs (if any)
6) Visual Asset TODO (Conditional)
If the section would materially benefit from a non-AI-drawable external web image, include:
TODO: add external web image- intended LaTeX placement (e.g., section/subsection or figure slot)
- purpose of the image (what claim/context it supports)
- required attribution metadata (
author/source URL/license/access date)
7) Confidence Assessment (Mandatory)
End with:
- Source Quality: High / Medium / Low
- Historical Consensus: High / Medium / Disputed
- Evidence Coverage: Full / Partial
- Open Gaps: any unresolved metadata or source gaps
8) JSON Mirror (Optional but Recommended)
When downstream automation is expected, add a machine-readable block containing:
claims[]withclaim_id,text,source_ids,confidence,todossources[]with normalized metadata andcandidate_bibtex_keydisagreements[](if any)
This JSON mirror should be semantically aligned with the human-readable Research Pack.
9) Mathematical Formalism Coverage (Required for Technical Subsections)
When the target subsection discusses concrete mathematical work (not just context/history), include:
- equations/derivations and/or diagrams/tables with professional relevance,
- enough formal artifacts to preserve technical depth without compressing explanation,
- explanatory text after each formula/diagram (what it means, notation, historical significance).
For balance and readability, prefer an adequacy check over rigid percentages: technical readers should be able to reconstruct the mathematical idea, and general readers should still follow the argument.
Exemptions (allowed prose-dominant sections):
- broad historical background,
- historiography-only comparison,
- impact/significance conclusion with no technical claim.
If exempted, explicitly mark: Formalism exemption: historical/context-only subsection.
When a subsection uses modernized notation/proof for accessibility, add an explicit disclosure sentence such as: For simplicity, we use modern notation; this is a simplified treatment and differs from the historical notation/proof style.
Citation Binding Contract (A4)
Use strict claim-source binding:
- assign each key claim a stable
C#id (e.g.,C1,C2) - assign each source a stable
S#id (e.g.,S1,S2) - each claim must cite at least one
S# - each
S#row must include source type and metadata completeness
BibTeX-readiness rules (repository-aligned):
- candidate key format:
AuthorYYYYShortTitle - web entries must include
url+urldate - if metadata is incomplete, keep explicit TODO fields instead of guessing
Definition of Done (DoD)
A response is complete only if all checks pass:
- Every key claim has >=1 high-quality source.
- Every priority/first-use claim has >=2 independent sources.
- Source Table metadata completeness is >=80%.
- If conflicts exist,
Disagreements & Variantsis present. - Claim-to-source binding coverage is 100% (no orphan key claims).
- If an external web image is judged necessary and not AI-drawable, a
TODO: add external web imagemarker is present with placement + attribution requirements. - Anti-trace scan gate passes for the current target (
high=0;mediumreviewed). - For technical subsections, formal artifacts are substantively sufficient for rigor (no token math), and each formula/diagram has local explanatory text.
- Historical notation/proof fidelity is respected, or modernized treatment is explicitly disclosed with wording such as "for simplicity" / "simplified treatment" plus a note of divergence from historical practice.
Writing Style
- Keep language precise, neutral, and academically conservative.
- Distinguish clearly between facts, interpretations, and unresolved disputes.
- Avoid overclaiming certainty when evidence is thin.
- For equations/figures, use explain-then-interpret style: notation first, mathematical meaning second, historical relevance third.
Failure / Exception Behavior
Use graded failure levels:
- Level A (full success): retrieval succeeded and high-quality evidence is sufficient -> standard output.
- Level B (partial evidence): retrieval succeeded but key metadata/evidence is incomplete -> output with explicit
Partialflags + TODO. - Level C (retrieval failure): external retrieval unavailable -> provisional answer with strict uncertainty labeling + mandatory verification TODO.
If external retrieval fails completely (Level C):
- explicitly state that search was unavailable
- provide a provisional answer with clear uncertainty labeling
- include
TODOmarkers for mandatory verification before manuscript use
Writing Timing Decision for writing-clearly-and-concisely
For this repository, use a hybrid policy with post-draft as default:
- Default (recommended): post-draft pass
- Apply
writing-clearly-and-conciselyafter A3+A4 complete and claim/citation integrity is stable. - Rationale: institutional writing-process guidance consistently separates drafting from revising/editing; the skill itself recommends "write draft first, then copyedit." This avoids polishing text that may later be structurally rewritten.
- Optional pre-writing micro-use (lightweight)
- Before drafting, load only a concise style checklist (active voice, concrete language, omit needless words).
- Do not run full polishing before claim verification.
Operational rule:
- First optimize correctness and traceability (A1→A4), then optimize prose naturalness.
Tooling & Skill Invocation Guide (How to Reuse Existing Capabilities)
When available in this workspace, use capabilities in this order:
- A1 discovery (default): Copilot web search
- Use
@websearch/#websearchfor current-info discovery and candidate URL collection. - This path is preferred for this repository's history-of-mathematics research tasks.
- A1 source fetch (default): recursive URL collection
- Use the
fetchMCP (mcp-server-fetch) to read selected URLs and recursively fetch relevant linked pages. - Prefer this for citation-safe extraction from static pages, docs, and article-style sources.
- Scholarly indexing and metadata expansion
- Use
openalex-databaseskill to find related works/DOIs and citation graph context.
- Citation normalization
- Use
citation-managementskill to convert verified metadata into BibTeX-ready entries.
- Interactive browser fallback (conditional)
- Use
web-accessonly when needed: dynamic rendering, login-required pages, or interactive workflows. - Do not use browser automation by default when lighter retrieval layers already satisfy evidence needs.
- Writing/paper integration (optional)
- Use
latex-paper-enfor section drafting polish. - Use
paper-auditfor reviewer-style sanity checks.
- Clarity and concision pass (recommended after A4)
- Use
writing-clearly-and-conciselyto reduce robotic phrasing and improve sentence rhythm while preserving factual claims and citations.
Conflict-avoidance rule for this repository:
- Use a single primary retrieval path per claim by default:
websearch -> fetch -> openalex. - Escalate to
web-accessonly when the default path cannot obtain required evidence. - Do not run multiple retrieval stacks redundantly for the same claim unless conflict verification requires a second pass.
Suggested stage-to-tool map:
- A1:
@websearch/#websearch+fetchMCP +openalex-database(fallback:web-access) - A2: source-quality rubric + conflict arbitration
- A3: research-pack drafting (
latex-paper-en) - A4:
citation-management+ binding QA - Postflight: anti-trace scanner + optional
paper-audit
If one capability is unavailable, continue with remaining ones and mark the gap explicitly.
Anti-Trace Postflight Gate (Required)
Use this gate to prevent visible drafting/tool artifacts from leaking into final PDF output.
Script and checklist
- Script:
scripts/scan_ai_trace_artifacts.py - Checklist:
references/ANTI_TRACE_SCAN_CHECKLIST.md
One-click full-manuscript command
Run from manuscript root (main.tex directory):
python "$SKILL_DIR/scripts/scan_ai_trace_artifacts.py" --pdf main.pdf --source-root . --fail-on medium --json-output research/anti_trace_report.json
Recommended cadence (answer to "last step vs final 50 pages")
Use a two-tier strategy:
- During writing (fast gate): source-only quick scan after each completed subsection.
- At integration milestones: full scan after each chapter merge.
- Near-final manuscript (~50 pages): mandatory full-manuscript gate before submission/export.
This catches leaks early while still enforcing a strict final integrated audit on the full PDF.
Integration Notes for This Repository
- Main paper body is English: keep Research Pack output directly reusable in English drafting.
- Respect citation integrity: no fabricated references or quotations.
- Prioritize claim traceability so outputs can flow into bibliography and claim-ledger steps.
- For external web images, do not fabricate figures: emit TODO + attribution requirements so the user can add licensed assets manually.
- If the user asks for "human-like" prose, interpret this as readability/disciplinary tone improvement, not authorship concealment.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

