math-workflow
/math-workflow
Rozwiązuje, sprawdza i tłumaczy zadania matematyczne, przeszukuje dołączony korpus OpenAI i weryfikuje formalizacje w Lean.
- Autor
- userbox020 ↗
- Repozytorium
- opencode-math-copilot ↗
- Licencja
- Apache-2.0
- Ostatnia zmiana repozytorium
- 10.11.2026
Ocena i bezpieczeństwo
- Pliki w paczce
- 1
- Skrypty
- 0
- Komentarze HTML
- 0
- Adresy URL w SKILL.md
- 0
Brak sygnałów. Repozytorium zmienione 10.11.2026, bez odwołań do wycofanych modeli i API.
Apache-2.0, otwarta: można używać i zmieniać, z zachowaniem licencji i informacji o zmianach.
Co robi i kiedy
Rozwiązuje, sprawdza i tłumaczy zadania matematyczne, przeszukuje dołączony korpus OpenAI i weryfikuje formalizacje w Lean.
Oryginalny opis (EN)
Use when solving, checking, or explaining a mathematical problem, searching the bundled OpenAI math corpus, or verifying Lean formalizations.
Jak działa
- Workflow
- Corpus and verification guardrails
- Tool-use patterns
- Answer shape
Podgląd SKILL.md
--- name: math-workflow description: Use when solving, checking, or explaining a mathematical problem, searching the bundled OpenAI math corpus, or verifying Lean formalizations. --- # Math workflow Solve the user's stated problem. Do not turn it into a broad research project. ## Workflow 1. Restate the problem and identify its mathematical domain. Determine whether the user wants a proof, computation, corpus lookup, or formal verification; clarify only blocking ambiguities. 2. Use `math_search` for related manuscripts and strategies. Start broad, then narrow by terminology or hypotheses. Use `math_manuscript` to read only the relevant abstract, outline, or LaTeX section. If the TeX source is missing or you need the released wording, use `math_pdf_text` on selected pages or `math_pdf_search` to locate a phrase first. 3. For a proof, give a lemma plan before algebra. Separate results cited from the corpus from new derivation, and check that each cited result's hypotheses apply. 4. For requested formal verification or a Lean statement, use `math_lean_search` to locate existing declarations, `math_lean_check` on small snippets first, then `math_lean_verify` with a trusted target type and the declared axiom policy for a named user solution. Use `math_lean_build` for the focused target and `math_comparator` only when a matching challenge config exists. Do not build the entire package by default. 5. For numerical or symbolic work, use `math_compute` for allowlisted SymPy operations. Otherwise show the computation and state the execution limitation. Numerical evidence is not a proof of an exact claim. 6. Independently check edge cases, quantifiers, hypotheses, and intermediate steps. Confirm whether each Lean check actually passed and what statement it checked; a passing unrelated snippet does not verify the requested theorem. ## Corpus and verification guardrails - `math/CONTENTS.md` maps 721 manuscripts in 373 result families. The archive contains raw research outputs, not independently certified results. - Currently 175 papers have Lean formalizations; `math/lean/formalization.yaml` is the catalogue. Presence in the catalogue does not certify every claim in a paper. - Check `math/history.md` when a result looks suspicious; it records revisions and withdrawals. Do not rely silently on a withdrawn result. - Never claim a paper is verified merely because it is in the corpus. - Compilation is not proof verification. For a user solution require `math_lean_verify` with `proof.status: "verified"`, a trusted `expectedType`, and the declared axiom policy. `math_lean_check` and `math_lean_build` report only compilation/build; `math_comparator` reports its challenge validation result. Report failures, skipped checks, missing prerequisites, and remaining gaps explicitly. - `math/lean/` is the single Lake package `OAI`, pinned to `leanprover/lean4:v4.34.1`. Prefer focused targets such as `OAI.Analysis`. - Use `math_status` to inspect current availability; do not treat an unavailable check as success. Native Windows Lean builds can be blocked by an NTFS-invalid path in the pinned dependency set, and Comparator/landrun require Linux/WSL. Report such blockers instead of silently switching claims. - Cite source paths relative to `math/`, for example `lean/formalization.yaml`, with manuscript identifiers and section names where available. ## Tool-use patterns - Query broad first, then narrow; do not perform repo-wide discovery for a localized question. - Read relevant sections rather than whole PDFs. Resolve released PDF paths from metadata rather than assuming a filename; use `math_pdf_search` to find a phrase, then `math_pdf_text` for the selected pages. - If the manuscript is unknown, use `math_pdf_corpus_search` for a bounded PDF search across top indexed candidates (default 5, pages 1-2). It is not a full-text index; no matches does not establish absence from the corpus. - Use `math_pdf_index_search` for discovery across prebuilt selected-page excerpts (default first 2 pages; no OCR, not full text), then `math_pdf_search` for deeper lookup; `math_doctor` reports corpus/index/cache and tool health. - Prefer `math_grep` for exact names or notation in TeX, Markdown, and Lean; use `math_lean_search` for declaration names. Scope searches to relevant files or directories when possible. - Use `math_compute` for symbolic checks, but state the operation and verify the returned expression independently. - Keep output bounded: summarize matches and quote only the needed statements or proof steps. - Use `math_reindex` after `math/` changes when the index needs refreshing. ## Answer shape 1. **Theorem / claim:** precise statement, assumptions, and scope. 2. **Proof / derivation:** lemma plan and justified steps, or the requested computation or lookup. 3. **Verification status:** checks actually run, outcomes, and limits of their coverage. 4. **Sources:** relevant corpus paths and sections; distinguish citations from new work. 5. **Open gaps:** unresolved steps or missing checks, or explicitly none identified.
Wersje
W bazie nie ma innych skilli o nazwie math-workflow.
Migawka bazy z 13.11.2026 · wersja paczki 5a8e9cb8cc44 (skrót SHA-256 całej paczki)
Pobrania w ostatnich 30 dniach: 0 · ranking
Zgłoś problem z tym skillem: szkodliwa treść, błędny opis albo prośba autora o usunięcie.
Podobne skille
- 100everythingmath
Rozwiązuje zadania matematyczne od początku do końca: rozwiązuje, dowodzi, sprawdza i opisuje wynik trzema niezależnymi kontrolami. - 100lean-proof-patterns
Przekłada rozumowanie matematyczne na jawne taktyki Lean, kontrolowane przepisywanie i czytelną strukturę dowodu przy pisaniu i poprawianiu. - 100math-paper-writing
Pisze, poprawia i audytuje rękopisy matematyczne oraz materiały do zgłoszenia, wyciągając styl autora z jego własnych tekstów. - 100ez-math-model
Prowadzi przez zadania modelowania matematycznego z konkursów CUMCM, MCM i ICM: dobór modelu, rozwiązanie w Pythonie, wykresy, tekst pracy i audyt jakości. - 90dpf-mathematical-thinking
Konstruuje obiekty i działania matematyczne, wyprowadza konsekwencje i spełnia wymagania dowodowe. - 100verify-math
Weryfikuje algebrę, rachunek różniczkowy, tożsamości, rozwiązywanie równań i nietrywialne kroki wyprowadzeń za pomocą SymPy.