菜单
Locate the active project, validate workspace state, and load required artifacts before any command executes.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | workspace-setup |
| description | Locate the active project, validate workspace state, and load required artifacts before any command executes. |
Run this skill at the start of every command invocation, before reading any project artifacts or dispatching any agent.
projects/active/."No active project found under
projects/active/. Create a project folder first (e.g.projects/active/my-topic/) with at least anotes/overview.mdand aproject.yaml."
$SLUG and proceed.Load these files in order. If any is missing, note it and continue (do not abort unless the command strictly requires it):
| File | Required for |
|---|---|
projects/active/$SLUG/project.yaml | All commands |
projects/active/$SLUG/notes/overview.md | All commands |
projects/active/$SLUG/literature/map.md | Literature, Ideation, Writer |
projects/active/$SLUG/conjectures/conjectures.md | Modeling, Proof, Writer |
projects/active/$SLUG/models/model_v<current>.md | Proof, Simulation, Writer |
The value of current_model_version is in project.yaml; use it to
resolve model_v<current>.md.
If present, also read these optional venue fields from project.yaml:
target_venuebackup_venuesvenue_familypublication_barloop_historyRead mode from project.yaml (values: discovery | project).
mode: discovery and the command is proof-pass or
experiment-pass → refuse immediately:
"The project is in discovery mode. Proof and simulation passes require the project to be in 'project' mode. Run a modeling pass and promote to project mode first."
inbox/Check projects/active/$SLUG/inbox/ for any PDF files.
literature-review or
ideate, note them in the context you pass to the Literature agent.
The inbox-parser skill handles the actual extraction.Surface a one-line preamble before proceeding:
"Active project:
$SLUG| mode:$MODE| model:$MODEL_VERSION| target venue:$TARGET_VENUE| open claims:$OPEN_COUNT| inbox PDFs:$PDF_COUNT"
Replace unavailable values with —.
| Situation | Action |
|---|---|
project.yaml missing | Warn, assume mode: discovery, proceed |
notes/overview.md missing | Ask the user for a brief topic before dispatching |
| Active project folder unreadable | Abort, report the path |
Academic research assistant for literature reviews, paper analysis, and scholarly writing. Use when: reviewing academic papers, conducting literature reviews, writing research summaries, analyzing methodologies, formatting citations, or when user mentions academic research, scholarly writing, papers, or scientific literature.
Adversarial review of mathematical proofs, theorems, and formal arguments. Use when asked to review a proof, check a paper's correctness, verify a theorem, find bugs in mathematical reasoning, audit a derivation, or stress-test a formal argument. Implements iterative self-correction from Woodruff et al. (2026) and the Generator-Verifier-Reviser pattern from Aletheia (Feng et al., 2026).
Read, update, and promote claim statuses through the controlled vocabulary. Includes the project.yaml patch protocol and the conjectures.md update procedure.
Systematically test mathematical conjectures by searching for counterexamples, verifying small cases, and constructing proofs or refutations. Use when Raman proposes a conjecture, when a paper claims an unproven bound, when testing whether a theorem generalizes, or when asked to "find a counterexample," "test this conjecture," "verify this bound," or "check if this holds." Implements the simulation and counterexample search techniques from Woodruff et al. (2026) and the neuro-symbolic verification loop from Aletheia (Feng et al., 2026).
Generate research ideas by finding cross-disciplinary connections, retrieving obscure theorems from distant fields, and identifying analogies between different mathematical domains. Use when Raman asks for new research directions, when ingesting a paper that might connect to other fields, when looking for "bridges" between topics, or when asked to "find connections," "what other fields use this technique," or "cross-pollinate." Implements the cross-pollination techniques from Woodruff et al. (2026, Section 2.2, 4.x) and AI Behavioral Science's framework for studying AI-human strategic interactions (Jackson et al., 2025).
Classify each prose claim before writing to paper/paper.md. Enforce the controlled vocabulary and reject illegal proof language.