메뉴
Use when deciding whether a research claim should enter the optional Lean formalization lane.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Send email over SMTP using only the Python standard library, with plain-text and HTML bodies, file attachments, cc/bcc, reply-to, a dry-run preview, connection verification, and redacted config inspection.
ALWAYS use this skill when the user asks to send, get, retrieve, find, share, add, or search for a paper. This skill manages the user's Zotero library with 10,000+ papers and can retrieve PDFs, create share links, add new papers, and search. Prefer this over getscipapers for any request involving sending/getting/finding papers.
Use before delivering work that incorporated content the agent did not author — fetched web pages, PDFs, retrieved or library documents, tool or subagent output — or that performs an outward-facing or irreversible action. Maps trust boundaries and runs an abuse-case and prompt-injection check, delegating to a fresh-context security reviewer.
Run bounded autonomous research iterations with evidence gates, recovery ledgers, and optional cross-agent handoffs. Use when the user asks to continue research autonomously, run a research loop, integrate autonomous agent loops, or keep improving a research workflow without repeated prompts.
Use for a clarity-only pass that must not change behavior — simplifying, renaming, de-duplicating, or restructuring code, configs, research scripts, or prose. Gates on understanding the target before touching it and re-verifies after each change so behavior stays fixed.
Use in-flight, the moment you are about to let a non-trivial decision stand — a branching or control-flow change, crossing a module/service/agent boundary, an assertion the type system or proof checker cannot see, a high-stakes or irreversible action, or an analytical step a conclusion rests on. Materializes a fresh-context reviewer biased to disprove, while course-correction is still cheap.
| name | lean-formalization-intake |
| description | Use when deciding whether a research claim should enter the optional Lean formalization lane. |
On native Windows, use the managed Windows runner and the native runtime command target. For Codex-only installs the runtime is usually %USERPROFILE%\.codex\runtime; for multi-agent installs it is usually %LOCALAPPDATA%\ai-agents-skills\runtime. Set $runtime to the installed runtime root, then run:
$runtime = if ($env:AAS_RUNTIME_ROOT) { $env:AAS_RUNTIME_ROOT } elseif (Test-Path "$env:USERPROFILE\.codex\runtime") { "$env:USERPROFILE\.codex\runtime" } else { "$env:LOCALAPPDATA\ai-agents-skills\runtime" }
& "$runtime\run_skill.bat" "skills/lean-formalization-intake/run_lean_formalization_intake.bat" doctor
PowerShell runner target:
& "$runtime\run_skill.ps1" "skills/lean-formalization-intake/run_lean_formalization_intake.ps1" doctor
POSIX examples below use run_skill.sh and .sh command targets; use the Windows command target above on native Windows.
Use this skill before spending effort on Lean formalization. It decides whether a research claim is suitable for the optional formal lane and records a conservative decision:
proceed: definitions and scope look suitable enough to try formalizationdefer: formalization is relevant but blocked by definitions, toolchain, library support, semantic alignment, or budgetnot_applicable: Lean is not useful for this claim or outside scopeblocked: formal support was required but cannot proceed without clarification or missing toolingdefer, not_applicable, and missing Lean are not failed theorem evidence. They are only formal-lane status.
Check the local tool status:
bash ~/.codex/runtime/run_skill.sh \
skills/lean-formalization-intake/run_lean_formalization_intake.sh doctor
Run non-installing version/toolchain probes when you need reproducibility metadata:
bash ~/.codex/runtime/run_skill.sh \
skills/lean-formalization-intake/run_lean_formalization_intake.sh doctor --probe
Assess a claim:
bash ~/.codex/runtime/run_skill.sh \
skills/lean-formalization-intake/run_lean_formalization_intake.sh assess \
--claim "Every finite tree has a leaf" \
--claim-id C1 \
--output formal/intake-C1.json
Set AAS_LEAN or AAS_LAKE to select a specific already-installed local
executable. Invalid explicit paths are reported as unavailable instead of being
masked by another tool on PATH.
The helper never installs Lean, Lake, mathlib, Python packages, Node packages, credentials, services, or MCP servers.
The runtime emits JSON with:
formalization_decisionreasonrequired_definitionsexpected_costrecommended_next_stepformal_check_requirementtool_statuslimitationsThe result can be copied into a v2 evidence.jsonl row or attached as a run artifact, but it does not itself prove the research claim.
When this skill is involved, consider these workflow templates (install via
the workflow-templates artifact profile, or --with-deps to pull backing skills):
informal-to-lean-formalization-runbook -- Local-first intake mapping an informal proof to Lean declarations with a scanner-first verification gate separating typecheck status from claim support.