Skip to main content

skill-logic-research

Research mathematical logic tasks using domain context and codebase exploration. Invoke for logic-language research involving modal logic, Kripke semantics, and related mathematical foundations.

跳到安装

来源信息

仓库
benbrastmckie/nvim
最近来源活动
2026年7月14日 23:14
检测到的 SKILL.md 语言
英语
星标
444
分支
459

安装方式

默认使用会先检查来源的 Prompt;你也可以切换为直接命令,或下载本地副本。

检查来源文件

决定是否安装前,请先阅读 SKILL.md,以及 SkillsMP 当前展示的配套文件。

正在显示 SKILL.md

SKILL.md
来源说明 · 只读预览
name
skill-logic-research
description
Research mathematical logic tasks using domain context and codebase exploration. Invoke for logic-language research involving modal logic, Kripke semantics, and related mathematical foundations.
allowed-tools
Agent, Bash, Edit, Read, Write
# Logic Research Skill Thin wrapper that delegates mathematical logic research to `logic-research-agent` subagent. **IMPORTANT**: This skill implements the skill-internal postflight pattern. After the subagent returns, this skill handles all postflight operations (status update, artifact linking, git commit) before returning. ## Context References Reference (do not load eagerly): - Path: `.claude/context/formats/return-metadata-file.md` - Metadata file schema Note: This skill is a thin wrapper with internal postflight. Context is loaded by the delegated agent. ## Trigger Conditions This skill activates when: - Task type is "logic" - Research involves modal logic, Kripke semantics, or general mathematical logic - Domain context files are needed for mathematical foundations --- ## Execution Flow ### Stage 1: Input Validation Validate required inputs: - `task_number` - Must be provided and exist in state.json - `focus_prompt` - Optional focus for research direction ```bash # Lookup task task_data=$(jq -r --argjson num "$task_number" \ '.active_projects[] | select(.project_number == $num)' \ specs/state.json) # Validate exists if [ -z "$task_data" ]; then return error "Task $task_number not found" fi # Extract fields task_type=$(echo "$task_data" | jq -r '.task_type // "general"') status=$(echo "$task_data" | jq -r '.status') project_name=$(echo "$task_data" | jq -r '.project_name') description=$(echo "$task_data" | jq -r '.description // ""') ``` --- ### Stage 2: Preflight Status Update Update task status to "researching" BEFORE invoking subagent. --- ### Stage 3: Create Postflight Marker Create the marker file to prevent premature termination. --- ### Stage 4: Prepare Delegation Context Prepare delegation context for the subagent: ```json { "session_id": "sess_{timestamp}_{random}", "delegation_depth": 1, "delegation_path": ["orchestrator", "research", "skill-logic-research"], "timeout": 3600, "task_context": { "task_number": N, "task_name": "{project_name}", "description": "{description}", "task_type": "logic" }, "focus_prompt": "{optional focus}", "metadata_file_path": "specs/{NNN}_{SLUG}/.return-meta.json" } ``` --- ### Stage 5: Invoke Subagent **CRITICAL**: You MUST use the **Agent** tool to spawn the subagent. **Required Tool Invocation**: ``` Tool: Agent (NOT Skill, NOT Plan) Parameters: - subagent_type: "logic-research-agent" - prompt: [Include task_context, delegation_context, focus_prompt, metadata_file_path] - description: "Execute logic research for task {N}" ``` **DO NOT** use `Skill(logic-research-agent)` - this will FAIL. The subagent will: - Load domain context files from `.claude/context/project/logic/` - Search codebase for existing patterns - Use Mathlib lookup tools (lean_leansearch, lean_loogle, lean_leanfinder, lean_local_search) - Execute web research for mathematical logic literature - Create research report in `specs/{NNN}_{SLUG}/reports/` - Write metadata to `specs/{NNN}_{SLUG}/.return-meta.json` - Return a brief text summary (NOT JSON) --- ### Stage 5b: Self-Execution Fallback **CRITICAL**: If you performed the work above WITHOUT using the Agent tool (i.e., you read files, wrote artifacts, or updated metadata directly instead of spawning a subagent), you MUST write a `.return-meta.json` file now before proceeding to postflight. Use the schema from `return-metadata-file.md` with status value "researched". If you DID use the Agent tool, skip this stage -- the subagent already wrote the metadata. --- ## Postflight (ALWAYS EXECUTE) The following stages MUST execute after work is complete, whether the work was done by a subagent or inline (Stage 5b). Do NOT skip these stages for any reason. ### Stage 6: Parse Subagent Return (Read Metadata File) Read the metadata file. --- ### Stage 7: Update Task Status (Postflight) If status is "researched", update state.json and TODO.md. --- ### Stage 8: Link Artifacts Add artifact to state.json with summary. Update TODO.md per `@.claude/context/patterns/artifact-linking-todo.md` with `field_name=**Research**`, `next_field=**Plan**`. --- ### Stage 9: Git Commit Commit changes with session ID using targeted staging. --- ### Stage 10: Cleanup Remove marker and metadata files. --- ### Stage 11: Return Brief Summary Return a brief text summary (NOT JSON). Example: ``` Research completed for task {N}: - Found existing patterns in source files - Loaded domain context for modal logic and Kripke semantics - Used Mathlib lookup tools to discover relevant theorems - Created report at specs/{NNN}_{SLUG}/reports/MM_{short-slug}.md - Status updated to [RESEARCHED] - Changes committed ``` --- ## Error Handling ### Input Validation Errors Return immediately with error message if task not found. ### Metadata File Missing If subagent didn't write metadata file: 1. Keep status as "researching" 2. Do not cleanup postflight marker 3. Report error to user ### Git Commit Failure Non-blocking: Log failure but continue with success response. ### Subagent Timeout Return partial status if subagent times out (default 3600s). Keep status as "researching" for resume. --- ## Return Format This skill returns a **brief text summary** (NOT JSON). The JSON metadata is written to the file and processed internally.
在 GitHub 查看