skill-lean-research
$
npx mdskill add benbrastmckie/nvim/skill-lean-researchThin wrapper that delegates Lean research to `lean-research-agent` subagent.
SKILL.md
.github/skills/skill-lean-researchView on GitHub ↗
---
name: skill-lean-research
description: Research Lean 4 and Mathlib for theorem proving tasks. Invoke for Lean-language research using LeanSearch, Loogle, and lean-lsp tools.
allowed-tools: Agent, Bash, Edit, Read, Write
---
# Lean Research Skill
Thin wrapper that delegates Lean research to `lean-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.
## Trigger Conditions
This skill activates when:
- Task type is "lean4" or "lean" (either accepted)
- Research involves Mathlib, theorems, or proofs
- Lean-specific MCP tools are needed
---
## 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 "$task_data" | jq -r '.description // ""')
```
---
### Stage 2: Preflight Status Update
Update task status to "researching" BEFORE invoking subagent.
**Update state.json**:
```bash
jq --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" \
--arg status "researching" \
--arg sid "$session_id" \
'(.active_projects[] | select(.project_number == '$task_number')) |= . + {
status: $status,
last_updated: $ts,
session_id: $sid
}' specs/state.json > specs/tmp/state.json && mv specs/tmp/state.json specs/state.json
```
**Update TODO.md**: Use Edit tool to change status marker from `[NOT STARTED]` or `[RESEARCHED]` to `[RESEARCHING]`.
---
### Stage 3: Prepare Delegation Context
Prepare delegation context for the subagent:
```json
{
"session_id": "sess_{timestamp}_{random}",
"delegation_depth": 1,
"delegation_path": ["orchestrator", "research", "skill-lean-research"],
"timeout": 3600,
"task_context": {
"task_number": N,
"task_name": "{project_name}",
"description": "{description}",
"task_type": "lean"
},
"focus_prompt": "{optional focus}",
"metadata_file_path": "specs/{N}_{SLUG}/.return-meta.json"
}
```
---
### Stage 4: 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: "lean-research-agent"
- prompt: [Include task_context, delegation_context, focus_prompt, metadata_file_path]
- description: "Execute Lean research for task {N}"
```
**DO NOT** use `Skill(lean-research-agent)` - this will FAIL.
The subagent will:
- Search Mathlib using lean_leansearch, lean_loogle, lean_leanfinder
- Verify theorems with lean_local_search and lean_hover_info
- Analyze findings and synthesize recommendations
- Create research report in `specs/{N}_{SLUG}/reports/`
- Write metadata to `specs/{N}_{SLUG}/.return-meta.json`
- Return a brief text summary (NOT JSON)
---
### Stage 4b: 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 the appropriate status value for this operation.
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 4b). Do NOT skip these stages for any reason.
### Stage 5: Parse Subagent Return
Read the metadata file:
```bash
metadata_file="specs/${padded_num}_${project_name}/.return-meta.json"
if [ -f "$metadata_file" ] && jq empty "$metadata_file" 2>/dev/null; then
status=$(jq -r '.status' "$metadata_file")
artifact_path=$(jq -r '.artifacts[0].path // ""' "$metadata_file")
artifact_type=$(jq -r '.artifacts[0].type // ""' "$metadata_file")
artifact_summary=$(jq -r '.artifacts[0].summary // ""' "$metadata_file")
else
echo "Error: Invalid or missing metadata file"
status="failed"
fi
```
---
### Stage 6: Update Task Status (Postflight)
If status is "researched", update state.json and TODO.md:
**Update state.json**:
```bash
jq --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" \
--arg status "researched" \
'(.active_projects[] | select(.project_number == '$task_number')) |= . + {
status: $status,
last_updated: $ts,
researched: $ts
}' specs/state.json > specs/tmp/state.json && mv specs/tmp/state.json specs/state.json
```
**Update TODO.md**: Use Edit tool to change status marker from `[RESEARCHING]` to `[RESEARCHED]`.
**On partial/failed**: Keep status as "researching" for resume.
---
### Stage 7: Link Artifacts
Add artifact to state.json with summary.
```bash
if [ -n "$artifact_path" ]; then
jq --arg path "$artifact_path" \
--arg type "$artifact_type" \
--arg summary "$artifact_summary" \
'(.active_projects[] | select(.project_number == '$task_number')).artifacts += [{"path": $path, "type": $type, "summary": $summary}]' \
specs/state.json > specs/tmp/state.json && mv specs/tmp/state.json specs/state.json
fi
```
**Update TODO.md**: Link artifact using count-aware format. Apply the four-case Edit logic from `@.claude/context/patterns/artifact-linking-todo.md` with `field_name=**Research**`, `next_field=**Plan**`.
---
### Stage 8: Git Commit
Commit changes with session ID:
```bash
git add \
"specs/${padded_num}_${project_name}/reports/" \
"specs/${padded_num}_${project_name}/.return-meta.json" \
"specs/TODO.md" \
"specs/state.json"
git commit -m "task ${task_number}: complete research
Session: ${session_id}
```
---
### Stage 9: Return Brief Summary
Return a brief text summary (NOT JSON). Example:
```
Research completed for task {N}:
- Found {count} relevant Mathlib theorems
- Identified proof strategy: {strategy}
- Created report at specs/{N}_{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. 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.
More from benbrastmckie/nvim
- skill-analyzeCompetitive landscape research with positioning maps
- skill-budgetGrant budget spreadsheet generation with forcing questions. Invoke for budget tasks.
- skill-consultRoute design consultations to domain-specific design partner agents
- skill-deckGenerate YC-style investor pitch decks in Typst
- skill-deck-implementRoute deck implementation to deck-builder-agent for Slidev pitch deck generation
- skill-deck-planPitch deck planning with interactive template, content, and ordering selection
- skill-deck-researchPitch deck content research through material synthesis
- skill-docx-editIn-place DOCX editing routing to docx-edit-agent
- skill-epi-implementImplementation skill for R-based epidemiology analysis. Invoke for epi/epi:study implementation tasks.
- skill-epi-researchResearch skill for epidemiology study design and analysis planning. Invoke for epi/epi:study research tasks.