skill-deck-research

Pitch deck content research through material synthesis

438 stars

Best use case

skill-deck-research is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Pitch deck content research through material synthesis

Teams using skill-deck-research should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/skill-deck-research/SKILL.md --create-dirs "https://raw.githubusercontent.com/benbrastmckie/nvim/main/.claude/extensions/founder/skills/skill-deck-research/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/skill-deck-research/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How skill-deck-research Compares

Feature / Agentskill-deck-researchStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Pitch deck content research through material synthesis

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

SKILL.md Source

# Deck Research Skill

Thin wrapper that routes pitch deck research requests to the `deck-research-agent`.

**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 Pointers

Reference (do not load eagerly):
- Path: `.claude/context/formats/subagent-return.md`
- Purpose: Return validation
- Load at: Subagent execution only

Note: This skill is a thin wrapper. Context is loaded by the delegated agent, not this skill.

## Trigger Conditions

This skill activates when:

### Direct Invocation
- User explicitly runs `/deck` command with task number
- User runs `/research` on a founder task with `task_type: "deck"`

### Implicit Invocation (during task implementation)

When an implementing agent encounters any of these patterns:

**Plan step language patterns**:
- "Create pitch deck"
- "Build investor presentation"
- "Deck content research"
- "Slide content extraction"

**Target mentions**:
- "pitch deck"
- "investor deck"
- "slide deck"
- "YC 10-slide"

### When NOT to trigger

Do not invoke for:
- Market sizing (use skill-market)
- Competitive analysis (use skill-analyze)
- Financial modeling (use skill-finance)
- Standalone deck generation without task workflow

---

## Execution Flow

### Stage 1: Input Validation

Validate required inputs:
- `task_number` - Must be provided and exist in state.json
- `purpose` - Optional, one of: INVESTOR, UPDATE, INTERNAL, PARTNERSHIP

```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
language=$(echo "$task_data" | jq -r '.language // "founder"')
status=$(echo "$task_data" | jq -r '.status')
project_name=$(echo "$task_data" | jq -r '.project_name')
description=$(echo "$task_data" | jq -r '.description // ""')

# Extract pre-gathered forcing_data (if present)
forcing_data=$(echo "$task_data" | jq -r '.forcing_data // null')
pre_gathered_purpose=$(echo "$forcing_data" | jq -r '.purpose // null' 2>/dev/null)

# Validate purpose if provided
if [ -n "$purpose" ]; then
  case "$purpose" in
    INVESTOR|UPDATE|INTERNAL|PARTNERSHIP) ;;
    *) return error "Invalid purpose: $purpose. Must be INVESTOR, UPDATE, INTERNAL, or PARTNERSHIP" ;;
  esac
fi
```

---

### 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 to `[RESEARCHING]`.

---

### Stage 3: Create Postflight Marker

```bash
padded_num=$(printf "%03d" "$task_number")
mkdir -p "specs/${padded_num}_${project_name}"

cat > "specs/${padded_num}_${project_name}/.postflight-pending" << EOF
{
  "session_id": "${session_id}",
  "skill": "skill-deck-research",
  "task_number": ${task_number},
  "operation": "research",
  "reason": "Postflight pending: status update, artifact linking, git commit",
  "created": "$(date -u +%Y-%m-%dT%H:%M:%SZ)"
}
EOF
```

---

### Stage 4: Prepare Delegation Context

Include pre-gathered forcing_data when available:

```json
{
  "task_context": {
    "task_number": N,
    "project_name": "{project_name}",
    "description": "{description}",
    "language": "founder",
    "task_type": "deck"
  },
  "forcing_data": {
    "purpose": "{pre_gathered_purpose}",
    "source_materials": ["task:123", "/path/to/file.md"],
    "context": "{company/project description}",
    "gathered_at": "{timestamp}"
  },
  "metadata_file_path": "specs/{NNN}_{SLUG}/.return-meta.json",
  "metadata": {
    "session_id": "sess_{timestamp}_{random}",
    "delegation_depth": 1,
    "delegation_path": ["orchestrator", "deck", "skill-deck-research"]
  }
}
```

**Note**: If `forcing_data` is present from STAGE 0 of /deck command, pass it to the agent.
The agent will use pre-gathered data for material ingestion.

---

### Stage 5: Invoke Agent

**CRITICAL**: You MUST use the **Task** tool to spawn the agent.

**Required Tool Invocation**:
```
Tool: Task (NOT Skill)
Parameters:
  - subagent_type: "deck-research-agent"
  - prompt: [Include task_context, forcing_data, metadata_file_path, metadata]
  - description: "Pitch deck content research through material synthesis"
```

The agent will:
- Use pre-gathered forcing_data for material sources
- Read all source materials (files, task references)
- Map content to 10-slide YC structure
- Ask at most 1-2 follow-up questions for critical gaps
- Create research report at specs/{NNN}_{SLUG}/reports/
- Write metadata file
- Return brief text summary

---

### Stage 6: Parse Subagent Return

```bash
padded_num=$(printf "%03d" "$task_number")
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
    status="failed"
fi
```

---

### Stage 7: 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
  }' 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 to `[RESEARCHED]`.

---

### Stage 8: Link Artifacts

Add artifact to state.json with summary.

**IMPORTANT**: Use two-step jq pattern to avoid escaping issues.

```bash
if [ -n "$artifact_path" ]; then
    # Step 1: Filter out existing research artifacts (use "| not" pattern)
    jq '(.active_projects[] | select(.project_number == '$task_number')).artifacts =
        [(.active_projects[] | select(.project_number == '$task_number')).artifacts // [] | .[] | select(.type == "research" | not)]' \
      specs/state.json > specs/tmp/state.json && mv specs/tmp/state.json specs/state.json

    # Step 2: Add new research artifact
    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**: Add research artifact link using count-aware format.

**Strip specs/ prefix for TODO.md** (TODO.md is inside specs/): `todo_link_path="${artifact_path#specs/}"`

Use count-aware artifact linking format per `.claude/rules/state-management.md` "Artifact Linking Format".

---

### Stage 9: Git Commit

```bash
git add -A
git commit -m "task ${task_number}: complete research

Session: ${session_id}

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>"
```

---

### Stage 10: Cleanup

```bash
rm -f "specs/${padded_num}_${project_name}/.postflight-pending"
rm -f "specs/${padded_num}_${project_name}/.postflight-loop-guard"
rm -f "specs/${padded_num}_${project_name}/.return-meta.json"
```

---

### Stage 11: Return Brief Summary

```
Pitch deck research completed for task {N}:
- Purpose: {purpose}, analyzed {N} source materials
- Slides populated: {M}/10 with extracted content
- Critical gaps: {G} identified
- Pre-gathered data used: {yes/no}
- Research report: specs/{NNN}_{SLUG}/reports/01_{short-slug}.md
- Status updated to [RESEARCHED]
- Changes committed
- Next: Run /plan {N} to create deck implementation plan
```

---

## Return Format

Brief text summary (NOT JSON).

Expected successful return:
```
Pitch deck research completed for task 234:
- Purpose: INVESTOR, analyzed 3 source materials
- Slides populated: 7/10 with extracted content
- Critical gaps: 3 (ask amount, traction numbers, financial projections)
- Pre-gathered data used: yes (purpose and sources from STAGE 0)
- Research report: specs/234_seed_round_pitch_deck/reports/01_deck-research.md
- Status updated to [RESEARCHED]
- Changes committed with session sess_1736700000_abc123
- Next: Run /plan 234 to create deck implementation plan
```

---

## Error Handling

### Input Validation Errors
Return immediately if task not found.

### Metadata File Missing
Keep status as "researching" for resume.

### User Abandonment
Return partial status with progress made.

### Git Commit Failure
Non-blocking: Log failure but continue.

Related Skills

skill-deck

438
from benbrastmckie/nvim

Generate YC-style investor pitch decks in Typst

skill-team-research

438
from benbrastmckie/nvim

Orchestrate multi-agent research with wave-based parallel execution. Spawns 2-4 teammates for diverse investigation angles and synthesizes findings.

skill-researcher

438
from benbrastmckie/nvim

Conduct general research using web search, documentation, and codebase exploration. Invoke for general research tasks.

skill-z3-research

438
from benbrastmckie/nvim

Research Z3/SMT tasks. Invoke for Z3-language research.

skill-web-research

438
from benbrastmckie/nvim

Conduct web development research using framework docs and codebase exploration. Invoke for web research tasks.

skill-typst-research

438
from benbrastmckie/nvim

Research Typst documentation tasks. Invoke for Typst-language research.

skill-python-research

438
from benbrastmckie/nvim

Research Python development tasks. Invoke for Python-language research.

skill-neovim-research

438
from benbrastmckie/nvim

Conduct Neovim configuration research using plugin docs and codebase exploration. Invoke for neovim research tasks.

skill-nix-research

438
from benbrastmckie/nvim

Conduct Nix/NixOS/Home Manager research using MCP-NixOS, web docs, and codebase exploration. Invoke for nix research tasks.

skill-lean-research

438
from benbrastmckie/nvim

Research Lean 4 and Mathlib for theorem proving tasks. Invoke for Lean-language research using LeanSearch, Loogle, and lean-lsp tools.

skill-latex-research

438
from benbrastmckie/nvim

Research LaTeX documentation tasks. Invoke for LaTeX-language research.

skill-deck-plan

438
from benbrastmckie/nvim

Pitch deck planning with interactive template, content, and ordering selection