IC Simulation Skill

Help startup founders prepare for the conversation that happens behind closed doors — the one where VC partners debate whether to invest. Produce a realistic IC simulation with three distinct partner perspectives, scored across 28 dimensions, with specific coaching on what to prepare. The tone is founder-first: a coaching tool for preparation, not a judgment.

Input Formats

Accept any combination: pitch deck, financial model, data room contents, text descriptions, prior market-sizing or deck-review artifacts, or just a verbal description of the business.

Available Scripts

All scripts are at

${CLAUDE_PLUGIN_ROOT}/skills/ic-sim/scripts/

• fund_profile.py

  — Validates fund profile structure (archetypes, check size, thesis, portfolio)

• detect_conflicts.py

  — Validates conflict assessments and computes summary stats

• score_dimensions.py

  — Scores 28 dimensions across 7 categories with conviction-based scoring

• compose_report.py

  — Assembles report with cross-artifact validation;

  --strict

  exits 1 on high/medium warnings

• visualize.py

  — Generates self-contained HTML with SVG charts (not JSON)

Run with:

python3 ${CLAUDE_PLUGIN_ROOT}/skills/ic-sim/scripts/<script>.py --pretty [args]

Available References

Read each when first needed — do NOT load all upfront. At

${CLAUDE_PLUGIN_ROOT}/skills/ic-sim/references/

• partner-archetypes.md

  — Read before Step 3. Three canonical archetypes with focus areas, debate styles, red flags

• evaluation-criteria.md

  — Read before Step 5. 28 dimensions across 7 categories with stage-calibrated thresholds

• ic-dynamics.md

  — Read before Step 5d. How real VC ICs work: formats, decisions, what kills deals

• artifact-schemas.md

  — Consult as needed when depositing agent-written artifacts

Artifact Pipeline

Every simulation deposits structured JSON artifacts into a working directory. The final step assembles all artifacts into a report and validates consistency. This is not optional.

startup_profile.json

prior_artifacts.json

fund_profile.json

fund_profile.py

conflict_check.json

detect_conflicts.py

partner_assessment_{role}.json

discussion.json

score_dimensions.json

score_dimensions.py

compose_report.py

Rules:

• Deposit each artifact before proceeding to the next step
• For agent-written artifacts, consult

  references/artifact-schemas.md

  for the JSON schema
• If a step is not applicable, deposit a stub:

  {"skipped": true, "reason": "..."}

• Do NOT use

  isolation: "worktree"

  for sub-agents — files written in a worktree won't appear in the main

  $SIM_DIR

Keep the founder informed with brief, plain-language updates at each step. Never mention file names, scripts, or JSON. After each analytical step (4–6), share a one-sentence finding before moving on.

Workflow

Path Setup

SCRIPTS="$CLAUDE_PLUGIN_ROOT/skills/ic-sim/scripts"
REFS="$CLAUDE_PLUGIN_ROOT/skills/ic-sim/references"
if ls "$(pwd)"/mnt/*/ >/dev/null 2>&1; then
  ARTIFACTS_ROOT="$(ls -d "$(pwd)"/mnt/*/ | head -1)artifacts"
elif ls "$(pwd)"/sessions/*/mnt/*/ >/dev/null 2>&1; then
  ARTIFACTS_ROOT="$(ls -d "$(pwd)"/sessions/*/mnt/*/ | head -1)artifacts"
else
  ARTIFACTS_ROOT="$(pwd)/artifacts"
fi

If

CLAUDE_PLUGIN_ROOT

Glob

**/founder-skills/skills/ic-sim/scripts/score_dimensions.py

SCRIPTS

REFS

If

ARTIFACTS_ROOT

$(pwd)/artifacts

artifacts/

$(pwd)

Glob

**/artifacts/founder_context.json

ARTIFACTS_ROOT

mkdir -p "$ARTIFACTS_ROOT"

SIM_DIR="$ARTIFACTS_ROOT/ic-sim-{company-slug}"
mkdir -p "$SIM_DIR"

Mode Selection

Ask the user (or infer from context):

1. Interactive — Pause between partner positions for founder input
2. Auto-pilot — Run all sections without pausing
3. Fund-specific — Research a real fund first. Combines with either mode.

Steps 1-2: Extract Startup Profile and Import Prior Artifacts

When files are provided, spawn a

general-purpose

startup_profile.json

prior_artifacts.json

$SIM_DIR

If missing fields are flagged, ask the user and patch the artifact. When only text is provided, extract directly without a sub-agent.

Graceful degradation: If Task tool is unavailable, extract directly.

Step 3: Build Fund Profile ->

fund_profile.json

REQUIRED — read

$REFS/partner-archetypes.md

Generic mode: Build a standard early-stage fund profile with the three canonical archetypes.

Fund-specific mode: Use WebSearch to research fund thesis, portfolio, partner backgrounds, check size range, and stage preference. Map real partners to archetype roles.

Validation constraints:

check_size_range

stage_focus

url

title

cat <<'FUND_EOF' | python3 "$SCRIPTS/fund_profile.py" --pretty -o "$SIM_DIR/fund_profile.json"
{...fund profile JSON...}
FUND_EOF

Accepted warnings: Add

accepted_warnings

code

match

reason

"acknowledged"

Step 4: Check Portfolio Conflicts ->

conflict_check.json

Review the fund's portfolio against the startup. Assess each company for: direct conflict, adjacent conflict, or customer overlap. Use consistent names between portfolio and conflicts. Duplicates are auto-deduplicated by (company, type) pair.

cat <<'CONFLICT_EOF' | python3 "$SCRIPTS/detect_conflicts.py" --pretty -o "$SIM_DIR/conflict_check.json"
{"portfolio_size": 15, "conflicts": [...]}
CONFLICT_EOF

Step 5: Partner Assessments and Discussion

Step 5a-5c: Parallel Sub-Agent Assessments

REQUIRED — read

$REFS/evaluation-criteria.md

Spawn 3

general-purpose

isolation: "worktree"

partner_assessment_{role}.json

Graceful degradation: If Task tool unavailable, generate sequentially with strict persona separation. Set

assessment_mode: "sequential"

"assessment_mode_intentional": true

Step 5d: Orchestrate Discussion ->

discussion.json

REQUIRED — read

$REFS/ic-dynamics.md

Read all 3 assessments. Generate debate: each partner presents, partners respond to each other, build toward consensus. In interactive mode, pause between positions.

Verdict reconciliation: Ensure each partner's verdict reflects their final position after debate, not their opening position. The compose report flags

UNANIMOUS_VERDICT_MISMATCH

Discussion-to-Score reconciliation: Before scoring, re-read discussion conclusions. If a dimension was debated as a dealbreaker, ensure the score reflects that severity. Compose flags

CONSENSUS_SCORE_MISMATCH

Step 6: Score Dimensions ->

score_dimensions.json

cat <<'SCORE_EOF' | python3 "$SCRIPTS/score_dimensions.py" --pretty -o "$SIM_DIR/score_dimensions.json"
{
  "items": [
    {"id": "team_founder_market_fit", "category": "Team", "status": "strong_conviction", "evidence": "...", "notes": "..."},
    ...all 28 items...
  ]
}
SCORE_EOF

Step 7: Compose and Validate Report

python3 "$SCRIPTS/compose_report.py" --dir "$SIM_DIR" --pretty -o "$SIM_DIR/report.json"

Fix high-severity warnings and re-run. Use

--strict

Primary deliverable: Read

report_markdown

$SIM_DIR/report.md

Step 8 (Optional): Generate Visual Report

python3 "$SCRIPTS/visualize.py" --dir "$SIM_DIR" -o "$SIM_DIR/report.html"

Present the HTML file path to the user so they can open the visual report.

Step 9: Deliver Artifacts

Copy final deliverables to workspace root:

{Company}_IC_Simulation.md

.html

.json

Scoring

• 28 dimensions, each:

  strong_conviction

  /

  moderate_conviction

  /

  concern

  /

  dealbreaker

  /

  not_applicable

• Conviction score:

  (strong*1.0 + moderate*0.5) / applicable * 100

• Verdicts:

  invest

  (>=75%),

  more_diligence

  (>=50%),

  pass

  (<50%),

  hard_pass

  (any dealbreaker)
• One dealbreaker forces

  hard_pass

  regardless of score

Cross-Agent Integration

This skill imports artifacts from prior market-sizing and deck-review analyses. Imported artifacts are recorded with dates. Imports older than 7 days are flagged as

STALE_IMPORT