feat: add sales-page-persona-simulator skill

[robnetinf]

Summary

• Adds skills/sales-page-persona-simulator, an independent, manually-triggered skill that simulates buyer personas reading a built sales page (Phase 7 output) to predict objections, drop-off points, and conversion likelihood before it ships.
• Every objection/fix the skill reports traces to design-intelligence/theory/conversion-psychology.md (Cialdini's principles, anchoring, loss aversion, etc.) and design-intelligence/references/patterns/objection-handling.md (FAQ, objection cards, comparison table, guarantee, risk-reversal banner) — no unsourced AI guessing.
• Complements sales-page-qa (mechanical checks) rather than overlapping it; never writes to pipeline state.json and isn't a pipeline phase — purely advisory.
• Adds /grow simulate [slug] shortcut in commands/grow/COMMAND.md (keyword bypass + full subcommand docs) and registers the skill in plugin.json.

Test plan

• Verified /grow simulate with zero existing output/sales-pages/ projects falls through to the correct usage/fallback message.
• Built a sample sales page (focusflow, a fictitious product) intentionally missing a guarantee, FAQ, price anchoring, and specific social proof, with no matching voice/offers/*.md file, to exercise the Default Persona Library fallback path.
• Ran the skill's simulation logic against it end-to-end: 4 personas evaluated, each objection/fix grounded in the two reference docs.
• Generated the HTML report, validated it parses cleanly with no leftover placeholders, and rendered it in headless Chromium to confirm the dark-theme styling matches the existing Sales Page Studio preview server.
• Removed the test fixture from output/sales-pages/ before committing (test-only content, gitignore pattern for output/sales-pages/** intentionally not added since this directory holds real user projects).

🤖 Generated with Claude Code

[ecc-tools]

Analyzing 200 commits...

[ecc-tools]

Analysis Complete

Generated ECC bundle from 1 commits | Confidence: 50%

View Pull Request #2

Repository Profile

Attribute	Value
Language	TypeScript
Framework	Not detected
Commit Convention	conventional
Test Directory	separate

Changed Files (3)

Metric	Value
Files changed	3
Additions	169
Deletions	2

Top hotspots

Path	Status	+/-
skills/sales-page-persona-simulator/SKILL.md	added	+132 / -0
commands/grow/COMMAND.md	modified	+34 / -0
plugin.json	modified	+3 / -2

Top directories

Directory	Files	Total changes
skills/sales-page-persona-simulator	1	132
commands/grow	1	34
.	1	5

Analysis Depth Readiness (commit-history, 7%)

ECC Tools uses this to decide whether recommendations should stay at commit-history/setup guidance or expand into CI, security, harness, reference-set, AI-routing, and team backlog work.

Area	Status	Evidence / Next Step
Commit history	Partial	1 commits sampled
CI/CD signals	Missing	Add workflow files or CI troubleshooting evidence so ECC Tools can reason about pipeline setup.
Security evidence	Missing	Add AgentShield, audit, SARIF, SBOM, or security review evidence so recommendations can cover security posture.
Harness configuration	Missing	Add Claude, Codex, OpenCode, Zed, dmux, MCP, plugin, or cross-harness config evidence for harness-agnostic recommendations.
Reference/eval evidence	Missing	Add fixtures, golden traces, reference sets, or evaluator benchmarks so deeper recommendations have regression evidence.
AI routing and cost controls	Missing	Add model-routing, budget, usage, or cost-control files before relying on AI-heavy automation recommendations.
Team handoff and project tracking	Missing	Add roadmap, runbook, project, Linear, or follow-up tracking docs so generated work can land in a team queue.

Reference Set Readiness (0/7, 0%)

Area	Status	Evidence / Next Step
Deep analyzer corpus	Missing	Add analyzer fixture, golden, benchmark, or reference-set files that can catch analyzer regressions.
RAG/evaluator comparison	Missing	Add retrieval or evaluator reference-set comparison fixtures with expected ranking behavior.
PR salvage/review corpus	Missing	Add stale-PR, review-thread, reopen-flow, or salvage reference cases for queue cleanup automation.
Discussion triage corpus	Missing	Add public discussion triage fixtures, golden cases, or reference sets for informational, answered, and no-response classifications.
Harness compatibility	Missing	Add cross-harness, adapter-compliance, or harness-audit evidence for Claude, Codex, OpenCode, Zed, dmux, and agent surfaces.
Security evidence	Missing	Attach security evidence such as SBOMs, SARIF, audit reports, or AgentShield evidence packs.
CI failure-mode evidence	Missing	Add captured CI failure logs, dry-run fixtures, or troubleshooting docs for common workflow failure modes.

Likely Future Issues (4)

Severity	Signal	Why it may show up
MEDIUM	CLI changes may ship without shell or end-to-end coverage	1 CLI surface paths changed; 0 CLI-focused integration or e2e tests changed
MEDIUM	AI or harness analysis changes may ship without reference-set validation	2 reference-sensitive path(s) changed; 0 eval, golden trace, benchmark, or reference-set artifacts changed
MEDIUM	Harness config changes may ship without compatibility evidence	1 harness config paths changed; 0 harness compatibility evidence artifacts changed
MEDIUM	Skill or agent guidance may ship without quality evidence	2 skill-quality path(s) changed; 0 examples, validator, eval, or reference artifacts changed

• CLI changes may ship without shell or end-to-end coverage: The PR changes CLI, bin, or command-entry files without touching any obvious CLI-focused integration or end-to-end tests.
• AI or harness analysis changes may ship without reference-set validation: The PR changes analyzer, skill, agent, command, or harness guidance without updating any obvious eval, golden trace, benchmark, or reference-set artifact.
• Harness config changes may ship without compatibility evidence: The PR changes harness, MCP, plugin, or agent configuration without touching harness audit, adapter matrix, cross-harness docs, or compatibility regression evidence.
• Skill or agent guidance may ship without quality evidence: The PR changes skill, agent, command, or rule guidance without touching examples, validator, eval, or reference evidence.

Suggested Follow-up Work (4)

Type	Suggested title	Targets
PR	test: add CLI coverage for commands/grow/COMMAND.md	commands/grow/COMMAND.md
PR	analysis: add reference-set evidence for commands/grow/COMMAND.md + skills/sales-page-persona-simulator/SKILL.md	commands/grow/COMMAND.md, skills/sales-page-persona-simulator/SKILL.md
PR	harness: add config quality evidence for commands/grow/COMMAND.md	commands/grow/COMMAND.md
PR	skills: add quality evidence for commands/grow/COMMAND.md + skills/sales-page-persona-simulator/SKILL.md	commands/grow/COMMAND.md, skills/sales-page-persona-simulator/SKILL.md

• test: add CLI coverage for commands/grow/COMMAND.md: Backfill CLI coverage before another command-surface change lands on the touched paths.
• analysis: add reference-set evidence for commands/grow/COMMAND.md + skills/sales-page-persona-simulator/SKILL.md: Backfill eval, golden trace, benchmark, or reference-set evidence before another AI or harness-analysis change lands on the touched surface.
• harness: add config quality evidence for commands/grow/COMMAND.md: Backfill harness audit, adapter matrix, or cross-harness compatibility evidence before another config change lands on the touched surface.
• skills: add quality evidence for commands/grow/COMMAND.md + skills/sales-page-persona-simulator/SKILL.md: Backfill examples, validator, eval, or reference evidence before another skill or agent guidance change lands on the touched surface.

Copy-ready bodies

test: add CLI coverage for commands/grow/COMMAND.md

## Summary
- Add shell, CLI, or end-to-end coverage for the recently changed command surface.

## Why
- Backfill CLI coverage before another command-surface change lands on the touched paths.

## Touched paths
- `commands/grow/COMMAND.md`

## Validation
- Add or extend shell, CLI, or end-to-end coverage for the changed command surface.
- Exercise the user-facing command invocation and expected exit/output behavior.

analysis: add reference-set evidence for commands/grow/COMMAND.md + skills/sales-page-persona-simulator/SKILL.md

## Summary
- Add reference-set or eval evidence for the recently changed AI, analyzer, skill, agent, command, or harness guidance surface.

## Why
- Backfill eval, golden trace, benchmark, or reference-set evidence before another AI or harness-analysis change lands on the touched surface.

## Touched paths
- `commands/grow/COMMAND.md`
- `skills/sales-page-persona-simulator/SKILL.md`

## Validation
- Add or update an eval, golden trace, benchmark, fixture, or reference-set artifact for the changed AI/harness behavior.
- Compare the changed behavior against the maintained reference set and record the pass/fail evidence.
- Confirm the follow-up evidence covers the same analyzer, skill, agent, command, or harness surface touched by this PR.

harness: add config quality evidence for commands/grow/COMMAND.md

## Summary
- Add harness compatibility evidence for the recently changed config surface.

## Why
- Backfill harness audit, adapter matrix, or cross-harness compatibility evidence before another config change lands on the touched surface.

## Touched paths
- `commands/grow/COMMAND.md`

## Validation
- Run or update the harness audit, adapter compliance matrix, or cross-harness compatibility check for the changed config.
- Add or update a regression, fixture, or doc evidence path that covers the affected harness, MCP, plugin, or agent loading behavior.

skills: add quality evidence for commands/grow/COMMAND.md + skills/sales-page-persona-simulator/SKILL.md

## Summary
- Add skill-quality evidence for the recently changed skill, agent, command, or rule guidance.

## Why
- Backfill examples, validator, eval, or reference evidence before another skill or agent guidance change lands on the touched surface.

## Touched paths
- `commands/grow/COMMAND.md`
- `skills/sales-page-persona-simulator/SKILL.md`

## Validation
- Add or update examples, trigger coverage, frontmatter validation, or skill validator fixtures for the changed guidance.
- Run the relevant skill, agent, command, or rule validation flow and record pass/fail evidence.
- Confirm the follow-up evidence covers the same guidance surface touched by this PR.

Generated Instincts (17)

Domain	Count
git	4
code-style	9
testing	2
architecture	2

After merging, import with:

/instinct-import .claude/homunculus/instincts/inherited/growthOS-instincts.yaml

Files

• .claude/ecc-tools.json
• .claude/skills/growthOS/SKILL.md
• .agents/skills/growthOS/SKILL.md
• .agents/skills/growthOS/agents/openai.yaml
• .claude/identity.json
• .codex/config.toml
• .codex/AGENTS.md
• .codex/agents/explorer.toml
• .codex/agents/reviewer.toml
• .codex/agents/docs-researcher.toml
• .claude/homunculus/instincts/inherited/growthOS-instincts.yaml

---

_{ECC Tools | Everything Claude Code}