Interactive Field Guide Skill

What this skill produces

The default output is a self-contained HTML file (~110KB) with sidebar nav, full-text ⌘K search, click-to-expand drawers, a clickable SVG ecosystem map, a 2×2 strategic positioning matrix, and structured analysis across up to 22 parts.

Alternative output: a concise markdown research brief (when the user explicitly requests "brief", "markdown summary", or chooses brief at the end of Discovery mode).

Quality bar: Every fact must have a [Source: X] citation. Every judgment must be falsifiable. Every report must include explicit counter-consensus framing. Matches Net Interest, Stratechery, and CB Insights research standards.

Operating principle: this skill is a suite, not a single tool. It supports 6 operational modes and 7 analytical personas. Always resolve mode + persona + output format BEFORE generating.

Outputs are designed for sharing. Treat every artifact as something the user might forward to a colleague, post publicly, or use in a stakeholder presentation. They must be free of any conversation-participant's personal context (see Critical Rule 7).

Step 0 — Resolve operation parameters

Before doing anything, classify the user's request along three dimensions.

0a. Detect mode (what kind of operation)

0b. Detect persona (analytical lens)

0c. Detect output format

Default: HTML field guide (interactive, 110KB).

Override to markdown research brief when:

• User explicitly says "brief", "markdown summary", "just the research foundation", "no HTML"
• User chose "brief only" at the end of Discovery dialogue
• Critique mode (always markdown; HTML doesn't apply)

0d. Decide: proceed immediately, or ask first?

Proceed immediately and announce when:

• Mode is clearly stated or strongly implied
• Persona is the topic-type default (Tier 2 for stocks, Industry Strategist for sectors)
• Output format is HTML (default)
• Topic is concrete (specific company, industry, ecosystem)

In this case, briefly tell the user: "Got it — running [mode] on [topic] with [persona] lens, output as [format]. Proceeding." Then execute. The user can interrupt if you've misread their intent.

Ask one concise clarifying question and WAIT for response when:

• Mode is ambiguous between Generate and Discovery
• User said "compare" but only named one entity
• User said "refresh" but didn't provide the prior report
• User said "drill into [vague subsection]" with no parent guide referenced
• Persona is unusual for the topic type (e.g. CEO persona on a public company they don't run)

Phrase the question as a single short ask: "To make sure I read this right — [specific clarifying question]?" Wait for the user's reply before proceeding.

Do not invent a function call name (e.g. avoid "AskUserQuestion()"). Just ask in plain text.

Step 1 — Load mode workflow

Read references/modes.md and find the section for the resolved mode. Each mode has its own multi-step workflow with specific dialogue patterns, output format, and validation rules.

Step 2 — Load persona lens

Read references/personas.md and find the section for the resolved persona. Each persona defines:

• Obsessive questions the analysis must answer
• Prioritized source tiers
• Topical emphasis (which themes to expand vs compress)
• Tone and rhetorical framing

Note: personas describe the LENS, not specific section numbers. Map the persona's emphasis topics onto whatever 22-part structure is current in references/structure.md.

Step 3 — Load shared references

For modes producing HTML output (Generate / Refresh / Compare / Drill-down), load:

• references/structure.md — 22-part menu with skip rules by topic type
• references/content-strategy.md — sourcing standards (Tier 1-3), counter-consensus framework, falsifiability rules
• references/data-schemas.md — JS object schemas + component HTML patterns
• references/pitfalls.md — known pitfalls + 9-check validation script (includes Template Wiring, Personalization Leakage, Accordion Double-binding)

For modes producing markdown output (Critique, Discovery brief-only), load only:

• references/content-strategy.md
• references/pitfalls.md

Step 4 — Execute workflow

Follow the mode's workflow step by step. Apply the persona's lens at each judgment point. Use assets/template.html as the rendering base for HTML outputs — surgically replace pre-populated content; do NOT rebuild from scratch (see Critical Rule 6 below).

Step 5 — Validate

For HTML outputs: run the 11-check validation script from references/pitfalls.md. Iterate up to 3 times to fix issues. Only deliver after passing all 11 checks.

Mandatory visibility: output the 11-check results as a visible code block in the response to the user, in the form:

=== 11-check validation results ===
1. Template instruction strip: ✓
2. Placeholder strip: ✓
...
11. Reverse grep (HTML→JS): ✓
=== Result: 11/11 passed, OK to deliver ===

The visibility requirement (Rule 10a) prevents silent skipping — if the validation block is missing from the response, the user knows something was bypassed.

The 11 checks cover:

1. Template instruction strip
2. Placeholder strip
3. JS validity (static syntax)
4. ID consistency (CN_NODES / data-id / DETAIL_DATA)
5. Constellation count
6. Sidebar consistency
7. Template wiring integrity (added v3.0.1)
8. Personalization leakage (added v3.0.2)
9. Accordion event handler integrity (added v3.0.2)
   • 9b. JS ↔ HTML ID matching (added v3.1.1): zero orphan IDs
10. Runtime execution sanity (added v3.1.1): use node vm sandbox to catch TypeError / ReferenceError / infinite loops at script init
11. Reverse grep — HTML→JS (added v3.1.1): when removing HTML elements, verify no remaining JS reference to that ID/class

Plus Rule 10 production contract: ≥15 Parts, 5 hard-floor interactions working, TOC visible (sidebar + top-nav + progress-bar), continuous Roman numerals, Part Coverage Audit present.

For markdown outputs (Critique, brief): self-review against content-strategy.md standards — every claim sourced, every judgment falsifiable, counter-consensus angle present. Also run personalization leakage check (#8).

Step 6 — Deliver (cross-platform)

Detect the runtime environment and write the output appropriately:

Filename convention:

• Generate / Discovery / Drill-down: <topic-slug>-field-guide.html (or .md for brief)
• Refresh: <topic-slug>-field-guide-refresh-<YYYY-MM-DD>.html
• Compare: <topic-A>-vs-<topic-B>-comparison.html
• Critique: <topic-slug>-critique.md

Filename must NOT contain personal names (no `klay-bytedanc