Skip to content

Agent-Engineer-Master/skill-engineer / strategy/industry-analysis/analyze-trajectory

analyze-trajectory

Unverified

Produces a forward-looking industry trajectory analysis: dual S-curve (market-adoption + technology lifecycle with diagnostic signals), Three Horizons overlay on G3 sub-segments (consumes size-market when present), discontinuities catalog (regulatory/tech/behavioral with year-range timing windows), Helmer Power Progression (which 7 Powers are buildable now / Year 3 / Year 5 / closed), and base/bear/bull scenarios with ≥3 named swing variables for the 5-year horizon. Output: trajectory.md with V/C/A/I tags. Sub-skill of analyze-industry but invocable standalone. Triggers on 'industry trajectory for [industry]', 'where is [industry] on the S-curve', 'three horizons for [industry]', 'scenario analysis for [industry]', 'discontinuities facing [industry]'. Do NOT activate for company-specific moat assessment (use assess-moat-sources), market sizing (use size-market), or competitive arena mapping (use map-competitive-arena).

references/edge-cases.md

View on GitHub
# Edge Cases — analyze-trajectory

Factual exceptions and special-handling protocols. Distinct from `learnings.md` (behavioral feedback).

## Very young industries (<3 years old)
- S-curve assessment is high-error. Default classification: Introduction with explicit note "stage classification has wide error bars; tech S-curve may matter more than market S-curve."
- Three Horizons collapses: there may be no H1 (everything is H2/H3). State this and recommend the analysis be re-run after the dominant design locks in.
- Power Progression: Counter-Positioning and Cornered Resource windows are wide open; Branding and Process Power not yet buildable.

## Declining industries
- Three Horizons partially collapses: H3 may be absent. State explicitly. Don't invent H3 sub-segments to fill the table.
- Power Progression: only defensive Powers remain (Scale defense, Process Power defense, Branding defense). Counter-Positioning and Network Economies windows are CLOSED.
- Scenarios: bull case is "decline arrested" not "growth resumed." Be honest.

## Platform / ecosystem industries
- Dual S-curve applied to both sides of the platform (e.g., for mobile gaming: market = consumer adoption; tech = device + content tooling).
- Three Horizons applied at the keystone level — sub-segments are use cases, not just product variants.
- Discontinuities often regulatory (app store fee rulings, antitrust) — scan that type deliberately.

## Heavily regulated industries (healthcare, finance, defense)
- Regulatory discontinuities dominate the catalog. Tech and behavioral still scanned but typically smaller mover.
- Timing windows often anchored to legislative or rulemaking calendars (e.g., "FDA Q4 2027 final rule").
- Power Progression: Cornered Resource (license) often dominates and is the binding constraint for new entrants.

## Multi-layer industries (e.g., semiconductors)
- Trajectory may differ per layer. Default: run trajectory at the SAME focal layer as the upstream Five Forces analysis (if present). Document the layer in the output header.
- S-curve at fabless vs OEM vs equipment will desynchronize; pick one.

## When size-market output is absent (standalone mode)
- Ask user for ≥3 named sub-segments at intake.
- If user can only name 1-2, run the analysis on the aggregate but flag in output: "Three Horizons applied at aggregate level due to insufficient G3 decomposition; recommend running size-market for finer overlay."

## When the industry slug spans multiple genuinely-different markets
- Reject. Three Horizons + scenarios cannot meaningfully be applied to "the AI industry" (too broad) or "the technology sector" (multi-industry). Narrow the slug and re-run.

## Hyper-cycle / sentiment-driven markets (e.g., crypto sub-segments)
- S-curve assessment is unreliable; sentiment cycles overlay underlying lifecycle. Default: classify the underlying technology S-curve only, note that market S-curve is sentiment-dominated, scenarios driven primarily by sentiment / regulatory swing variables.
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall