Agent-Engineer-Master/skill-engineer / strategy/industry-analysis/analyze-trajectory
analyze-trajectory
UnverifiedProduces 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).
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 10.6 KB |
| assets/trajectory-template.md | markdown | 4.1 KB |
| evals/evals.json | config | 4.9 KB |
| references/discontinuities-catalog.md | markdown | 3.6 KB |
| references/edge-cases.md | markdown | 3.0 KB |
| references/learnings.md | markdown | 2.3 KB |
| references/power-progression.md | markdown | 3.7 KB |
| references/s-curve-methodology.md | markdown | 5.2 KB |
| references/scenario-methodology.md | markdown | 4.6 KB |
| references/three-horizons.md | markdown | 2.8 KB |
| scripts/validate_trajectory.pyexecutable | script | 12.6 KB |
references/learnings.md
View on GitHub# Learnings — analyze-trajectory
Behavioral feedback accumulated during real use. Update after every run. Distinct from `edge-cases.md` which holds factual exceptions.
## What Has Worked
- Forcing dual S-curve assessment (market AND tech) consistently surfaces the desynchronization that single-curve analyses miss. The desynchronization is usually where the trajectory thesis lives.
- Power Progression as a named lookup table (open-now / Year 3 / Year 5+ / closed) reads better than prose. Hand-off to `assess-moat-sources` is cleaner.
- Year-range timing windows (e.g., "2026-2028 likely") + named leading indicators stop the "AI will disrupt soon" anti-pattern.
## What Has Failed
- (To be populated after first real-world runs.)
- Predicted: drafters classifying all sub-segments as H1. Validator catches universal-H1.
- Predicted: drafters writing single S-curve assessment then asserting the other is "same stage." Validator now requires both stages named distinctly.
- Predicted: drafters skipping Power Progression because it feels like overlap with assess-moat-sources. Distinction: this skill establishes the MENU of available Powers (what windows are open); assess-moat-sources SELECTS from the menu for a specific firm.
## Patterns and Preferences
- Antony's preference: every load-bearing claim carries a V/C/A/I tag. Trajectory claims about year-ranges should be `[C]` or `[I]` with the inference basis named.
- Senior bar expectation: the trajectory analysis must produce ONE actionable insight (the binding constraint or the highest-leverage swing variable), not a balanced encyclopedia.
- Preferred output length: 2-3 pages of dense analysis. Three Horizons table + Power Progression table + scenario table do most of the visual work.
## Open Questions
- For very young industries (<3yr old), is the S-curve assessment meaningful or premature? Currently: classify Introduction and note "stage classification has wide error bars."
- Should base/bear/bull scenarios include numerical TAM under each scenario, or qualitative outcomes? Currently: quantified when size-market output present, qualitative when standalone.
- For declining industries, does Three Horizons collapse (everything H1)? Currently: yes, and we surface it explicitly with "declining-stage Powers only" note.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| 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: 471k | Updated | Claude CodeCodex | Verified | Install |
| 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: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| 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 available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |