Skip to content

Agent-Engineer-Master/skill-engineer / strategy/industry-analysis/map-five-forces

map-five-forces

Unverified

Produces a Porter Five Forces analysis extended with complementors (sixth force, Brandenburger/Nalebuff) and AI-as-named-force (cost-structure impact + new-entry vector + data-intermediary position) for a defined industry. Output: five-forces.md naming THE governing force that determines this industry's profit distribution in one causal sentence, plus per-force intensity assessment with V/C/A/I-tagged evidence and explicit profit-pool cross-reference. Sub-skill of analyze-industry but invocable standalone. Triggers on 'five forces analysis for [industry]', 'Porter analysis for [industry]', 'industry-structure analysis for [industry]', 'is [industry] structurally attractive'. Do NOT activate for single-company competitive positioning (use map-competitive-arena or build-company-model), market sizing (use size-market), or moat assessment of a specific company (use assess-moat-sources).

FileKindSize
SKILL.mdskill md11.5 KB
assets/heatmap-template.mdmarkdown2.6 KB
evals/evals.jsonconfig5.1 KB
references/ai-as-force.mdmarkdown7.0 KB
references/complementors.mdmarkdown2.4 KB
references/dynamism.mdmarkdown3.8 KB
references/edge-cases.mdmarkdown2.9 KB
references/forces-rubric.mdmarkdown10.5 KB
references/learnings.mdmarkdown2.3 KB
references/platform-extensions.mdmarkdown4.8 KB
scripts/validate_forces.pyexecutablescript8.9 KB

references/learnings.md

View on GitHub
# Learnings — map-five-forces

Behavioral feedback accumulated during real use. Update after every run via the closing feedback gate. Distinct from `edge-cases.md` which holds factual exceptions.

## What Has Worked

- Per-force "structural reason" sentence (one causal sentence after intensity) consistently produces better assessments than intensity ratings alone. Without it, drafts collapse into checklist mode.
- Requiring the governing-force sentence as a hard validator check (not just a guideline) catches universal-Moderate failure mode at ship time, not at Gate 2.
- Disaggregating supplier power by input category (specialty vs commodity) per `forces-rubric.md` consistently surfaces the structural insight that "supplier power overall is Moderate" hides.

## What Has Failed

- (To be populated after first real-world runs.)
- Predicted: drafters skipping the direction-of-travel arrow on forces they consider "obvious." Validator now catches missing arrows on all 7 force lines.
- Predicted: drafters writing the AI-as-force section but omitting the reshape-matrix table. Validator now catches missing reshape matrix.

## Patterns and Preferences

- Antony's preference (inherited from `build-company-model` work): every load-bearing claim carries a V/C/A/I tag; the lead is the analytical insight, not the data dump.
- Senior bar expectation: at least 3 non-obvious observations across the 7 forces. If the brief contains only obvious observations (e.g., "rivalry is high because there are many competitors"), it fails the bar test even if structurally complete.
- Preferred output length: ~2-3 pages of dense analysis, not 8 pages of structured emptiness. Force the analyst to choose what matters.

## Open Questions

- Should the AI-reshape matrix appear inline within each force section, or as a single consolidated matrix at the end? Currently consolidated; may revise based on reader feedback.
- Should the heatmap be required (validator-enforced) or optional? Currently asset-only — added by convention, not validator. Promote to required after at least 3 real runs.
- For non-platform industries, is the boundary note required or skipped? Currently: required for platform industries (detected via test in `platform-extensions.md`), skipped otherwise. Verify this routing in practice.
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