competitive-analysis

---
name: competitive-analysis
description: Orchestrator — select competitive-analysis frameworks, run them inline one per session, and synthesize market landscape findings
type: research
version: v0.29
required_conventions: [alignment-page, interrogation-page]
argument-hint: "[optional: \"--synthesize\" | \"core\" | concept/category/competitors]"
invocation: orchestrator
context_intake: scoped
visual_tier: visual
---

## Pack Availability Guard

Before telling the user to run a skill from another project-local pack, check `.agents/project.json.enabled_packs`. If the target pack is not enabled, recommend `npx skillpacks install <pack>` from the project shell, instead of the target skill. After install, tell Codex users to start a fresh Codex CLI session if the `$` skill list remains stale. Only the currently running skill and skills verified available in the active session or project-local install state are directly recommendable. For unavailable pack skills, recommend `npx skillpacks install <pack-or-skill>`; for unavailable base skills, recommend `npx skillpacks init` before the skill.

# Competitive Analysis — Orchestrator

Invoke as `$competitive-analysis`.

This is a **Pattern A framework-decomposition orchestrator** that runs as a self-advancing **Research Session Loop** (see `docs/research-session-loop-convention.md` and the Execution Model below). It resolves product/research scope, recommends competitive-analysis frameworks, runs each selected framework inline one per session, and synthesizes the approved framework outputs into the canonical competitive landscape report. Individual frameworks live as child skills under `frameworks/`.

Available frameworks:

| Framework | Slug | Lens | Default |
|-----------|------|------|---------|
| Porter's Five Forces | `porter-five-forces` | Industry structure, power dynamics, substitutes, entrants, rivalry | Yes |
| SWOT | `swot` | Strengths, weaknesses, opportunities, threats against market evidence | Yes |
| Strategic Group Map | `strategic-group-map` | Competitive clusters, positioning axes, whitespace by segment | Optional |
| Feature/Pricing Matrix | `feature-pricing-matrix` | Capability, package, and price comparisons across alternatives | Yes |

## Report-First Approval Gate

Default to scope-first approval: before synthesized research, inspect only enough repository, user, and source context to propose research scope, source plan, assumptions, output paths, and approval questions in a `review` alignment page plus a concise conversation summary.

Do not perform synthesized research, rank candidates, make recommendations, or write working packets or canonical deliverables until final compiled YAML approves the research scope. Minimal pre-approval discovery may identify available files, source categories, and open questions; label it as scope evidence, not findings.

After approved research-scope YAML, perform the research and write only the non-canonical working packet defined in the staged workflow. Then update the `review` alignment page with findings and stop again for feedback-only YAML or final compiled YAML artifact approval before creating or updating canonical research, spec, or task files.

Do not include `Recommended next skill`, `Recommended next command`, or downstream routing language while a scope, framework findings, or synthesis approval is pending. The approval request itself is the next action: tell the user to review the page, compile responses, clear context, and paste the compiled YAML into a fresh session. The compiled YAML carries the parent command in `command` and `agent_routing.command`, such as `$competitive-analysis` plus the same product/research path argument when present. Parent-loop continuation is not downstream routing. Only emit downstream next-skill routing after the synthesized `competitive-analysis.md` artifact has been approved and written.

## Staged Research Workflow

Use this staged workflow for synthesized research or report outputs that would create or update canonical research, spec, or task files.

0. **Stage 0 - Interrogation.** On cold start, before framework selection, run the shared interrogation-page loop and build `interrogation/competitive-analysis-r{N}-{branch}.html`. The interrogation must surface competitor set, market boundary, evidence coverage, pricing/feature evidence availability, strategic-axis assumptions, force/SWOT assumptions, source gaps, unknowns, and framework-selection implications. Do not build the framework multi-select alignment page until approved compiled interrogation YAML has been consumed and the confidence gate is satisfied.
1. **Stage 1 - Scope discovery and approval.** Inspect only enough repository, user, and source context to propose research scope, source plan, assumptions, output paths, and approval questions. Build the `review` HTML alignment page before synthesized research. The page must render the proposed scope, available source categories, known context, assumptions/confidence, proposed working-packet and canonical output paths, and research-scope approval gates. Stop for final compiled YAML approval of the research scope. Do not perform synthesized research, rank candidates, make recommendations, or write working packets, canonical research, spec, or task files in Stage 1.
2. **Stage 2 - Research and artifact review.** Only after approved research-scope YAML with no unresolved `needs-clarification`, unresolved `down` feedback, or other unresolved negative feedback, perform the synthesized research, run required source/code checks, and write only a non-canonical working packet: flat mode uses `research/_working/preliminary-<skill>-research.md`; product-path mode uses `research/{slug}/_working/preliminary-<skill>-research.md`. Replace `<skill>` with this skill's `name` value. Raw evidence or search logs may remain as supporting evidence where this skill already requires them, but synthesized deliverables stay in the working packet. Update the `review` HTML alignment page so it renders the complete working-packet substance as structured HTML review UI: purpose-built sections, tables, matrices, gates, cards, and tier-appropriate charts or diagrams that preserve every packet section, finding, caveat, and decision detail without summary loss. Raw Markdown packet text may appear only as a supplemental source view after the rendered review UI; do not make a `Full Preliminary Packet` or `Full Working Packet` raw Markdown dump, giant `<pre><code>` block, link-only view, or source-only view the primary review surface. Include the evidence matrix, assumptions/confidence register, source coverage gaps, proposed canonical file changes, and artifact approval gates. Stop for either feedback-only YAML or final compiled YAML. Feedback-only YAML revises the working packet and page, then remains in Stage 2.
3. **Stage 3 - Finalize approved artifacts.** Consume final compiled YAML for artifact approval only when it has no unresolved `needs-clarification`, unresolved `down` feedback, or other unresolved negative feedback. Apply approved edits first, archive the working packet to `docs/history/archive/YYYY-MM-DD/HHMMSS/<original-working-path>`, remove the active working packet, write the approved canonical artifacts to the unchanged output paths below, and convert the alignment page to `confirmed` with the approval record preserved.

Canonical output paths remain unchanged. Search logs and other supporting evidence remain allowed only where this skill's output contract already requires them.

## Evidence And Feedback Handling

Treat user feedback as input to evaluate, not as automatic ground truth.

- For factual, evidentiary, technical, or source-backed claims: verify against available evidence. If the user appears to misunderstand the evidence or states something factually incorrect, push back clearly and cite the evidence. Do not rewrite findings merely to agree.
- For taste, brand, positioning preference, risk appetite, prioritization, or other subjective judgment calls: weigh user feedback heavily and adapt the recommendation unless it conflicts with verified evidence.
- When feedback mixes facts and preference, separate them explicitly: correct the factual part, then incorporate the preference where it is a legitimate judgment call.
- When uncertain, say what is known, what is inferred, and what would change the conclusion.

## Prerequisites

**Detect mode before proceeding:**

- **Concept-validation mode** activates when: no `research/icp.md` AND (no meaningful codebase OR `$ARGUMENTS` contains "concept"/"validate"). Use this mode to validate market gaps after a concept has been shaped by `$idea-scope-brief` or an equivalent brief; if no concept is clear, recommend `$idea-scope-brief` first. Announce mode to user, then ask for concept description (problem, audience, approach).
- **Standard mode** (default): Read the codebase, README, CLAUDE.md, and existing research/specs (`research/icp.md` or `research/{slug}/icp.md`, `research/enterprise-icp.md` or `research/{slug}/enterprise-icp.md`, `research/mvp-gap.md` or `research/{slug}/mvp-gap.md`) to understand the product.
- Read `research/.progress.yaml` when present. Normalize `active_path` (singular legacy) to `active_paths` (plural list) when reading; treat legacy `abandoned` as `archived` and exclude archived/deferred/revisit/promoted paths plus `research/_archive/` scopes from active target selection. In standard mode, scope the full competitive analysis to the first entry in `active_paths` by default. Treat `product_paths[]` entries with `status: deferred` or `status: revisit_candidate` as parked product paths, not as extra full research tracks.

**Provisional product-path evidence.** When a referenced product path is not present in `research/.progress.yaml` (either absent entirely or not in `active_paths` or `product_paths[]`), do not treat it as a canonical active path. Before using it as source context, require an explicit provisional-path evidence reference: a `review-only-approved` alignment page (e.g., `alignment/idea-scope-brief-{topic}.html` with `approval_status: review-only-approved`) that fully renders the proposed path's concept, brief, and manifest entry. If no such evidence exists, ask the user whether to proceed with the path as unverified context or to run `$idea-scope-brief` first.

## Execution Model — Research Session Loop

This is a **self-advancing Pattern A research orchestrator** (see `docs/research-session-loop-convention.md`). Each invocation starts cold, resolves its state from **pasted YAML + filesystem**, runs **exactly one heavy phase**, emits the next gate, and stops. The user advances the loop by starting a fresh Codex session and re-invoking `$competitive-analysis`. The user never invokes a framework subskill directly — the orchestrator follows each selected framework's subskill inline.

When a framework is pending, the only user-facing continuation route is re-invoking `$competitive-analysis` with the same product/research path argument when present, for example `$competitive-analysis research/afps-tracker`. Never tell the user to run a path-shaped child framework command; the parent resolves the pending framework from the run manifest and filesystem.


### Terminal Handoff Contract

Every terminal response for this Research Session Loop must end with `## Next Work`. While a `review` page is waiting for compiled YAML, `## Next Work` is the final section and tells the user to review the page, compile responses, clear context, and paste the compiled YAML into a fresh session. Use `## Recommended Next Command` only after approved YAML has been consumed and the approved artifact has been written or updated. Do not put any other section after the applicable final section.

### Self-Routing Continuation Payload

Every `review` alignment page this parent creates must include `agent_routing` in the bottom compiled YAML. The mapping routes a fresh agent back to this parent orchestrator; it does not authorize direct framework invocation or replace parent-owned state resolution. Use this shape, preserving the current product/research path argument when present:

```yaml
agent_routing:
  workflow: pattern-a-research-loop
  parent_skill: competitive-analysis
  command: "$competitive-analysis research/{slug}"
  product_path: research/{slug}        # omit in flat mode
  gate_owner: parent-orchestrator
  gate_type: framework-findings        # or framework-selection, shortcut-selection, synthesis
  framework_slug: <framework-slug>     # only for framework-findings gates
  framework_mode: inline-subskill      # only for framework-findings gates
  run_manifest: research/{slug}/_working/competitive-analysis-run.yaml
  next_resolution: parent-resolves-from-yaml-and-filesystem
```

For framework selection, shortcut, and synthesis gates, omit `framework_slug` and `framework_mode`; `gate_type` must name the actual gate. The `command` field must carry the parent command the user would otherwise have copied separately. The parent consumes the YAML, writes or amends the artifact, archives consumed sources, derives progress from the run manifest plus canonical-intermediate files, and decides whether to load a framework subskill inline.

For review-pending framework, selection, shortcut, or synthesis pages, `## Next Work` tells the user to review the alignment page, compile YAML, clear context, and paste the compiled YAML into a fresh session. The compiled YAML carries the parent command, including `$competitive-analysis` with the same product/research path argument when present. For post-write pending-framework states, `## Next Work` reports progress as "k of N frameworks complete" and says the next run executes the next pending framework; `## Recommended Next Command` names `$competitive-analysis`.

After every framework write, recalculate pending frameworks from the run manifest and canonical-intermediate files before writing this handoff. If no selected frameworks remain and canonical `competitive-analysis.md` is missing, `## Next Work` says the next run builds the unified synthesis review page, and `## Recommended Next Command` names `$competitive-analysis --synthesize` with the same product/research path argument when present. After approved synthesis writes canonical `competitive-analysis.md`, the final command section names only the first downstream command selected by the Next Steps decision tree.


State lives in two places only:

- **Run manifest** — `research/_working/competitive-analysis-run.yaml` (flat) or `research/{slug}/_working/competitive-analysis-run.yaml` (product-path). Records the selected framework set and each framework's intermediate path. Written when the multi-select YAML is approved. Shape:

  ```yaml
  orchestrator: competitive-analysis
  slug: skills-showcase            # omit in flat mode
  selected_frameworks:
    - slug: porter-five-forces
      intermediate: research/skills-showcase/competitive-analysis-porter-five-forces.md
    - slug: swot
      intermediate: research/skills-showcase/competitive-analysis-swot.md
  ```

- **Canonical-intermediate existence** — a selected framework is *done* when `research/competitive-analysis-{framework}.md` (or `research/{slug}/competitive-analysis-{framework}.md`) exists, *pending* otherwise. `pending = selected − existing-intermediates`. The manifest stores selection only, not per-framework status.

`research/.progress.yaml` stays coarse — its `pipeline_stage` is a pointer, not per-framework status.

### State resolution (resolve the first match; YAML first, then most-progressed A→E)

On each invocation, after Product-Path Scope Resolution (step 0), resolve state:

| State | Detected when | Heavy phase this session | Emits / stops with |
|---|---|---|---|
| **0 — pasted YAML** | a compiled alignment YAML is pasted | branch on `approval_status`: `ready-for-agent-review` → apply the approval for the gate it answers (light: write manifest and/or prior framework intermediate, archive consumed source), then fall through to the next pending state below; `not-approved` → amend the named page (refinement session) and stop | amended page, or proceeds ↓ |
| **A — done** | canonical `research/competitive-analysis.md` (or `research/{slug}/competitive-analysis.md`) exists | — | done; emit next-skill route (synthesis step) |
| **B — synthesize** | run manifest exists, all selected intermediates exist, no canonical `competitive-analysis.md` (also forced by `--synthesize`) | **synthesis** (step 4) | synthesis `review` page |
| **C — run framework** | run manifest exists, ≥1 selected framework pending | **run next pending framework inline at its research stage** (step 3) | that framework's findings `review` page |
| **G — interrogation** | no run manifest, no canonical, and no approved interrogation handoff for this scope | **stage-zero interrogation** | interrogation page and confidence gate |
| **E — build selection** | no run manifest, no canonical, and approved interrogation handoff exists | establish context from compiled interrogation YAML + mode detect → recommend frameworks → build multi-select page (steps 1–2) | multi-select `review` page |

### Re-entry Routing Guard

When a user re-invokes `$competitive-analysis`, treat existing progress as routing evidence before doing any status, audit, cleanup, or cold-start selection work:

- If a run manifest exists and at least one selected framework intermediate is missing, resolve directly to **State C** and run the first pending framework inline through this parent orchestrator.
- If no run manifest exists but legacy `tasks/todo.md` contains an approved `## Competitive Analysis Framework Execution` queue with child framework rows, treat that queue as compatibility evidence only: identify the first unchecked framework row, reconstruct the selected framework order from the queue, and run that first pending framework inline through this parent orchestrator.
- Do not rerun State E, perform a status audit, do bookkeeping-only cleanup, route to `$exec`, or tell the user to invoke path-shaped framework commands.
- Exception: if the user explicitly asks for status, re-scoping, queue cleanup, or synthesis, honor that explicit request instead of forcing State C.

**Cold entry (state G, no state F).** This orchestrator uses `context_intake: scoped` plus the shared interrogation-page convention. A cold start (nothing on disk) resolves to **state G** first. Only after an approved interrogation completion handoff does the next run resolve to **state E** for framework multi-select scope approval; the interrogation answers fold into the E-session context instead of becoming a direct research approval.

**Light vs heavy.** Recording the approved selection into the run manifest (state 0→C head), writing an already-reviewed framework intermediate, and archiving a consumed source are *light* — they fold into the head of the next heavy session. The heavy phase (one framework's research, synthesis) is the only thing isolated per session.

**Shortcuts.** `$competitive-analysis --synthesize` forces state B. `$competitive-analysis core` presets the state-E multi-select defaults to `porter-five-forces`, `swot`, and `feature-pricing-matrix` (the user may still add `strategic-group-map`); it does not skip the selection gate.

---

## Process

### 0. Product-Path Scope Resolution

Resolve research scope by product path before using code or app structure as a hint:

1. If `$ARGUMENTS` names a non-archived `research/{slug}/` directory or a product-path ID whose `scope_path` points there, use that path. Treat `{slug}` as the product/app name, not the ICP, audience, or segment label.
2. If `$ARGUMENTS` names only `research/_archive/{slug}/` or a manifest entry with `status: archived` or legacy `status: abandoned`, stop and warn that the path is archived; do not write or update scoped outputs there.
3. Read `research/.progress.yaml` when present. Normalize legacy `active_path` to `active_paths` on read and write back `active_paths` on manifest updates. Treat legacy `abandoned` as `archived`; exclude `archived`, `abandoned`, `deferred`, `revisit_candidate`, `promoted`, and any `scope_path` under `research/_archive/` from active target selection.
4. If active product paths exist in the manifest, use those paths. If multiple active paths exist, ask which one to target unless this skill explicitly supports cross-path output.
5. If no active manifest target exists, list non-archived product directories under `research/`, excluding `research/_archive/` and dot directories. Auto-select only when exactly one exists; ask when multiple exist.
6. If no product directories exist, use flat `research/` single-product mode.
7. Detect monorepo/app/package structure only as a secondary hint. Suggest creating a missing `research/{slug}/` product path when code clearly exposes an app, but do not require code or monorepo detection before using `research/{slug}/`.

When product path `{slug}` is active, read and write research under `research/{slug}/`, specs under `specs/{slug}/`, and treat top-level `research/*.md` files as flat-mode documents or cross-path summaries.

### 1. Establish Product Context

Before building the framework multi-select page, consume the approved compiled interrogation YAML. Treat it as the required stage-zero handoff for competitor set, market boundary, source coverage, pricing/feature evidence, strategic-axis assumptions, force/SWOT assumptions, and open unknowns. If no completed interrogation handoff exists for this scope, return to State G instead of selecting frameworks.

**Standard mode:** Read CLAUDE.md, README, package config, key source files. Read `research/icp.md` (or `research/{slug}/icp.md`) if it exists — the ICP defines the competitive frame. Read `research/enterprise-icp.md` (or `research/{slug}/enterprise-icp.md`) and `research/mvp-gap.md` (or `research/{slug}/mvp-gap.md`) if they exist. Summarise what the product does, who it's for, and what problem it solves.

**Concept-validation mode:** Use `research/idea-brief.md` when present, otherwise use the concept description from Prerequisites. Summarise what the concept proposes (problem, audience, approach). Confirm with the user before building the multi-select page.

Write the context summary, resolved mode, candidate competitor categories, known competitors from arguments, and source gaps to `research/_working/preliminary-competitive-analysis-research.md` (or `research/{slug}/_working/preliminary-competitive-analysis-research.md`) so framework subskills inherit the same scope.

### 2. State E — Recommend Frameworks & Build Multi-Select Page

Recommend framework defaults based on context:

- **Always default**: `porter-five-forces`, `swot`, and `feature-pricing-matrix`.
- **Default `strategic-group-map`** when the category has more than five likely competitors, multiple segments, multiple buyer types, or the user asks for landscape/positioning whitespace.
- **Concept-validation mode**: keep `porter-five-forces` and `swot` defaulted; use `feature-pricing-matrix` only when named competitors or visible pricing alternatives exist; use `strategic-group-map` when the concept competes across multiple categories.
- **`core` shortcut**: default only `porter-five-forces`, `swot`, and `feature-pricing-matrix`; still allow the user to add `strategic-group-map`.

Build the framework multi-select `review` alignment page: mode, product-path scope, context summary, selected/default frameworks, optional frameworks, which canonical sections each framework feeds, output paths, source coverage gaps, a loop explanation (the selected set is the scope-and-candidate approval gate; each selected framework is then run inline — one findings page per framework — and the run advances by re-invoking `$competitive-analysis`), and the approval gate.

This multi-select approval **is** the Stage-1 scope approval for the whole selected set, b

… Documentation preview truncated. Open the source for the complete file.