Competitive Analysis

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 /pack install <pack> instead of the target skill. Global skills are always valid. Skills from this same pack are valid because the current skill is already running from that pack.

Competitive Analysis — Orchestrator

Invoke as /competitive-analysis.

This is a Pattern A framework-decomposition orchestrator. It resolves product/research scope, recommends competitive-analysis frameworks, writes framework execution steps to tasks/todo.md, and later synthesizes approved framework outputs into the canonical competitive landscape report. Individual frameworks live as child skills under frameworks/.

Available frameworks:

Report-First Approval Gate

Default to report-only: present findings, evidence coverage, assumptions, recommended artifact path, and proposed file changes in a pre-approval alignment page plus a concise conversation summary for user approval before creating or updating canonical research, spec, or task files.

Do not write or overwrite synthesized deliverables until the user explicitly approves, unless the user invoked an explicit write/update/fix mode or clearly asked to write files upfront. Raw evidence capture may be persisted before analysis when reproducibility requires it; report those raw paths separately and still gate synthesized research/report writes.

When stopping for approval, build and attempt to open the alignment preview page first, then ask the user to review it and approve, question, or request adjustments. Do not include Recommended next skill, Recommended next command, or downstream routing language. The approval request itself is the next action. Only emit next-skill routing after the approved artifact has been written or updated.

Staged Research Workflow

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

1. Stage 1 - Research and clarify. Perform the research, run required source/code checks, and ask any needed clarification questions. 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. Do not create or update canonical research, spec, or task files in Stage 1. Raw evidence or search logs may remain as supporting evidence where this skill already requires them, but synthesized deliverables stay in the working packet.
2. Stage 2 - Review alignment. Consume the working packet and build the review HTML alignment page. The page must render the full preliminary packet, evidence matrix, assumptions/confidence register, source coverage gaps, proposed canonical file changes, and 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 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.

Conduct competitive landscape research through selected framework subskills, then synthesize the approved intermediates into a comprehensive canonical report. The orchestrator owns framework selection, task queueing, synthesis, and downstream routing; subskills own framework-specific research and must not emit next-step routing.

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 exists AND (no meaningful codebase — i.e. no README, no source files, no package config — OR $ARGUMENTS contains "concept" or "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. In this mode, announce to the user: "Running in concept-validation mode — no ICP or product detected. I'll evaluate the market gap for your concept." Then ask the user to describe the concept, the problem it addresses, and the intended audience.
• 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 what the product does, who it's for, and what value it claims to provide. This context is essential for identifying the right competitors and evaluating positioning. If no codebase or specs exist but research/icp.md is present, proceed in standard mode using the ICP as context.
• 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.

Operational Modes

Mode A: Framework Selection (default)

Activated by /competitive-analysis, /competitive-analysis [concept/category], or /competitive-analysis core.

Resolve scope, load context, choose mode, recommend frameworks, build an alignment page with selected defaults, and after approval write framework steps plus a synthesis step to tasks/todo.md. Stop after queueing the work; /exec drives each framework and the final synthesis step.

Mode B: Synthesis

Activated by /competitive-analysis --synthesize.

Read approved framework intermediates, synthesize the canonical competitive analysis and search log, present the report-first alignment page, then write canonical artifacts only after final approval YAML.

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

Standard mode:

• Read CLAUDE.md, README, package config, and key source files to understand the product
• Read research/icp.md (or research/{slug}/icp.md) if it exists — the customer profile, pain map, and value prop define 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 for additional context
• If $ARGUMENTS names specific competitors, preserve those as seeded competitors for framework subskills
• 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 to establish the problem space
• Summarise what the concept proposes (problem it addresses, intended audience, hypothesised approach)
• Confirm this understanding with the user before queueing frameworks

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. Mode A — Recommend Frameworks

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 an alignment page that includes: mode, product-path scope, context summary, selected/default frameworks, optional frameworks, execution plan, output paths, source coverage gaps, and approval gates.

After approval, overwrite or update the current execution section of tasks/todo.md with the selected framework steps and synthesis step:

## Competitive Analysis Framework Execution

- [ ] Run `/competitive-analysis/frameworks/porter-five-forces` - Porter's Five Forces industry structure
- [ ] Run `/competitive-analysis/frameworks/swot` - SWOT from competitive evidence
- [ ] Run `/competitive-analysis/frameworks/strategic-group-map` - Strategic group mapping
- [ ] Run `/competitive-analysis/frameworks/feature-pricing-matrix` - Feature and pricing comparison
- [ ] Synthesize: `/competitive-analysis --synthesize` - Combine framework outputs into research/competitive-analysis.md

Only include frameworks the user selected. Always append synthesis last. Do not emit downstream next-step routing in Mode A.

3. Framework Execution

Framework subskills read the orchestrator working packet and any existing relevant research, then produce approved intermediate artifacts:

• research/competitive-analysis-porter-five-forces.md
• research/competitive-analysis-swot.md
• research/competitive-analysis-strategic-group-map.md
• research/competitive-analysis-feature-pricing-matrix.md

In product-path mode, write under research/{slug}/. Subskills follow the staged research workflow, present before writing, and do not emit next-step routing.

4. Mode B — Synthesis (/competitive-analysis --synthesize)

Read all existing research/competitive-analysis-*.md framework outputs for the active scope. At least one approved framework output must exist; if none exist, stop and ask the user to run /competitive-analysis to queue framework research.

Synthesize across framework outputs into the canonical deliverables below:

• competitor landscape and categories
• company/product profiles
• observable GTM and pricing patterns
• market gaps and white-space opportunities
• implications for deferred product paths when evidence materially changes them
• concept-validation ## Gap Assessment when the orchestrator context selected concept-validation mode
• ## Next Steps using the unchanged routing contract below

Build the report-first alignment page before writing. Only after final compiled YAML approval, write canonical artifacts, archive the working packet, update research/.progress.yaml only when active-path evidence changed, and emit downstream next-step routing.

Standard mode next steps: ## Next Steps section with a Recommended item and Other options (2-4 alternatives). Choose the recommended item by the first matching condition:

1. IF no research/journey-map.md: check .agents/project.json.enabled_packs for customer-lifecycle - if customer-lifecycle is not enabled, recommend /pack install customer-lifecycle first; if customer-lifecycle is enabled, recommend /journey-map - map the customer and user journey before solution-value decisions, using competitive gaps as inspiration
2. IF no research/positioning.md: /positioning - frame the market category and alternatives after journey evidence shows where value is delivered
3. IF no specs/user-flow-*.md: check .agents/project.json.enabled_packs for product-design - if product-design is not enabled, recommend /pack install product-design first; if product-design is enabled, recommend /user-flow-map [top journey-backed market gap or positioning opportunity] - map flow structure before UI requirements, layout variants, and production specification
4. IF no research/value-prop.md AND solution-customer fit is weak, disputed, or needs explicit fit scoring: /value-prop-canvas - validate contested solution-fit evidence as an optional detour
5. IF no research/gtm.md: check .agents/project.json.enabled_packs for business-growth - if business-growth is not enabled, recommend /pack install business-growth first; if business-growth is enabled, recommend /gtm - build go-to-market plan leveraging competitive gaps
6. IF codebase exists and no research/mvp-gap.md: check .agents/project.json.enabled_packs for business-ops - if business-ops is not enabled, recommend /pack install business-ops first; if business-ops is enabled, recommend /mvp-gap - check if the codebase exploits the gaps found

Use this format in the output:

Next Steps

Recommended: [first matching command above] - [reason grounded in this analysis]

Other options:

• /pack install customer-lifecycle or /journey-map - map the customer journey to find where competitors fall short (if no research/journey-map.md and not recommended; check .agents/project.json.enabled_packs for customer-lifecycle - if not enabled, recommend /pack install customer-lifecycle; if enabled, recommend /journey-map)
• /positioning - frame the market category and competitive alternatives after journey evidence exists (if no research/positioning.md and not recommended)
• check .agents/project.json.enabled_packs for product-design - if product-design is not enabled, recommend /pack install product-design first; if product-design is enabled, recommend /user-flow-map [top journey-backed market gap or positioning opportunity] - map flow structure before UI requirements, layout variants, and production specification (if positioning exists and not recommended)
• /value-prop-canvas - optional detour only when solution-customer fit is weak, disputed, or needs explicit fit scoring before positioning/spec work
• check .agents/project.json.enabled_packs for business-growth - if business-growth is not enabled, recommend /pack install business-growth first; if business-growth is enabled, recommend /gtm - build go-to-market plan leveraging competitive gaps (if no research/gtm.md and not recommended)
• check .agents/project.json.enabled_packs for business-ops - if business-ops is not enabled, recommend /pack install business-ops first; if business-ops is enabled, recommend /mvp-gap - check if the codebase exploits the gaps found (if codebase exists, no research/mvp-gap.md exists, and not recommended)
• check .agents/project.json.enabled_packs for product-design - if product-design is not enabled, recommend /pack install product-design first; if product-design is enabled, recommend /brainstorm - generate alternative solution ideas (only if the analysis found multiple plausible market gaps and product direction is still unclear)

Only include items whose conditions are met. Do not recommend brainstorm just because competitive whitespace exists.

Concept-validation mode next steps: Use the same Recommended + Other options format, but choose the recommendation from the validated ## Gap Assessment verdict:

Next Steps

Recommended: [verdict-based next step] - [reason grounded in the gap assessment]

Other options:

• IF verdict is Proceed to Customer Discovery: recommend /customer-discovery - the competitive gap is validated; define who to build for
• IF verdict is Pivot concept: recommend /brainstorm - the market has a gap, but this concept needs a different angle before ICP work is useful
• IF verdict is Abandon: recommend No follow-up skill recommended - the analysis did not find a meaningful gap worth pursuing; include /brainstorm only if the user wants to explore a new concept
• /competitive-analysis - re-run in standard mode after ICP is defined (only after a proceed verdict and after /customer-discovery creates research/icp.md)

Output

research/competitive-analysis.md (or research/{slug}/competitive-analysis.md)

# Competitive Analysis

> Product: [product name and one-line description]
> Category: [market category]
> Date: [current date]
> Sources: [number of competitors analysed]

## Summary
[3-5 sentences: competitive landscape overview, our positioning, and the biggest opportunity]

## Competitive Landscape

### Direct Competitors
For each:
- **[Competitor Name]** — [one-line description]
  - Stage: [pre-launch / early / growth / mature / declining]
  - Founded: [year] | Funding: [amount or "bootstrapped"] | Team: [size estimate]
  - Pricing: [model and range]
  - GTM: [primary strategy]
  - Strengths: [2-3 bullets]
  - Weaknesses: [2-3 bullets]
  - Key takeaway: [what we can learn]

### Indirect Competitors
[Same format]

### Incumbents & DIY Alternatives
[Same format, briefer]

### Emerging Players
[Same format, briefer]

## Observable GTM Patterns
- **Dominant acquisition model**: [PLG / sales-led / community-led / etc. — as observed]
- **Pricing models seen**: [what competitors charge and how — from public pricing pages]
- **Common channels**: [where competitors are visibly present]
- **What works in this market**: [patterns from successful competitors]
- **What doesn't work**: [patterns from struggling competitors]

## Gap Assessment (concept-validation mode only)

### Market State
[Virgin / Sparse / Crowded — with evidence]

### Incumbent Quality
[Dominant-and-loved / Dominant-but-resented / Fragmented-and-mediocre / Emerging-and-unproven — with evidence]

### Gap Quality
[Clear unmet need / Underserved segment / UX/approach gap / Minor improvement / No meaningful gap — with evidence]

### Verdict
[Proceed to Customer Discovery / Pivot concept / Abandon — with reasoning]

## Market Gaps
- **[Gap title]** — [Description of the unmet need, who it affects, and why it exists]
- ...

## Competitive Positioning

### Market Gaps Identified
[Specific gaps, unserved segments, and white-space opportunities with evidence]

### Lessons from Competitors
- **Do this** (learned from [competitor]): [what they did well that we should emulate]
- **Avoid this** (learned from [competitor]): [what they did poorly that we should avoid]
- ...

Positioning recommendations ("where we fit", "recommended positioning") belong in `/positioning`.

<!-- Include this section only when downstream impact is Minor or Major. Omit entirely for None. -->
## Downstream Impact

> Checked: [list of downstream docs checked]
> Impact: Minor | Major

### Conflicts Found

1. **research/[file].md** — [Section Name]
   - **Stale**: "[exact quote from downstream doc]"
   - **Now**: [what this skill's output says instead]

[For Major only:]
> **Recommended action**: Run `/reconcile-research` to audit and fix all affected downstream documents.

## Next Steps

**Recommended:** [first matching item from step 6]

**Other options:**
- [remaining conditional items from step 6 — only include items whose conditions are met]

## Signals for Downstream Research

> Raw signals captured during research. These are unvalidated observations —
> use the linked skill to verify, validate, and explore alternatives.

### → /positioning
- [signal]: positioning gaps identified in the landscape
- [signal]: category whitespace or unclaimed territory
- [signal]: differentiation opportunities from competitor weaknesses

### → /gtm
- [signal]: competitor channel strategies observed
- [signal]: pricing models and tiers seen across competitors
- [signal]: messaging patterns that appear effective

### → /monetization
- [signal]: competitor pricing tiers and structures
- [signal]: freemium vs. paid patterns in the market
- [signal]: enterprise pricing signals from competitor pages

### → /value-prop-canvas
- [signal]: competitor strengths and weaknesses mapped to customer jobs
- [signal]: unmet customer needs revealed by competitor gaps
- [signal]: value delivery patterns across the landscape

research/competitive-analysis-search-log.md (or research/{slug}/competitive-analysis-search-log.md)

Raw research log — every search query, key findings with source attribution, and the reasoning behind categorisation and positioning recommendations.

research/.progress.yaml

Update only when active-path evidence changes a deferred product path's status, reason, evidence refs, revisit trigger, or next skill. Use product_paths terminology instead of branch terminology. When writing manifest entries, include pipeline_stage: competitive-analysis on the active path entry.

Create the research/ (or research/{slug}/) directory if it doesn't exist.

Task Classification

When this skill produces follow-up work, file it by execution semantics:

• Immediately actionable implementation or documentation work goes in tasks/todo.md.
• Human-only external actions tied to automated steps go in tasks/manual-todo.md with _(blocks: Step N.X)_ or _(after: Step N.X)_; repo edits, SDK wiring, generated assets, local commands, tests, audits, and authenticated CLI/API work stay in tasks/todo.md.
• One-time condition-gated records, baselines, or future measurements go in tasks/record-todo.md with source, condition, non-blocking reason, evidence, and promotion rule.
• Cadence-based reviews, playtests, adoption checks, investor updates, retros, or docs-health checks go in tasks/recurring-todo.md with cadence, owner/agent, next due, evidence path, and escalation conditions.
• Do not put non-blocking records or recurring obligations in tasks/todo.md unless they have been explicitly promoted into current execution work.

Constraints

• Use web search extensively. Framework execution and synthesis must be grounded in real, current market data — not assumptions or hallucinated competitor names. Every competitor cited must come from a web search result.
• Cite sources. When stating facts about competitors (funding, features, pricing), note where the information came from.
• Be honest about uncertainty. If information couldn't be verified, say so. Don't fabricate metrics.
• Stay in analysis mode. Do not propose product changes, architecture, features, or positioning recommendations — product changes are for /spec-interview and /mvp-gap; positioning is for /positioning.
• Focus on actionable insights. Raw competitor lists are easy; the value is in the synthesis — gaps, patterns, positioning angles.
• Do not overwrite existing research/competitive-analysis.md (or research/{slug}/competitive-analysis.md) without asking the user first.
• Keep research current. Prefer recent sources (last 12 months). Flag any information that may be outdated.
• Search breadth over depth initially. Cast a wide net to find all competitors before going deep on each one. It's better to identify 15 competitors and research 8 deeply than to miss half the landscape.
• Present before writing. Never write output files until findings have been presented to the user and validated through the checkpoint questions. The user must see and approve the analysis before anything is written to disk.
• Queue before research in Mode A. Default invocation queues framework work only; it must not emit downstream next-step routing.
• Keep framework subskills route-free. Framework subskills must not emit Recommended next skill or Recommended next command; routing belongs to synthesis after canonical artifacts are approved.

Context Gathering

Step 1 — Scope questions. Before queueing frameworks, ask the user 1–3 questions via AskUserQuestion only if the product/service, target audience, or decision goal is unclear from the repository and arguments.

Step 2 — Framework selection. Use the answers plus repo context to choose defaults, present the framework-selection alignment page, and write framework steps to tasks/todo.md after approval.

Step 3 — Synthesis validation. In /competitive-analysis --synthesize, present the 3–5 most important cross-framework findings before building the final approval alignment page.

Alignment Page

When this skill produces durable deliverables (research, specs, plans, reports, prototypes, or any document output), build a full-depth HTML alignment page following ALIGNMENT-PAGE.md in this skill's directory. Output: alignment/competitive-analysis-{topic}.html.

Default Shipping Contract

Follow the shared shipping contract convention in CLAUDE.md.