skillpacks 0.1.0

package/packs/business-discovery/codex/competitive-analysis/SKILL.md

@@ -0,0 +1,237 @@
+---
+name: competitive-analysis
+description: Orchestrator — select competitive-analysis frameworks, queue framework research, and synthesize market landscape findings
+type: research
+version: v0.16
+argument-hint: "[optional: \"--synthesize\" | \"core\" | concept/category/competitors]"
+invocation: orchestrator
+interview_depth: light
+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 `$pack install <pack>` instead of the target skill. Global skills are always valid. Skills from this same pack are valid because the current skill is already running from that pack.
+
+# Competitive Analysis — Orchestrator
+
+Invoke as `$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:
+
+| 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. 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 - 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 with the full preliminary packet, 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.
+
+## 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, 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 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:
+
+```markdown
+## 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.
+
+## Deliverables
+
+- `research/competitive-analysis.md` (or `research/{slug}/competitive-analysis.md`) — Full competitive landscape: summary, competitor profiles, observable GTM patterns, market gaps, competitive positioning (gaps identified, lessons), signals for downstream research, next steps. In concept-validation mode, includes `## Gap Assessment` section (Market State, Incumbent Quality, Gap Quality, Verdict).
+- `research/competitive-analysis-search-log.md` (or `research/{slug}/competitive-analysis-search-log.md`) — Raw research log: every query, findings, source attribution, reasoning
+- `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.
+
+**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 `$customer-discovery` creates `research/icp.md`)
+
+## Task Classification
+
+When this skill produces follow-up work, file it by execution semantics:
+
+- Immediately actionable implementation or documentation work goes in `tasks/todo.md`.
+- Human-only external actions tied to automated steps go in `tasks/manual-todo.md` with `_(blocks: Step N.X)_` or `_(after: Step N.X)_`; repo edits, SDK wiring, generated assets, local commands, tests, audits, and authenticated CLI/API work stay in `tasks/todo.md`.
+- One-time condition-gated records, baselines, or future measurements go in `tasks/record-todo.md` with source, condition, non-blocking reason, evidence, and promotion rule.
+- Cadence-based reviews, playtests, adoption checks, investor updates, retros, or docs-health checks go in `tasks/recurring-todo.md` with cadence, owner/agent, next due, evidence path, and escalation conditions.
+- Do not put non-blocking records or recurring obligations in `tasks/todo.md` unless they have been explicitly promoted into current execution work.
+
+## Constraints
+
+- Framework execution must use web search extensively — every competitor in a framework output or synthesis must come from a search result.
+- Cite sources for competitor facts.
+- Be honest about uncertainty.
+- Stay in analysis mode — no product changes, architecture, or positioning recommendations. Positioning belongs in `$positioning`.
+- Focus on actionable insights over raw lists.
+- Do not overwrite existing `research/competitive-analysis.md` (or `research/{slug}/competitive-analysis.md`) without asking.
+- Prefer recent sources (last 12 months).
+- Search breadth over depth initially.
+- Present before writing — never write until findings are validated.
+- Default Mode A queues framework work only; it must not emit downstream next-step routing.
+- Framework subskills must not emit `Recommended next skill` or `Recommended next command`; routing belongs to synthesis after canonical artifacts are approved.
+- `## Next Steps` must be the final section in the output file, with a recommended next step and 2–4 other options.
+
+## 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.

package/packs/business-discovery/codex/competitive-analysis/agents/openai.yaml

@@ -0,0 +1,7 @@
+interface:
+  display_name: "Competitive Analysis"
+  short_description: "Research competitors via web search — map landscape, GTM, strengths, weaknesses, and gaps"
+  default_prompt: "Use $competitive-analysis to research the competitive landscape for this project."
+
+policy:
+  allow_implicit_invocation: true

package/packs/business-discovery/codex/competitive-analysis/archive/v0.0/SKILL.md

@@ -0,0 +1,191 @@
+---
+name: competitive-analysis
+description: Research competitors via web search — map the landscape, GTM strategies, strengths, weaknesses, and market gaps
+type: research
+version: v0.0
+argument-hint: "[concept | optional: product category or specific competitors to investigate]"
+---
+
+## 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 `$pack install <pack>` instead of the target skill. Global skills are always valid. Skills from this same pack are valid because the current skill is already running from that pack.
+
+# Competitive Analysis — Market Landscape Research
+
+## Report-First Approval Gate
+
+Default to report-only: present findings, evidence coverage, assumptions, recommended artifact path, and proposed file changes in a pre-approval alignment page plus a concise conversation summary for user approval before creating or updating canonical research, spec, or task files.
+
+Do not write or overwrite synthesized deliverables until the user explicitly approves, unless the user invoked an explicit write/update/fix mode or clearly asked to write files upfront. Raw evidence capture may be persisted before analysis when reproducibility requires it; report those raw paths separately and still gate synthesized research/report writes.
+
+When stopping for approval, build and attempt to open the alignment preview page first, then ask the user to review it and approve, question, or request adjustments. Do not include `Recommended next skill`, `Recommended next command`, or downstream routing language. The approval request itself is the next action. Only emit next-skill routing after the approved artifact has been written or updated.
+
+Conduct deep web-based research to compile a comprehensive competitive landscape for the project. Uses web search to identify competitors, evaluate their maturity, analyse their go-to-market strategies, and surface market gaps.
+
+Default stance: assume the user has no insider knowledge of the market. Present the landscape, category terms, and recommendations from first principles so the analysis stands on its own. Ask for corrections, hard constraints, or proprietary facts, not intuition.
+
+## Prerequisites
+
+**Detect mode before proceeding:**
+
+- **Concept-validation mode** activates when: no `research/icp.md` AND (no meaningful codebase OR `$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/{app}/icp.md`, `research/enterprise-icp.md` or `research/{app}/enterprise-icp.md`, `research/mvp-gap.md` or `research/{app}/mvp-gap.md`) to understand the product.
+
+## Process
+
+### 0. App Scope Resolution (Monorepo Support)
+
+Before checking prerequisites, determine the app scope:
+
+1. If `$ARGUMENTS` specifies an app name matching a subdirectory of `research/`, use it.
+2. If `research/` contains subdirectories (excluding files), list them and ask the user which app to target. If the session is already in Plan mode and there are 2-3 concrete choices, prefer `request_user_input`; otherwise ask in plain text. If only one subdirectory exists, use it automatically.
+3. If no subdirectories exist, proceed with flat structure (single-product mode).
+
+When app scope `{app}` is active:
+- Read/write research from `research/{app}/` instead of `research/`
+- Read/write specs from `specs/{app}/` instead of `specs/`
+- Also read `research/icp.md` (cross-app overview) for broader context
+
+### 1. Establish Product Context
+
+**Standard mode:** Read CLAUDE.md, README, package config, key source files. Read `research/icp.md` (or `research/{app}/icp.md`) if it exists — the ICP defines the competitive frame. Read `research/enterprise-icp.md` (or `research/{app}/enterprise-icp.md`) and `research/mvp-gap.md` (or `research/{app}/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/concept-brief.md` when present, otherwise use the concept description from Prerequisites. Summarise what the concept proposes (problem, audience, approach). Confirm with the user before researching.
+
+### 2. Identify Competitors
+
+Use web search extensively across: direct competitors, indirect competitors, incumbents, emerging players, DIY alternatives.
+
+**Checkpoint 1 — Present competitor list to user.** Show all identified competitors grouped by category. For each competitor, include a one-line description and why it's in that category, citing the search source. Ask: "Are there competitors I missed? Any incorrectly categorised?" Incorporate feedback.
+
+### 3. Research Each Competitor
+
+For each: Company & Product (features, funding, pricing), Maturity & Traction (stage, user signals, integrations), GTM Strategy (acquisition, pricing, content, community), Strengths (user praise, moat), Weaknesses (complaints, gaps, vulnerabilities).
+
+### 4. Identify Market Gaps
+
+Synthesise: underserved segments, feature gaps, pricing gaps, UX gaps, integration gaps, geographic/vertical gaps, technology gaps.
+
+### 4a. Gap Assessment (concept-validation mode only)
+
+Synthesise market gaps into: **Market State** (Virgin/Sparse/Crowded), **Incumbent Quality** (Dominant-and-loved / Dominant-but-resented / Fragmented-and-mediocre / Emerging-and-unproven), **Gap Quality** (Clear unmet need / Underserved segment / UX/approach gap / Minor improvement / No meaningful gap), **Verdict** (Proceed to ICP / Pivot concept / Abandon). If the session is already in Plan mode, prefer `request_user_input`; otherwise ask in plain text before continuing.
+
+### 5. Analyse Positioning Opportunities
+
+**Standard mode:** Where we fit, differentiation angles, competitor lessons, GTM strategy fit, 2-3 angles we could own.
+
+**Concept-validation mode:** Frame as hypothetical — "if you built this": where it would fit, differentiation angles, competitor lessons, GTM fit.
+
+### 6. Present Findings & Validate
+
+**Checkpoint 2 — Present full analysis before writing.** Show: landscape summary, key competitors, market gaps, recommended positioning, GTM insights. Ask: "Which gaps, positioning claims, or assumptions need stronger evidence? Any product-specific constraints or facts I should factor in?" Continue until all details are nailed down.
+
+### 7. Write Output
+
+Only after user validates, write the output files.
+
+## Deliverables
+
+- `research/competitive-analysis.md` (or `research/{app}/competitive-analysis.md`) — Full competitive landscape: summary, competitor profiles, GTM analysis, market gaps, positioning recommendations, next steps. In concept-validation mode, includes `## Gap Assessment` section (Market State, Incumbent Quality, Gap Quality, Verdict).
+- `research/competitive-analysis-search-log.md` (or `research/{app}/competitive-analysis-search-log.md`) — Raw research log: every query, findings, source attribution, reasoning
+
+**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`: `$journey-map` — map the customer and user journey before solution-value decisions, using competitive gaps as inspiration
+2. IF no `research/value-prop.md`: `$value-prop-canvas` — validate solution-customer fit using journey-placed competitive gaps to sharpen the value map
+3. IF no `specs/` directory or it's empty: `$spec-interview [top journey-backed market gap or positioning opportunity]` — spec the strongest opportunity after journey context exists
+4. IF no `research/gtm.md`: `$gtm` — build go-to-market plan leveraging competitive gaps
+5. IF codebase exists and no `research/mvp-gap.md`: `$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:
+- `$value-prop-canvas` — validate solution-customer fit before positioning decisions (if no `research/value-prop.md` and not recommended)
+- `$journey-map` — map the customer journey to find where competitors fall short (if no `research/journey-map.md` and not recommended)
+- `$spec-interview [riskiest competitive assumption or top journey-backed market gap]` — validate the most important unresolved competitive assumption with a targeted interview (if not recommended and journey context exists)
+- `$gtm` — build go-to-market plan leveraging competitive gaps (if no `research/gtm.md` and not recommended)
+- `$mvp-gap` — check if the codebase exploits the gaps found (if codebase exists, no `research/mvp-gap.md` exists, and not recommended)
+- `$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.
+Any `$spec-interview` recommendation must include a concrete target from the analysis, not a bare command. Use the top market gap, riskiest competitive assumption, or strongest positioning opportunity as the bracketed topic.
+
+**Concept-validation mode next steps:** Use the same Recommended + Other options format, but choose the recommendation from the validated `## Gap Assessment` verdict:
+
+## Next Steps
+
+**Recommended:** [verdict-based next step] — [reason grounded in the gap assessment]
+
+Other options:
+- IF verdict is **Proceed to ICP**: recommend `$icp` — 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
+- `$competitive-analysis` — re-run in standard mode after ICP is defined (only after a proceed verdict and after `$icp` creates `research/icp.md`)
+
+## 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 — every competitor must come from a search result.
+- Cite sources for competitor facts.
+- Be honest about uncertainty.
+- Stay in analysis mode — no product changes or architecture.
+- Focus on actionable insights over raw lists.
+- Do not overwrite existing `research/competitive-analysis.md` (or `research/{app}/competitive-analysis.md`) without asking.
+- Prefer recent sources (last 12 months).
+- Search breadth over depth initially.
+- Present before writing — never write until findings are validated.
+- `## Next Steps` must be the final section in the output file, with a recommended next step and 2–4 other options.
+
+## Alignment Page
+
+When this skill produces durable deliverables (research, specs, plans, reports, prototypes, or any document output), build a full-depth HTML alignment page at `alignment/v0.0-{topic}.html`. Use a normalized topic slug derived from the app, feature, research subject, report subject, or output filename.
+
+**Full content requirement.** The alignment page must contain the complete content of every proposed markdown deliverable -- every section, every finding, every detail, every list item. It is a thorough interactive review document, not a summary. Render the full deliverable content in clean, readable HTML with appropriate hierarchy, styling, and navigation. If the skill writes multiple scoped deliverables in one run, build one alignment page that contains all deliverables with anchor-linked navigation. Durable tracker artifacts, such as `research/assumption-tracker.md`, remain canonical markdown outputs but must also be fully rendered into the alignment page before approval.
+
+**Dark-mode styling.** Use a dark color scheme by default. Base CSS variables: `--bg: #0d1117; --surface: #161b22; --border: #30363d; --text: #c9d1d9; --text-muted: #8b949e; --accent: #58a6ff; --green: #3fb950; --red: #f85149; --orange: #d29922; --purple: #bc8cff;`. Apply `background: var(--bg); color: var(--text);` on body. Use `--surface` for cards, nav, and table headers. Use `--border` for all borders. Use `--purple` for question blocks and gate headings. Use `--accent` for links and section headings. Keep headings `color: #fff` or `var(--accent)` for hierarchy. Question block backgrounds should use `#1c2333`.
+
+**Alignment gates.** Treat gates as explicit review sections inside the HTML page. A gate blocks finalization until its required inline questions are answered and compiled into YAML. Include every gate that applies to the skill output, and include these gate types whenever relevant: evidence coverage, assumptions/confidence, scope/non-goals, candidate/verdict decisions, artifact destination, proposed file changes, coverage checkpoint, and post-approval route.
+
+**Report-only research gates.** For report-only or pre-approval research skills, the alignment page must explicitly contain evidence coverage, assumptions/confidence, recommended path, proposed file changes, and approval gates before any canonical research, spec, or task file is created or updated.
+
+
+**Required inline questions.** Each gate must contain at least one required inline question placed directly under the content it governs, inside a visually distinct question block. Each question must use radio-button inputs and include two standing options after the skill-generated choices: "Other / None of the above" backed by a multi-line text box for free-form input, and "Need clarification" backed by an optional notes box where the user can explain what is unclear. When any radio option other than "Other" or "Need clarification" is selected, show an optional "Additional notes" text box beneath it so the user can qualify their choice. Generate questions based on what genuinely needs user input -- do not add filler questions. Do not create a separate bottom "Decisions & Clarifications" section.
+
+**Gate YAML contract.** At the bottom of the page, include a "Compile Answers" button that aggregates answers from all inline gate questions throughout the page, including free-text notes. The button remains disabled until every required question has a selection, shows a count of remaining unanswered questions, and scrolls to the first unanswered question if clicked early. When every question is answered, generate a structured YAML block with one item per gate answer using this stable shape: `section`, `gate_type`, `status` (`answered`, `other`, or `needs-clarification`), `answer`, optional `notes`, and optional `target_artifact` or `target_path` when the gate controls file output. Display the YAML in a read-only, click-to-copy textarea.
+
+**Pre-approval stop.** Before user approval, the next action is review of the HTML alignment page, not downstream routing. Ask the user to review the page and provide the compiled YAML answers. Do not include `Recommended next skill`, `Recommended next command`, or downstream routing language until after compiled YAML has been provided and the approved artifacts have been written or updated.
+
+**Diff highlighting on updates.** When the agent updates an existing alignment page after receiving compiled answers, highlight what changed since the previous version. The agent chooses inline annotation or side-by-side layout per situation.
+
+**Archiving.** Before replacing an existing alignment page, archive it to `docs/history/archive/YYYY-MM-DD/HHMMSS/alignment/v0.0-{topic}.html`.
+
+**Browser open.** Attempt to open the resulting HTML page in the browser and report whether the open succeeded or was blocked. A blocked browser-open attempt does not make the skill fail when the files were written correctly.
+
+## Archive-First Replacement Policy
+
+- Before replacing or substantively rewriting an existing canonical research/spec document (`research/**/*.md`, `specs/**/*.md`, or `docs/specifications/**/*.md`), copy the current file to `docs/history/archive/YYYY-MM-DD/HHMMSS/<original-relative-path>`.
+- Preserve the archived snapshot exactly as it existed before the change; do not edit the archived copy after creating it.
+- After the archive snapshot exists, write the updated document to the original canonical path.
+- Report both the archive path and the updated canonical path in the final output.
+- New files do not need archive snapshots. Append-only updates do not need archive snapshots unless an existing section is regenerated or rewritten.
+- Keep any existing user approval requirement before overwriting or replacing a document; archiving does not replace asking when the skill already requires approval.
+
+## Default Shipping Contract
+
+- **Default next-step routing:** when reporting completion, include either `Recommended next skill: <command>` or the two-line pair `**Next work:** <specific task or "none">` and `**Recommended next command:** <one command or route>` so the next operator has a concrete handoff.
+- If this skill creates or modifies tracked repository files, finish by committing and pushing all intended changes to the repository primary branch (`main` when present, otherwise `master`) before stopping, even if the user did not explicitly ask for commit/push.
+- Do not leave tracked changes or unpushed commits behind. If unrelated tracked work is already present, either include it in sensible commits too or stop and explain the blocker.
+- This contract does not override stricter safety rules about secrets, destructive history changes, release publication/tag confirmation, or production deploy confirmation.