skillpacks 0.1.1 → 0.1.2

package/packs/business-research/codex/positioning/frameworks/jtbd-positioning/archive/v0.7/SKILL.md

@@ -0,0 +1,218 @@
+---
+name: jtbd-positioning
+description: Jobs-to-be-Done positioning analysis — identify primary job, map functional/social/emotional dimensions, position around job outcome
+type: research
+version: v0.7
+invocation: sub-skill
+parent: positioning
+---
+
+## 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. Global skills are always valid. Skills from this same pack are valid because the current skill is already running from that pack.
+
+# JTBD Positioning — Jobs-to-be-Done Analysis
+
+Invoke as `$jtbd-positioning`.
+
+## 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.
+
+## Purpose
+
+Applies Clayton Christensen's Jobs-to-be-Done framework to positioning. Instead of positioning around features or competitive differences, positions the product around the *job outcome* the customer is trying to achieve. Produces an intermediate artifact that feeds into the parent `$positioning` synthesis.
+
+## Prerequisites
+
+- **Hard**: `research/icp.md` (or `research/{slug}/icp.md`) must exist. If not, tell the user to run `$customer-discovery` first and stop.
+- **Hard**: `research/competitive-analysis.md` (or `research/{slug}/competitive-analysis.md`) must exist. If not, tell the user to run `$competitive-analysis` first and stop.
+- **Hard**: `research/journey-map.md` (or `research/{slug}/journey-map.md`) must exist. If not, tell the user to run `$journey-map` first and stop.
+- **Soft**: Read if they exist:
+  - `research/customer-feedback.md` — real language about what customers hire the product to do
+  - `research/positioning.md` — existing positioning to build upon
+
+## Product-Path Scope Resolution
+
+Resolve research scope by product path before using code or app structure as a hint:
+
+1. If `$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.
+
+## Process
+
+### 1. Load Context
+
+- Read `research/icp.md` — segments, pain points, trigger events
+- Read `research/competitive-analysis.md` — how alternatives frame themselves
+- Read `research/journey-map.md` — where value is delivered, switching triggers
+- Read `research/customer-feedback.md` if it exists — actual hiring/firing language
+
+### 2. Identify the Primary Job
+
+Research and determine the core job the customer is trying to get done:
+
+- Use WebSearch with 3-5 queries targeting job language in the domain
+- Distinguish the **core functional job** from related consumption-chain jobs
+- Frame as: "When [situation], I want to [motivation], so I can [expected outcome]"
+- Identify the job at the right level of abstraction — not too broad (meaningless), not too narrow (feature-level)
+
+Validate with user. If the session is already in Plan mode, prefer `request_user_input`; otherwise ask in plain text:
+- "Here is the primary job the evidence supports. Is the abstraction level right? Are there competing job framings I should consider?"
+
+### 3. Map Job Dimensions
+
+For the primary job, map three dimensions:
+
+**Functional dimension** — What the customer is practically trying to accomplish:
+- Core steps in getting the job done
+- Speed, accuracy, reliability requirements
+- Where current solutions break down
+
+**Social dimension** — How the customer wants to be perceived:
+- Professional identity alignment
+- Team/peer perception
+- Status and credibility implications
+
+**Emotional dimension** — How the customer wants to feel:
+- Confidence and control
+- Reduced anxiety or frustration
+- Sense of progress
+
+### 4. Identify Job Outcome Metrics
+
+Define success metrics from the customer's perspective (not product metrics):
+- **Speed**: How quickly can the job be completed?
+- **Accuracy**: How reliably does the job get done right?
+- **Effort**: How much work does the customer have to put in?
+- **Satisfaction**: How good does the outcome feel?
+
+Map where alternatives fail on these metrics.
+
+### 5. Position Around Job Outcome
+
+Synthesize positioning that frames the product as the best way to achieve the desired job outcome:
+
+- What is the job the product is hired for?
+- What makes this product uniquely suited to the job?
+- What outcome does the customer achieve that alternatives cannot deliver?
+- Which dimension (functional/social/emotional) is the strongest positioning angle?
+
+Validate with user. If the session is already in Plan mode, prefer `request_user_input`; otherwise ask in plain text:
+- "This JTBD positioning emphasizes [dimension]. Does that match where you see the strongest pull from customers?"
+
+### 6. Write Output
+
+Only after user approval.
+
+## Output
+
+### `research/positioning-jtbd.md` (or `research/{slug}/positioning-jtbd.md`)
+
+```markdown
+# JTBD Positioning Analysis
+
+> Based on: research/icp.md, research/competitive-analysis.md, research/journey-map.md
+> Date: [current date]
+> Methodology: Jobs-to-be-Done (Clayton Christensen / Tony Ulwick)
+
+## Primary Job Statement
+
+When [situation], I want to [motivation], so I can [expected outcome].
+
+## Job Dimensions
+
+### Functional
+| Step | Current Solution | Pain Point | Our Advantage |
+|------|-----------------|------------|---------------|
+| [step] | [how done today] | [what breaks] | [how we're better] |
+
+### Social
+- [social dimension 1]
+- [social dimension 2]
+
+### Emotional
+- [emotional dimension 1]
+- [emotional dimension 2]
+
+## Outcome Metrics
+
+| Metric | Customer Need | Alternative Performance | Our Performance |
+|--------|--------------|------------------------|-----------------|
+| Speed | [need] | [how alternatives do] | [how we do] |
+| Accuracy | [need] | [performance] | [performance] |
+| Effort | [need] | [performance] | [performance] |
+
+## Positioning Angle
+
+**Lead dimension**: [Functional / Social / Emotional]
+**Job outcome framing**: [one sentence: how to position around the job outcome]
+**Evidence strength**: [Strong / Moderate / Weak — with justification]
+
+## Competitive Alternatives by Job
+
+| Alternative | Which Job It Serves | Where It Fails |
+|-------------|--------------------|--------------------|
+| [alternative] | [job framing] | [gap] |
+
+## Implications for Positioning Synthesis
+
+[How this JTBD analysis should influence the final positioning statement — what it suggests for market category, target segment, and key differentiator]
+```
+
+## Task Classification
+
+When this skill produces follow-up work, file it by execution semantics:
+
+- Immediately actionable work goes in `tasks/todo.md`.
+- Human-only external actions go in `tasks/manual-todo.md` with blocking/dependency annotations.
+- Condition-gated records go in `tasks/record-todo.md`.
+- Cadence-based reviews go in `tasks/recurring-todo.md`.
+
+## Constraints
+
+- **Intermediate artifact only.** This produces `research/positioning-jtbd.md`, not the canonical `research/positioning.md`.
+- **Requires journey evidence.** JTBD positioning without understanding the customer journey is speculative.
+- **Job abstraction level matters.** Challenge yourself: is the job too broad or too narrow?
+- **Present before writing.** Never write output files until findings are validated.
+- **Customer language preferred.** Use actual customer words from feedback/interviews when available.
+
+## 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/jtbd-positioning-{topic}.html`.
+
+## Default Shipping Contract
+
+Follow the shared shipping contract convention in CLAUDE.md.

package/packs/business-research/codex/positioning/frameworks/moore-positioning/ALIGNMENT-PAGE.md

@@ -57,9 +57,13 @@ The tier is set per skill via `visual_tier` in SKILL.md frontmatter (or detected
 
 **Report-only research gates.** For report-only or pre-approval research skills, the first `review` alignment page must explicitly contain proposed research scope, source plan, assumptions/confidence, recommended output path, proposed file changes, and approval gates before synthesized research begins and before any working packet, canonical research, spec, or task file is created or updated.
 
-**Staged research workflow.** Heavy report-first research uses a scope-first three-stage approval workflow. Stage 1 is minimal scope discovery only: inspect enough repository, user, and source context to propose research scope, source plan, assumptions, output paths, and approval questions. Build the `review` 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 response YAML approval of the research scope. Do not synthesize findings, rank candidates, recommend a path, or create working packets, canonical research, spec, or task files in Stage 1. Stage 2 starts only after final compiled response YAML approves the research scope 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-moore-positioning-research.md`; product-path mode uses `research/{slug}/_working/preliminary-moore-positioning-research.md`. Existing raw evidence or search-log outputs may remain as supporting evidence when the skill contract already requires them, but synthesized deliverables stay in the working packet. Update the same `review` alignment page so it renders the full preliminary packet, evidence matrix, assumptions/confidence register, source coverage gaps, proposed canonical file changes, and artifact approval gates. Partial compiled responses revise the working packet and review page, then remain in Stage 2. Stage 3 consumes final compiled response YAML for artifact approval only when it has `approval_status: ready-for-agent-review` and 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, and convert the page to `confirmed` with the approval record preserved.
+**Staged research workflow.** Heavy report-first research uses a scope-first three-stage approval workflow. Stage 1 is minimal scope discovery only: inspect enough repository, user, and source context to propose research scope, source plan, assumptions, output paths, and approval questions. Build the `review` 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, research-scope approval gates, and a `Stage 2 Preview / Expected Review Format` section that shows the future Stage 2 review shape before research starts. Stop for final compiled response YAML approval of the research scope. Do not synthesize findings, rank candidates, recommend a path, or create working packets, canonical research, spec, or task files in Stage 1. Stage 2 starts only after final compiled response YAML approves the research scope 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-moore-positioning-research.md`; product-path mode uses `research/{slug}/_working/preliminary-moore-positioning-research.md`. Existing raw evidence or search-log outputs may remain as supporting evidence when the skill contract already requires them, but synthesized deliverables stay in the working packet. Update the same `review` 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. Partial compiled responses revise the working packet and review page, then remain in Stage 2. Stage 3 consumes final compiled response YAML for artifact approval only when it has `approval_status: ready-for-agent-review` and 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, and convert the page to `confirmed` with the approval record preserved.
 
-**Research-pack translation.** For business, devtool, game, creator, and media research packs, render the claim/evidence/inference/assumption/decision-impact structure, source coverage categories appropriate to the domain, lower-confidence findings, and downstream implications before asking for approval or routing to the next skill.
+**Stage 2 review-page template.** Stage 1 scope-review pages must include a `Stage 2 Preview / Expected Review Format` section that previews the exact section sequence, table shapes, evidence treatment, visual density, and approval gates the user will see after research; make it specific enough for the user to flag preferred content formats, grouping, labels, visuals, and evidence density before the agent does heavy research. After scope approval and research, the Stage 2 review page must include these sections as structured HTML, not as raw Markdown dumps: `Research Scope Approved` status block with approved scope, source plan, output paths, and unresolved caveats; `Executive Findings` or a skill-specific top-findings section with confidence labels; `Evidence Matrix` mapping claim, evidence/source/path, inference, confidence, assumptions, and decision impact; `Working Packet Review` with the complete working-packet substance rendered as purpose-built HTML sections, lists, tables, matrices, cards, and tier-appropriate charts or diagrams; `Alternatives / Rejected or Lower-Confidence Findings`; `Source Coverage & Gaps`; `Assumptions / Confidence Register`; `Proposed Canonical Artifacts & File Changes`; a required `User Format Preferences` gate asking whether the layout, tables, grouping, visuals, labels, and evidence density match expectations; and a required `Final Artifact Approval` gate for Stage 3 readiness. Raw Markdown packet text, search logs, or source notes may appear only as supplemental source views after the rendered review UI and never replace the Stage 2 review sections.
+
+**Moore positioning translation.** Research focus: Gather evidence for target customer, need, product category, key benefit, primary alternative, and differentiation. Separate template claims from evidence, inference, assumptions, confidence, and decision impact. Review/documentation format: Render Geoffrey Moore positioning templates, claim-by-claim evidence matrix, alternative/differentiator comparison, confidence register, and rejected template variants. Suggested user feedback: Ask reviewers to confirm target segment, category label, benefit statement, alternative frame, differentiator, confidence, missing proof, and final template implications. Apply the shared artifact-destination/proposed-file-changes de-duplication rule: combine them into one visual gate when they ask only the same path-destination question, and render separate gates when destination approval differs from downstream mutation scope, timing, or allowed files.
+
+**Visual tier rendering.** This skill's alignment page uses the `visual` tier. Inline charts and diagrams are rendered via self-contained Canvas/SVG within the HTML file. Use the alignment chart snippet library (`scripts/alignment-chart-snippets.js`) as reference — copy needed chart functions directly into the page's `<script>` block. Charts must read CSS variables (`--chart-1` through `--chart-8`) for the data visualization palette. Every chart must include a `<table>` fallback, `aria-label` on canvas/SVG, and a "View as table" toggle. Data is embedded as inline JSON — no external fetches.
 
 **Glossary Additions gate.** When this research introduces domain-specific terms, acronyms, or concept definitions that a reader outside the project would not know, include a `## Glossary Additions` section in the alignment page. Render a table of proposed terms with columns: Term, Definition, Source (`moore-positioning`), Category (business/tooling/workflow/technical/domain), and per-term Approve/Edit/Reject/Flag radio controls. Only user-approved terms are appended to the target glossary (`research/glossary.md` or `research/{slug}/glossary.md` for scoped paths) during the confirmed-page write step. When the skill operates in a product-path scope, ask whether each term belongs in the parent or scoped glossary; default to the scoped glossary.
 

package/packs/business-research/codex/positioning/frameworks/moore-positioning/CHANGELOG.md

@@ -1,5 +1,13 @@
 # Changelog
 
+## v0.8 - 2026-06-12
+
+- Clarified staged research review pages must render complete working-packet substance as structured HTML UI, with raw Markdown packet text allowed only as a supplemental source view.
+
+## v0.7 - 2026-06-12
+
+- Standardized active pack and skill install guidance on `npx skillpacks install <pack-or-skill>` instead of agent-native `/pack install` or `$pack install` recommendations.
+
 ## v0.6 - 2026-06-10
 
 - Added npm-aware `npx skillpacks install <pack>` wording to the Pack Availability Guard while preserving runner-specific in-agent pack install routes.

package/packs/business-research/codex/positioning/frameworks/moore-positioning/SKILL.md

@@ -2,14 +2,14 @@
 name: moore-positioning
 description: Geoffrey Moore positioning hypothesis — generate Moore template, map evidence per element, identify weakest link
 type: research
-version: v0.6
+version: v0.8
 invocation: sub-skill
 parent: positioning
 ---
 
 ## 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>` inside Codex, or `npx skillpacks install <pack>` from the project shell, 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.
+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. Global skills are always valid. Skills from this same pack are valid because the current skill is already running from that pack.
 
 # Moore Positioning — Geoffrey Moore Hypothesis
 
@@ -30,7 +30,7 @@ Do not include `Recommended next skill`, `Recommended next command`, or downstre
 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.
+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.

package/packs/business-research/codex/positioning/frameworks/moore-positioning/archive/v0.6/SKILL.md

@@ -0,0 +1,224 @@
+---
+name: moore-positioning
+description: Geoffrey Moore positioning hypothesis — generate Moore template, map evidence per element, identify weakest link
+type: research
+version: v0.6
+invocation: sub-skill
+parent: positioning
+---
+
+## 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 `$pack install <pack>` inside Codex, or `npx skillpacks install <pack>` from the project shell, instead of the target skill. Global skills are always valid. Skills from this same pack are valid because the current skill is already running from that pack.
+
+# Moore Positioning — Geoffrey Moore Hypothesis
+
+Invoke as `$moore-positioning`.
+
+## 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.
+
+## Purpose
+
+Applies Geoffrey Moore's positioning template from "Crossing the Chasm" to generate a structured positioning hypothesis, rigorously map evidence status for each element, and identify the weakest link that needs strengthening. This is a disciplined fill-in-the-blanks exercise that exposes gaps in positioning logic. Produces an intermediate artifact for the parent `$positioning` synthesis.
+
+## Prerequisites
+
+- **Hard**: `research/icp.md` (or `research/{slug}/icp.md`) must exist. If not, tell the user to run `$customer-discovery` first and stop.
+- **Hard**: `research/competitive-analysis.md` (or `research/{slug}/competitive-analysis.md`) must exist. If not, tell the user to run `$competitive-analysis` first and stop.
+- **Soft**: Read if they exist:
+  - `research/journey-map.md` — context for trigger events and value delivery
+  - `research/customer-feedback.md` — customer language for framing
+  - `research/positioning-jtbd.md` — job framing to inform target customer
+  - `research/positioning-strategic-canvas.md` — differentiation evidence
+  - `research/positioning.md` — existing positioning to compare against
+
+## Product-Path Scope Resolution
+
+Resolve research scope by product path before using code or app structure as a hint:
+
+1. If `$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.
+
+## Process
+
+### 1. Load Context
+
+- Read `research/icp.md` — target customers, pain points, trigger events
+- Read `research/competitive-analysis.md` — competitive landscape, alternatives
+- Read any prior framework outputs (JTBD, strategic canvas) for evidence accumulation
+- Read CLAUDE.md, README, key source files for product understanding
+
+### 2. Generate Moore Template Hypothesis
+
+Fill in the Geoffrey Moore positioning template:
+
+> **For** [target customer]
+> **who** [statement of need or opportunity]
+> **the** [product name] **is a** [product category]
+> **that** [key benefit — compelling reason to buy]
+> **Unlike** [primary competitive alternative]
+> **our product** [statement of primary differentiation]
+
+Generate 2-3 candidate hypotheses with different framings:
+- Vary the target customer specificity
+- Vary the product category (existing, subcategory, new)
+- Vary the competitive alternative anchor
+- Vary the differentiation angle
+
+### 3. Map Evidence Status Per Element
+
+For each element of the template, assess evidence strength:
+
+| Element | Content | Evidence Source | Confidence | Gap |
+|---------|---------|----------------|------------|-----|
+| Target customer | [from template] | [which research file] | Strong/Moderate/Weak | [what's missing] |
+| Need/opportunity | [from template] | [source] | [confidence] | [gap] |
+| Product category | [from template] | [source] | [confidence] | [gap] |
+| Key benefit | [from template] | [source] | [confidence] | [gap] |
+| Competitive alt. | [from template] | [source] | [confidence] | [gap] |
+| Differentiation | [from template] | [source] | [confidence] | [gap] |
+
+Use WebSearch (2-4 queries) to validate category framing and competitive alternative accuracy:
+- "[product category] definition", "[primary alternative] positioning"
+- "[category] market leader", "who competes with [alternative]"
+
+### 4. Identify Weakest Link
+
+Determine which template element has the weakest evidence or most problematic framing:
+
+- **Target too broad?** — Positioning that works for everyone works for no one.
+- **Need too generic?** — "Saves time" is not a positioning-grade need.
+- **Category unclear?** — If buyers don't recognize the category, they can't evaluate.
+- **Benefit not unique?** — If alternatives also claim this benefit, it's not positioning.
+- **Wrong competitive anchor?** — If buyers don't actually consider this alternative, the "unlike" fails.
+- **Differentiation unproven?** — Claims without evidence are aspirational, not positioning.
+
+Present findings. If the session is already in Plan mode, prefer `request_user_input`; otherwise ask in plain text:
+- "The weakest link in this positioning hypothesis is [element] because [reason]. Which framing resonates best, and what evidence or insight can strengthen the weak link?"
+
+### 5. Recommend Strongest Hypothesis
+
+Select the strongest candidate and explain:
+- Why it outperforms alternatives
+- What evidence supports each element
+- What remains unproven and how to resolve it
+- How it compares to existing positioning (if any)
+
+### 6. Write Output
+
+Only after user approval.
+
+## Output
+
+### `research/positioning-moore.md` (or `research/{slug}/positioning-moore.md`)
+
+```markdown
+# Moore Positioning Hypothesis
+
+> Based on: research/icp.md, research/competitive-analysis.md[, prior framework outputs]
+> Date: [current date]
+> Methodology: Geoffrey Moore "Crossing the Chasm" positioning template
+
+## Recommended Hypothesis
+
+> **For** [target customer]
+> **who** [statement of need or opportunity]
+> **the** [product name] **is a** [product category]
+> **that** [key benefit — compelling reason to buy]
+> **Unlike** [primary competitive alternative]
+> **our product** [statement of primary differentiation]
+
+## Evidence Map
+
+| Element | Content | Source | Confidence | Gap |
+|---------|---------|--------|------------|-----|
+| Target customer | [content] | [source] | [S/M/W] | [gap or "none"] |
+| Need/opportunity | [content] | [source] | [S/M/W] | [gap] |
+| Product category | [content] | [source] | [S/M/W] | [gap] |
+| Key benefit | [content] | [source] | [S/M/W] | [gap] |
+| Competitive alt. | [content] | [source] | [S/M/W] | [gap] |
+| Differentiation | [content] | [source] | [S/M/W] | [gap] |
+
+## Weakest Link Analysis
+
+**Weakest element**: [element name]
+**Why it's weak**: [explanation]
+**How to strengthen**: [specific action — more research, customer interviews, product changes]
+**Risk if unresolved**: [what happens if this stays weak]
+
+## Alternative Hypotheses Considered
+
+### Hypothesis B
+> [full Moore template]
+
+**Why not recommended**: [reason]
+
+### Hypothesis C
+> [full Moore template]
+
+**Why not recommended**: [reason]
+
+## Implications for Positioning Synthesis
+
+[How this Moore analysis should influence the final positioning — which elements are strongest, where the template reveals gaps, and what it suggests for the canonical positioning statement]
+```
+
+## Task Classification
+
+When this skill produces follow-up work, file it by execution semantics:
+
+- Immediately actionable work goes in `tasks/todo.md`.
+- Human-only external actions go in `tasks/manual-todo.md` with blocking/dependency annotations.
+- Condition-gated records go in `tasks/record-todo.md`.
+- Cadence-based reviews go in `tasks/recurring-todo.md`.
+
+## Constraints
+
+- **Intermediate artifact only.** This produces `research/positioning-moore.md`, not the canonical `research/positioning.md`.
+- **Evidence mapping is non-negotiable.** Every template element must have a cited source and confidence level.
+- **Multiple hypotheses required.** Never present a single option — the comparison reveals trade-offs.
+- **Weakest link must be actionable.** Don't just identify the weakness — recommend how to fix it.
+- **Present before writing.** Never write output files until findings are validated.
+- **Accumulate prior framework evidence.** If JTBD or strategic canvas outputs exist, use them as evidence sources.
+
+## 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/moore-positioning-{topic}.html`.
+
+## Default Shipping Contract
+
+Follow the shared shipping contract convention in CLAUDE.md.