[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6D6BGCRCMV760YVQVGA1GAY":3,"skill-same:01M6D6BGCRCMV760YVQVGA1GAY":69},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":28,"publishedAt":38,"linkOnly":39,"markdownContent":40,"markdownBody":41,"frontMatter":42,"refName":45,"commitSha":46,"skillDirectory":47,"forksCount":48,"repositoryHtmlUrl":49,"repositoryHomepageUrl":50,"ownerHtmlUrl":51,"ownerBlogUrl":52,"ownerDescription":53,"updatedAt":54,"install":55,"resources":68},"01M6D6BGCRCMV760YVQVGA1GAY","positioning",null,"Parent router — detect market vs product mode, recommend positioning frameworks, synthesize outputs into unified positioning","GeorgeQLe\u002Fagentic-skills","GeorgeQLe","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F21134126?v=4","01M6D2JP418S0VGJGF8M93EC3H","George Le","01M6D2JPBAKYD82TA5FS6HKQ3D",1,"MIT","https:\u002F\u002Fgithub.com\u002FGeorgeQLe\u002Fagentic-skills\u002Fblob\u002Fmaster\u002Fpacks\u002Fbusiness-research\u002Fclaude\u002Fpositioning\u002Farchive\u002Fv0.7\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000021","资料检索与研究","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000031","产品经理","PROFESSION","适用职业",[5,29,30,31,32,33,34,35,36,37],"research","product","orchestrator","v0","router","Market","frameworks","synthesize","focus","2026-11-10 10:12:30",false,"---\nname: positioning\ndescription: Parent router — detect market vs product mode, recommend positioning frameworks, synthesize outputs into unified positioning\ntype: research\nversion: v0.7\nargument-hint: \"[optional: \\\"product\\\" | \\\"--synthesize\\\" | focus area]\"\ninvocation: orchestrator\n---\n\n## Pack Availability Guard\n\nBefore telling the user to run a skill from another project-local pack, check `.agents\u002Fproject.json.enabled_packs`. If the target pack is not enabled, recommend `\u002Fpack install \u003Cpack>` 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.\n\n# Positioning — Parent Router\n\nThis is a **parent router skill**. It detects context, recommends applicable positioning frameworks, and synthesizes their outputs. Individual frameworks live as child skills under `frameworks\u002F`.\n\n## Report-First Approval Gate\n\nDefault 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.\n\nDo not write or overwrite synthesized deliverables until the user explicitly approves, unless the user invoked an explicit write\u002Fupdate\u002Ffix 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\u002Freport writes.\n\nWhen 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.\n\n## Prerequisites\n\n- **Hard**: `research\u002Ficp.md` (or `research\u002F{slug}\u002Ficp.md`) must exist. If not, tell the user to run `\u002Ficp` first and stop.\n- **Hard**: `research\u002Fcompetitive-analysis.md` (or `research\u002F{slug}\u002Fcompetitive-analysis.md`) must exist. If not, tell the user to run `\u002Fcompetitive-analysis` first and stop.\n- **Strong default**: `research\u002Fjourney-map.md` (or `research\u002F{slug}\u002Fjourney-map.md`) should exist before writing canonical positioning. If missing, recommend `\u002Fjourney-map` first unless the user explicitly needs a provisional positioning analysis.\n- **Soft**: Read these if they exist:\n  - `research\u002Fjourney-map.md` — where value is delivered, the aha moment\n  - `research\u002Fcustomer-feedback.md` — real customer language about what makes the product different\n  - `research\u002Fmonetization.md` — pricing context for value perception\n\n## Operational Modes\n\n### Mode A: Framework Selection (default first invocation)\n\nActivated by: `\u002Fpositioning` or `\u002Fpositioning [focus area]` (no special flags).\n\n### Mode B: Synthesis\n\nActivated by: `\u002Fpositioning --synthesize`\n\n### Mode C: Product-Positioning Shortcut\n\nActivated by: `\u002Fpositioning product` or `\u002Fpositioning post-launch` or `\u002Fpositioning obviously-awesome`\n\n---\n\n## Process\n\n### 0. Product-Path Scope Resolution\n\nResolve research scope by product path before using code or app structure as a hint:\n\n1. If `$ARGUMENTS` names a non-archived `research\u002F{slug}\u002F` directory or a product-path ID whose `scope_path` points there, use that path. Treat `{slug}` as the product\u002Fapp name, not the ICP, audience, or segment label.\n2. If `$ARGUMENTS` names only `research\u002F_archive\u002F{slug}\u002F` 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.\n3. Read `research\u002F.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\u002F_archive\u002F` from active target selection.\n4. 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.\n5. If no active manifest target exists, list non-archived product directories under `research\u002F`, excluding `research\u002F_archive\u002F` and dot directories. Auto-select only when exactly one exists; ask when multiple exist.\n6. If no product directories exist, use flat `research\u002F` single-product mode.\n7. Detect monorepo\u002Fapp\u002Fpackage structure only as a secondary hint. Suggest creating a missing `research\u002F{slug}\u002F` product path when code clearly exposes an app, but do not require code or monorepo detection before using `research\u002F{slug}\u002F`.\n\nWhen product path `{slug}` is active, read and write research under `research\u002F{slug}\u002F`, specs under `specs\u002F{slug}\u002F`, and treat top-level `research\u002F*.md` files as flat-mode documents or cross-path summaries.\n\n### 1. Mode Detection\n\nDetect **market-positioning mode** (default) or **product-positioning mode**:\n\n**Market-positioning mode** activates when:\n- No `research\u002Fcustomer-feedback.md` with post-launch customer evidence, AND\n- No production codebase with live users detected, AND\n- `$ARGUMENTS` does not contain \"product\", \"post-launch\", or \"obviously-awesome\"\n\nAvailable frameworks in market mode:\n- `jtbd-positioning` — Jobs-to-be-Done positioning analysis\n- `strategic-canvas` — Blue Ocean strategic canvas (eliminate\u002Freduce\u002Fraise\u002Fcreate)\n- `moore-positioning` — Geoffrey Moore positioning hypothesis\n- `category-design` — Play Bigger category creation\n\n**Product-positioning mode** activates when:\n- `research\u002Fcustomer-feedback.md` exists with real customer data, OR\n- `$ARGUMENTS` contains \"product\", \"post-launch\", or \"obviously-awesome\", OR\n- Production spec exists AND customer feedback references real users\n\nAvailable frameworks in product mode:\n- `obviously-awesome` — April Dunford (requires real customer evidence)\n- `strategic-canvas` — optionally, for category refresh\n\n### 2. Load Context\n\n- Read `research\u002Ficp.md` — ICP segments, pain points, value props, trigger events\n- Read `research\u002Fcompetitive-analysis.md` — competitor landscape, gaps\n- Read `research\u002Fjourney-map.md` if it exists — aha moment, value delivery\n- Read `research\u002Fcustomer-feedback.md` if it exists — real language, satisfaction drivers\n- Read CLAUDE.md, README for product context\n- Read any existing `research\u002Fpositioning-*.md` intermediate artifacts (from prior runs)\n\n### 3. Mode A — Framework Selection\n\nBuild an alignment page with:\n\n1. **Mode explanation**: which mode was detected and why (evidence for detection)\n2. **Available evidence summary**: what research exists and what's missing\n3. **Multi-select framework section**: checkboxes for each available framework with:\n   - Framework name and one-line description\n   - Why it's recommended or optional for this context\n   - Pre-checked defaults based on available evidence:\n     - Market mode defaults: `jtbd-positioning` + `strategic-canvas` + `moore-positioning` pre-checked; `category-design` unchecked (recommended only when strategic canvas shows no existing category fits)\n     - Product mode defaults: `obviously-awesome` pre-checked; `strategic-canvas` unchecked (optional refresh)\n4. **Execution plan explanation**: selected frameworks will be written to `tasks\u002Ftodo.md` for sequential `\u002Fexec` execution\n5. **Approval gate**: framework selection confirmation\n\nAfter user approval via compiled YAML (which includes `selected_frameworks` list):\n\nWrite selected frameworks as sequential steps in `tasks\u002Ftodo.md`:\n\n```markdown\n## Positioning Framework Execution\n\n- [ ] Run `\u002Fpositioning\u002Fframeworks\u002Fjtbd-positioning` — JTBD analysis\n- [ ] Run `\u002Fpositioning\u002Fframeworks\u002Fstrategic-canvas` — Blue Ocean gap analysis\n- [ ] Run `\u002Fpositioning\u002Fframeworks\u002Fmoore-positioning` — Positioning hypothesis\n- [ ] Synthesize: `\u002Fpositioning --synthesize` — Combine framework outputs into research\u002Fpositioning.md\n```\n\nOnly include frameworks the user selected. Always append the synthesis step last.\n\nStop after writing `tasks\u002Ftodo.md`. The user runs `\u002Fexec` to execute each framework sequentially.\n\n### 4. Mode B — Synthesis (`\u002Fpositioning --synthesize`)\n\nRead all intermediate framework outputs:\n- `research\u002Fpositioning-jtbd.md`\n- `research\u002Fpositioning-strategic-canvas.md`\n- `research\u002Fpositioning-moore.md`\n- `research\u002Fpositioning-category-design.md`\n- `research\u002Fpositioning-obviously-awesome.md`\n\nAt least one must exist. If none exist, tell user to run framework selection first.\n\nSynthesize into unified `research\u002Fpositioning.md`:\n\n**Market-positioning synthesis includes:**\n- Combined positioning hypothesis drawing from all framework outputs\n- Moore template filled with evidence from JTBD + Canvas + Category analysis\n- Evidence matrix: each claim mapped to which framework(s) support it\n- Confidence levels per claim (strong\u002Fmoderate\u002Fhypothesized)\n- Validation plan: what needs testing before the position is canonical\n- Mode header: `> Mode: Market Positioning (hypothesized, pre-product)`\n\n**Product-positioning synthesis includes:**\n- Positioning statement (Obviously Awesome output)\n- Evidence matrix grounded in customer feedback\n- Confidence levels (most should be \"strong\" — backed by customer data)\n- Mode header: `> Mode: Product Positioning (customer-grounded)`\n\nBuild alignment page for synthesis approval with:\n- Full proposed `research\u002Fpositioning.md` content\n- Evidence matrix combining all framework sources\n- Confidence\u002Fassumption register\n- Proposed file changes gate\n- Approval gate\n\nAfter approval: write `research\u002Fpositioning.md`, then emit next-step routing.\n\n### 5. Mode C — Product-Positioning Shortcut\n\nSkip multi-select. Write directly to `tasks\u002Ftodo.md`:\n\n```markdown\n## Positioning Framework Execution\n\n- [ ] Run `\u002Fpositioning\u002Fframeworks\u002Fobviously-awesome` — April Dunford positioning\n- [ ] Synthesize: `\u002Fpositioning --synthesize` — Write research\u002Fpositioning.md\n```\n\nStop — user runs `\u002Fexec`.\n\n### 6. Next Steps (after synthesis only)\n\nInclude 3–5 applicable items with \"Recommended + Other options\" framing:\n\n- ALWAYS: check `.agents\u002Fproject.json.enabled_packs` for `product-design` — if not enabled, recommend `\u002Fpack install product-design`; if enabled, recommend `\u002Fux-variations [positioning-backed product direction]`\n- IF no `research\u002Fjourney-map.md`: check for `customer-lifecycle` pack → recommend `\u002Fjourney-map`\n- IF solution-customer fit is weak\u002Fdisputed: `\u002Fvalue-prop-canvas`\n- IF revenue\u002Fchannels\u002Fcost\u002Fdefensibility risks exposed: `\u002Flean-canvas`\n- IF no `research\u002Fgtm.md`: check for `business-growth` pack → recommend `\u002Fgtm`\n- IF `research\u002Fgtm.md` exists: recommend `\u002Fgtm` refresh\n- IF no `research\u002Fmonetization.md`: check for `business-growth` pack → recommend `\u002Fmonetization`\n- IF codebase exists: check for `business-ops` pack → recommend `\u002Fmvp-gap`\n\n### 7. Downstream Impact Check (after synthesis write)\n\nCheck for downstream research documents that may be affected:\n- `research\u002Fgtm.md`\n\nClassify impact as None\u002FMinor\u002FMajor per standard pattern.\n\n## Optional Research Trigger Map\n\nThese detours are conditional framework owners, not required AFPS chain links. Apply after synthesis.\n\n| Positioning signal | Owner | Trigger threshold |\n|---|---|---|\n| Solution-customer fit weak\u002Fdisputed, value mapping low confidence | `\u002Fvalue-prop-canvas` | Trigger: unique attributes can't be confidently mapped to value. Skip: value mapping clear even if hypothesized. |\n| Business-model risk (revenue\u002Fchannels\u002Fcost\u002Fdefensibility) exposed by category strategy | `\u002Flean-canvas` | Trigger: risk would change UX or prototype choices. Skip: normal competitive findings. |\n| Pricing architecture central to positioning (premium vs value changes direction) | `\u002Fmonetization` | Trigger: category\u002Fvalue mapping requires grounded pricing. Skip: pricing not a differentiator. |\n\n## Output\n\n### Mode A output: `tasks\u002Ftodo.md` update\n\nFramework execution steps (see section 3 above).\n\n### Mode B output: `research\u002Fpositioning.md` (or `research\u002F{slug}\u002Fpositioning.md`)\n\n```markdown\n# Positioning\n\n> Based on: [list of framework outputs used]\n> Date: [current date]\n> Mode: Market Positioning (hypothesized, pre-product) | Product Positioning (customer-grounded)\n> Frameworks applied: [list]\n\n## Positioning Statement\n\n**For** [target segment]\n**who** [key pain \u002F trigger event]\n**[product name] is a** [market category]\n**that** [key value \u002F unique benefit]\n**Unlike** [primary competitive alternative]\n**[product name]** [key differentiator]\n\n## Summary\n[2-3 sentences: the positioning thesis]\n\n## Evidence Matrix\n\n| Claim | Supporting Framework(s) | Evidence | Confidence | Assumption Status |\n|-------|------------------------|----------|------------|-------------------|\n| [claim] | JTBD \u002F Canvas \u002F Moore \u002F Category \u002F OA | [source] | Strong \u002F Moderate \u002F Hypothesized | Validated \u002F Needs testing |\n\n## Framework Synthesis\n\n### From JTBD Analysis\n[Key findings — primary job, outcome positioning]\n\n### From Strategic Canvas\n[Key findings — eliminate\u002Freduce\u002Fraise\u002Fcreate moves, competitive gaps]\n\n### From Moore Hypothesis\n[Key findings — positioning template, evidence gaps]\n\n### From Category Design\n[Key findings — category diagnosis, POV if new category]\n\n### From Obviously Awesome\n[Key findings — if product mode]\n\n## Target Segment\n[Best-fit segment with evidence from multiple frameworks]\n\n## Market Category\n[Chosen category with evidence from multiple frameworks]\n\n## Confidence Register\n\n| Element | Confidence | Evidence Source | What Would Change It |\n|---------|-----------|----------------|---------------------|\n| [element] | [level] | [source] | [condition] |\n\n## Validation Plan (market mode only)\n[What needs testing before this position is canonical]\n\n## Positioning Implications\n\n### For Messaging\n### For Product\n### For Sales\n### For Pricing\n\n## Downstream Impact\n[Standard pattern]\n\n## Next Steps\n[Standard routing]\n```\n\n## Task Classification\n\nWhen this skill produces follow-up work, file it by execution semantics:\n\n- Immediately actionable implementation or documentation work goes in `tasks\u002Ftodo.md`.\n- Human-only external actions tied to automated steps go in `tasks\u002Fmanual-todo.md` with `_(blocks: Step N.X)_` or `_(after: Step N.X)_`.\n- One-time condition-gated records go in `tasks\u002Frecord-todo.md`.\n- Cadence-based reviews go in `tasks\u002Frecurring-todo.md`.\n- Do not put non-blocking records or recurring obligations in `tasks\u002Ftodo.md` unless promoted.\n\n## Constraints\n\n- **Requires ICP + competitive analysis.** Positioning without knowing the customer and the competition is guesswork.\n- **Customer-grounded.** Every positioning decision must connect to real customer behavior or research evidence.\n- **Mode detection is evidence-based.** Do not override mode detection without user confirmation.\n- **Parent does not execute frameworks.** It selects and queues them. `\u002Fexec` handles execution.\n- **Synthesis requires at least one framework output.** Do not synthesize from zero evidence.\n- **Do not overwrite existing `research\u002Fpositioning.md`** without asking the user first.\n\n## Alignment Page\n\nWhen 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\u002Fpositioning-{topic}.html`.\n\n## Default Shipping Contract\n\nFollow the shared shipping contract convention in CLAUDE.md.\n","## Pack Availability Guard\n\nBefore telling the user to run a skill from another project-local pack, check `.agents\u002Fproject.json.enabled_packs`. If the target pack is not enabled, recommend `\u002Fpack install \u003Cpack>` 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.\n\n# Positioning — Parent Router\n\nThis is a **parent router skill**. It detects context, recommends applicable positioning frameworks, and synthesizes their outputs. Individual frameworks live as child skills under `frameworks\u002F`.\n\n## Report-First Approval Gate\n\nDefault 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.\n\nDo not write or overwrite synthesized deliverables until the user explicitly approves, unless the user invoked an explicit write\u002Fupdate\u002Ffix 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\u002Freport writes.\n\nWhen 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.\n\n## Prerequisites\n\n- **Hard**: `research\u002Ficp.md` (or `research\u002F{slug}\u002Ficp.md`) must exist. If not, tell the user to run `\u002Ficp` first and stop.\n- **Hard**: `research\u002Fcompetitive-analysis.md` (or `research\u002F{slug}\u002Fcompetitive-analysis.md`) must exist. If not, tell the user to run `\u002Fcompetitive-analysis` first and stop.\n- **Strong default**: `research\u002Fjourney-map.md` (or `research\u002F{slug}\u002Fjourney-map.md`) should exist before writing canonical positioning. If missing, recommend `\u002Fjourney-map` first unless the user explicitly needs a provisional positioning analysis.\n- **Soft**: Read these if they exist:\n  - `research\u002Fjourney-map.md` — where value is delivered, the aha moment\n  - `research\u002Fcustomer-feedback.md` — real customer language about what makes the product different\n  - `research\u002Fmonetization.md` — pricing context for value perception\n\n## Operational Modes\n\n### Mode A: Framework Selection (default first invocation)\n\nActivated by: `\u002Fpositioning` or `\u002Fpositioning [focus area]` (no special flags).\n\n### Mode B: Synthesis\n\nActivated by: `\u002Fpositioning --synthesize`\n\n### Mode C: Product-Positioning Shortcut\n\nActivated by: `\u002Fpositioning product` or `\u002Fpositioning post-launch` or `\u002Fpositioning obviously-awesome`\n\n---\n\n## Process\n\n### 0. Product-Path Scope Resolution\n\nResolve research scope by product path before using code or app structure as a hint:\n\n1. If `$ARGUMENTS` names a non-archived `research\u002F{slug}\u002F` directory or a product-path ID whose `scope_path` points there, use that path. Treat `{slug}` as the product\u002Fapp name, not the ICP, audience, or segment label.\n2. If `$ARGUMENTS` names only `research\u002F_archive\u002F{slug}\u002F` 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.\n3. Read `research\u002F.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\u002F_archive\u002F` from active target selection.\n4. 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.\n5. If no active manifest target exists, list non-archived product directories under `research\u002F`, excluding `research\u002F_archive\u002F` and dot directories. Auto-select only when exactly one exists; ask when multiple exist.\n6. If no product directories exist, use flat `research\u002F` single-product mode.\n7. Detect monorepo\u002Fapp\u002Fpackage structure only as a secondary hint. Suggest creating a missing `research\u002F{slug}\u002F` product path when code clearly exposes an app, but do not require code or monorepo detection before using `research\u002F{slug}\u002F`.\n\nWhen product path `{slug}` is active, read and write research under `research\u002F{slug}\u002F`, specs under `specs\u002F{slug}\u002F`, and treat top-level `research\u002F*.md` files as flat-mode documents or cross-path summaries.\n\n### 1. Mode Detection\n\nDetect **market-positioning mode** (default) or **product-positioning mode**:\n\n**Market-positioning mode** activates when:\n- No `research\u002Fcustomer-feedback.md` with post-launch customer evidence, AND\n- No production codebase with live users detected, AND\n- `$ARGUMENTS` does not contain \"product\", \"post-launch\", or \"obviously-awesome\"\n\nAvailable frameworks in market mode:\n- `jtbd-positioning` — Jobs-to-be-Done positioning analysis\n- `strategic-canvas` — Blue Ocean strategic canvas (eliminate\u002Freduce\u002Fraise\u002Fcreate)\n- `moore-positioning` — Geoffrey Moore positioning hypothesis\n- `category-design` — Play Bigger category creation\n\n**Product-positioning mode** activates when:\n- `research\u002Fcustomer-feedback.md` exists with real customer data, OR\n- `$ARGUMENTS` contains \"product\", \"post-launch\", or \"obviously-awesome\", OR\n- Production spec exists AND customer feedback references real users\n\nAvailable frameworks in product mode:\n- `obviously-awesome` — April Dunford (requires real customer evidence)\n- `strategic-canvas` — optionally, for category refresh\n\n### 2. Load Context\n\n- Read `research\u002Ficp.md` — ICP segments, pain points, value props, trigger events\n- Read `research\u002Fcompetitive-analysis.md` — competitor landscape, gaps\n- Read `research\u002Fjourney-map.md` if it exists — aha moment, value delivery\n- Read `research\u002Fcustomer-feedback.md` if it exists — real language, satisfaction drivers\n- Read CLAUDE.md, README for product context\n- Read any existing `research\u002Fpositioning-*.md` intermediate artifacts (from prior runs)\n\n### 3. Mode A — Framework Selection\n\nBuild an alignment page with:\n\n1. **Mode explanation**: which mode was detected and why (evidence for detection)\n2. **Available evidence summary**: what research exists and what's missing\n3. **Multi-select framework section**: checkboxes for each available framework with:\n   - Framework name and one-line description\n   - Why it's recommended or optional for this context\n   - Pre-checked defaults based on available evidence:\n     - Market mode defaults: `jtbd-positioning` + `strategic-canvas` + `moore-positioning` pre-checked; `category-design` unchecked (recommended only when strategic canvas shows no existing category fits)\n     - Product mode defaults: `obviously-awesome` pre-checked; `strategic-canvas` unchecked (optional refresh)\n4. **Execution plan explanation**: selected frameworks will be written to `tasks\u002Ftodo.md` for sequential `\u002Fexec` execution\n5. **Approval gate**: framework selection confirmation\n\nAfter user approval via compiled YAML (which includes `selected_frameworks` list):\n\nWrite selected frameworks as sequential steps in `tasks\u002Ftodo.md`:\n\n```markdown\n## Positioning Framework Execution\n\n- [ ] Run `\u002Fpositioning\u002Fframeworks\u002Fjtbd-positioning` — JTBD analysis\n- [ ] Run `\u002Fpositioning\u002Fframeworks\u002Fstrategic-canvas` — Blue Ocean gap analysis\n- [ ] Run `\u002Fpositioning\u002Fframeworks\u002Fmoore-positioning` — Positioning hypothesis\n- [ ] Synthesize: `\u002Fpositioning --synthesize` — Combine framework outputs into research\u002Fpositioning.md\n```\n\nOnly include frameworks the user selected. Always append the synthesis step last.\n\nStop after writing `tasks\u002Ftodo.md`. The user runs `\u002Fexec` to execute each framework sequentially.\n\n### 4. Mode B — Synthesis (`\u002Fpositioning --synthesize`)\n\nRead all intermediate framework outputs:\n- `research\u002Fpositioning-jtbd.md`\n- `research\u002Fpositioning-strategic-canvas.md`\n- `research\u002Fpositioning-moore.md`\n- `research\u002Fpositioning-category-design.md`\n- `research\u002Fpositioning-obviously-awesome.md`\n\nAt least one must exist. If none exist, tell user to run framework selection first.\n\nSynthesize into unified `research\u002Fpositioning.md`:\n\n**Market-positioning synthesis includes:**\n- Combined positioning hypothesis drawing from all framework outputs\n- Moore template filled with evidence from JTBD + Canvas + Category analysis\n- Evidence matrix: each claim mapped to which framework(s) support it\n- Confidence levels per claim (strong\u002Fmoderate\u002Fhypothesized)\n- Validation plan: what needs testing before the position is canonical\n- Mode header: `> Mode: Market Positioning (hypothesized, pre-product)`\n\n**Product-positioning synthesis includes:**\n- Positioning statement (Obviously Awesome output)\n- Evidence matrix grounded in customer feedback\n- Confidence levels (most should be \"strong\" — backed by customer data)\n- Mode header: `> Mode: Product Positioning (customer-grounded)`\n\nBuild alignment page for synthesis approval with:\n- Full proposed `research\u002Fpositioning.md` content\n- Evidence matrix combining all framework sources\n- Confidence\u002Fassumption register\n- Proposed file changes gate\n- Approval gate\n\nAfter approval: write `research\u002Fpositioning.md`, then emit next-step routing.\n\n### 5. Mode C — Product-Positioning Shortcut\n\nSkip multi-select. Write directly to `tasks\u002Ftodo.md`:\n\n```markdown\n## Positioning Framework Execution\n\n- [ ] Run `\u002Fpositioning\u002Fframeworks\u002Fobviously-awesome` — April Dunford positioning\n- [ ] Synthesize: `\u002Fpositioning --synthesize` — Write research\u002Fpositioning.md\n```\n\nStop — user runs `\u002Fexec`.\n\n### 6. Next Steps (after synthesis only)\n\nInclude 3–5 applicable items with \"Recommended + Other options\" framing:\n\n- ALWAYS: check `.agents\u002Fproject.json.enabled_packs` for `product-design` — if not enabled, recommend `\u002Fpack install product-design`; if enabled, recommend `\u002Fux-variations [positioning-backed product direction]`\n- IF no `research\u002Fjourney-map.md`: check for `customer-lifecycle` pack → recommend `\u002Fjourney-map`\n- IF solution-customer fit is weak\u002Fdisputed: `\u002Fvalue-prop-canvas`\n- IF revenue\u002Fchannels\u002Fcost\u002Fdefensibility risks exposed: `\u002Flean-canvas`\n- IF no `research\u002Fgtm.md`: check for `business-growth` pack → recommend `\u002Fgtm`\n- IF `research\u002Fgtm.md` exists: recommend `\u002Fgtm` refresh\n- IF no `research\u002Fmonetization.md`: check for `business-growth` pack → recommend `\u002Fmonetization`\n- IF codebase exists: check for `business-ops` pack → recommend `\u002Fmvp-gap`\n\n### 7. Downstream Impact Check (after synthesis write)\n\nCheck for downstream research documents that may be affected:\n- `research\u002Fgtm.md`\n\nClassify impact as None\u002FMinor\u002FMajor per standard pattern.\n\n## Optional Research Trigger Map\n\nThese detours are conditional framework owners, not required AFPS chain links. Apply after synthesis.\n\n| Positioning signal | Owner | Trigger threshold |\n|---|---|---|\n| Solution-customer fit weak\u002Fdisputed, value mapping low confidence | `\u002Fvalue-prop-canvas` | Trigger: unique attributes can't be confidently mapped to value. Skip: value mapping clear even if hypothesized. |\n| Business-model risk (revenue\u002Fchannels\u002Fcost\u002Fdefensibility) exposed by category strategy | `\u002Flean-canvas` | Trigger: risk would change UX or prototype choices. Skip: normal competitive findings. |\n| Pricing architecture central to positioning (premium vs value changes direction) | `\u002Fmonetization` | Trigger: category\u002Fvalue mapping requires grounded pricing. Skip: pricing not a differentiator. |\n\n## Output\n\n### Mode A output: `tasks\u002Ftodo.md` update\n\nFramework execution steps (see section 3 above).\n\n### Mode B output: `research\u002Fpositioning.md` (or `research\u002F{slug}\u002Fpositioning.md`)\n\n```markdown\n# Positioning\n\n> Based on: [list of framework outputs used]\n> Date: [current date]\n> Mode: Market Positioning (hypothesized, pre-product) | Product Positioning (customer-grounded)\n> Frameworks applied: [list]\n\n## Positioning Statement\n\n**For** [target segment]\n**who** [key pain \u002F trigger event]\n**[product name] is a** [market category]\n**that** [key value \u002F unique benefit]\n**Unlike** [primary competitive alternative]\n**[product name]** [key differentiator]\n\n## Summary\n[2-3 sentences: the positioning thesis]\n\n## Evidence Matrix\n\n| Claim | Supporting Framework(s) | Evidence | Confidence | Assumption Status |\n|-------|------------------------|----------|------------|-------------------|\n| [claim] | JTBD \u002F Canvas \u002F Moore \u002F Category \u002F OA | [source] | Strong \u002F Moderate \u002F Hypothesized | Validated \u002F Needs testing |\n\n## Framework Synthesis\n\n### From JTBD Analysis\n[Key findings — primary job, outcome positioning]\n\n### From Strategic Canvas\n[Key findings — eliminate\u002Freduce\u002Fraise\u002Fcreate moves, competitive gaps]\n\n### From Moore Hypothesis\n[Key findings — positioning template, evidence gaps]\n\n### From Category Design\n[Key findings — category diagnosis, POV if new category]\n\n### From Obviously Awesome\n[Key findings — if product mode]\n\n## Target Segment\n[Best-fit segment with evidence from multiple frameworks]\n\n## Market Category\n[Chosen category with evidence from multiple frameworks]\n\n## Confidence Register\n\n| Element | Confidence | Evidence Source | What Would Change It |\n|---------|-----------|----------------|---------------------|\n| [element] | [level] | [source] | [condition] |\n\n## Validation Plan (market mode only)\n[What needs testing before this position is canonical]\n\n## Positioning Implications\n\n### For Messaging\n### For Product\n### For Sales\n### For Pricing\n\n## Downstream Impact\n[Standard pattern]\n\n## Next Steps\n[Standard routing]\n```\n\n## Task Classification\n\nWhen this skill produces follow-up work, file it by execution semantics:\n\n- Immediately actionable implementation or documentation work goes in `tasks\u002Ftodo.md`.\n- Human-only external actions tied to automated steps go in `tasks\u002Fmanual-todo.md` with `_(blocks: Step N.X)_` or `_(after: Step N.X)_`.\n- One-time condition-gated records go in `tasks\u002Frecord-todo.md`.\n- Cadence-based reviews go in `tasks\u002Frecurring-todo.md`.\n- Do not put non-blocking records or recurring obligations in `tasks\u002Ftodo.md` unless promoted.\n\n## Constraints\n\n- **Requires ICP + competitive analysis.** Positioning without knowing the customer and the competition is guesswork.\n- **Customer-grounded.** Every positioning decision must connect to real customer behavior or research evidence.\n- **Mode detection is evidence-based.** Do not override mode detection without user confirmation.\n- **Parent does not execute frameworks.** It selects and queues them. `\u002Fexec` handles execution.\n- **Synthesis requires at least one framework output.** Do not synthesize from zero evidence.\n- **Do not overwrite existing `research\u002Fpositioning.md`** without asking the user first.\n\n## Alignment Page\n\nWhen 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\u002Fpositioning-{topic}.html`.\n\n## Default Shipping Contract\n\nFollow the shared shipping contract convention in CLAUDE.md.\n",{"name":5,"type":29,"version":43,"invocation":31,"description":7,"argument-hint":44},"v0.7","[optional: \"product\" | \"--synthesize\" | focus area]","master","96e2912af886dd1606b1b97df707715aef062b02","packs\u002Fbusiness-research\u002Fclaude\u002Fpositioning\u002Farchive\u002Fv0.7",0,"https:\u002F\u002Fgithub.com\u002FGeorgeQLe\u002Fagentic-skills","https:\u002F\u002Fagentic-skills-blush.vercel.app","https:\u002F\u002Fgithub.com\u002FGeorgeQLe","georgeqle.com","George Le is a futurist and serial tech entrepreneur who wants to work toward a world where humanity is free from robotic tasks.","2026-11-10 04:07:24",{"source":8,"skillName":5,"commands":56,"prompt":66,"zipAvailable":67},[57,60,63],{"tool":58,"command":59},"npx","npx skills add GeorgeQLe\u002Fagentic-skills --skill positioning",{"tool":61,"command":62},"bunx","bunx skills add GeorgeQLe\u002Fagentic-skills --skill positioning",{"tool":64,"command":65},"pnpm","pnpm dlx skills add GeorgeQLe\u002Fagentic-skills --skill positioning","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FGeorgeQLe\u002Fagentic-skills\u002Fblob\u002Fmaster\u002Fpacks\u002Fbusiness-research\u002Fclaude\u002Fpositioning\u002Farchive\u002Fv0.7\u002FSKILL.md",true,[],[70,82,92,104,117,128],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":38},"01M6G0NJES15RJKZE6YZ0TSYGF","source-checkout-allowed","Valid source-checkout-only fixture.","https:\u002F\u002Fgithub.com\u002FGeorgeQLe\u002Fagentic-skills\u002Fblob\u002Fmaster\u002Ftests\u002Ffixtures\u002Fskill-install-routing\u002Fvalid\u002Fsource-checkout-allowed\u002FSKILL.md",[],[77,78,79,80,32,81],"source checkout allowed","checkout","fixture","only","valid",{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":38},"01M6G0NFZ3R1MNB1E3DVTM0WB7","deck-install-valid","Valid deck install fixture.","https:\u002F\u002Fgithub.com\u002FGeorgeQLe\u002Fagentic-skills\u002Fblob\u002Fmaster\u002Ftests\u002Ffixtures\u002Fskill-install-routing\u002Fvalid\u002Fdeck-install\u002FSKILL.md",[],[89,90,91,81,79,32],"deck install valid","deck","install",{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":38},"01M6G0ND3QZQC4MDZ9NVB97PT2","codex-pack-guard-valid","Valid Codex Pack Availability Guard fixture.","https:\u002F\u002Fgithub.com\u002FGeorgeQLe\u002Fagentic-skills\u002Fblob\u002Fmaster\u002Ftests\u002Ffixtures\u002Fskill-install-routing\u002Fvalid\u002Fcodex-pack-guard\u002FSKILL.md",[],[99,100,101,81,102,103,79,32],"codex pack guard valid","pack","guard","codex","availability",{"skillNo":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":113,"publishedAt":38},"01M6G0NA9YB3NKGZKD3S96JMNB","codex-missing-skill-valid","Valid Codex missing skill fallback fixture.","https:\u002F\u002Fgithub.com\u002FGeorgeQLe\u002Fagentic-skills\u002Fblob\u002Fmaster\u002Ftests\u002Ffixtures\u002Fskill-install-routing\u002Fvalid\u002Fcodex-missing-skill-fallback\u002FSKILL.md",[110],{"categoryNo":111,"categoryName":112,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[114,115,81,102,32,116,79],"codex missing skill valid","missing","fallback",{"skillNo":118,"name":119,"nameZh":6,"description":120,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":121,"categories":122,"keywords":124,"publishedAt":38},"01M6G0N7PC0EKFD40ZWQAXSAQ9","codex-base-skill-fallback-valid","Valid Codex base skill fallback fixture.","https:\u002F\u002Fgithub.com\u002FGeorgeQLe\u002Fagentic-skills\u002Fblob\u002Fmaster\u002Ftests\u002Ffixtures\u002Fskill-install-routing\u002Fvalid\u002Fcodex-base-skill-fallback\u002FSKILL.md",[123],{"categoryNo":111,"categoryName":112,"taxonomyType":21,"taxonomyTypeDesc":22},[81,102,116,125,126,127,32,79],"base skill","codex base skill fallback valid","base",{"skillNo":129,"name":130,"nameZh":6,"description":131,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":132,"categories":133,"keywords":134,"publishedAt":38},"01M6G0N4VRR2YKZQ6N3Y6S2BQA","claude-pack-guard-valid","Valid Claude Pack Availability Guard fixture.","https:\u002F\u002Fgithub.com\u002FGeorgeQLe\u002Fagentic-skills\u002Fblob\u002Fmaster\u002Ftests\u002Ffixtures\u002Fskill-install-routing\u002Fvalid\u002Fclaude-pack-guard\u002FSKILL.md",[],[81,101,100,135,103,32,79],"claude pack guard valid"]