# Narrative Building

> Use when building product positioning, crafting strategy narratives, preparing stakeholder pitches, writing launch narratives, or constructing the 'why now' story for a product or initiative. Encodes Narrative Arc Construction, April Dunford-inspired Positioning, Why Now analysis, Audience Adaptation, Evidence-Narrative Integration, Objection Anticipation, Competitive Narrative Analysis, and Narr…

- **Type:** Skill
- **Install:** `agentstack add skill-avyayalaya-pm-skills-arsenal-narrative-building`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [Avyayalaya](https://agentstack.voostack.com/s/avyayalaya)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [Avyayalaya](https://github.com/Avyayalaya)
- **Source:** https://github.com/Avyayalaya/pm-skills-arsenal/tree/main/skills/narrative-building
- **Website:** https://avyayalaya.github.io/pm-skills-arsenal/

## Install

```sh
agentstack add skill-avyayalaya-pm-skills-arsenal-narrative-building
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

## Purpose

Produce an elite-tier Strategic Narrative Document that constructs the story making a product, feature, or strategy feel inevitable — not by assertion but by structural argument. The output is not a tagline or a slide deck outline; it is a narrative engineering system: a structural spine, audience-adapted variants, evidence-integrated claims, pre-embedded objection responses, and a testing protocol that validates the narrative before it goes live.

## When to Use / When NOT to Use

**Use this skill when:**
- Positioning a new product or repositioning an existing one in a competitive market
- Preparing a board deck, investor pitch, or executive strategy narrative
- Writing the "why now" story for a product launch or market entry
- Crafting the internal alignment narrative ("here's why we're doing this and not that")
- Building a launch narrative for press, analyst briefings, or customer communications
- Translating competitive analysis findings into a positioning story (downstream of Competitive Analysis)
- A product has strong fundamentals but the story isn't landing with stakeholders or customers

**Do NOT use this skill when:**
- You need competitive analysis (use Competitive & Market Analysis skill first — this skill consumes its output, it does not produce it)
- You need to define what to build (use Specification Writing skill — narrative follows strategy, not the other way around)
- You need customer discovery or research synthesis (use Discovery & Research skill — that's primary research, this is narrative construction from existing inputs)
- You need metric design or success measurement (use Metric Design & Experimentation skill)
- You need a tagline, slogan, or brand identity system (this skill produces strategic narrative, not copy)

**Anti-inputs (what this skill does NOT handle):**
- Customer interview synthesis (-> Discovery & Research skill)
- Competitive landscape mapping (-> Competitive & Market Analysis skill)
- Product specification (-> Specification Writing skill)
- Marketing copy, ad copy, or social media content (-> copywriting, not strategic narrative)
- Visual design for presentations (this produces the narrative structure; design is a separate discipline)

## Example

**Prompt:** We're launching Forge, an AI coding assistant. Unlike Copilot/Cursor/Codeium which focus on autocomplete, Forge understands your entire codebase architecture and helps with large-scale refactoring. Our beta users (47 teams) report 60% reduction in time spent on major refactors. We need a launch narrative that positions us distinctly — not as "better autocomplete" but as a different category.

**Output excerpt** (full output is 2,000-5,000 words):

> **Executive Narrative:** Every engineering team lives with a contradiction: the tools that help you write code faster are accelerating the creation of the systems you need to refactor later. AI autocomplete generates 40% of new code at large enterprises, but no AI tool helps you evolve the 95% of code that already exists. **Forge is the first codebase-aware AI that understands your full system architecture to execute large-scale refactoring — reducing major refactor time by 60%, validated across 47 engineering teams.**
>
> **Audience Adaptation (Investor Variant):** The AI coding tools market ($4.2B, growing 35% YoY) is entirely concentrated on code generation. This leaves the larger adjacent problem untouched: codebase evolution. Forge is the first product to address this structurally. The category of "codebase evolution AI" does not yet exist in analyst taxonomies; Forge defines it.

*See `examples/USE_CASES.md` for 3 complete before/after comparisons.*

## Critical Rules

**MUST:**
- Complete the Context Gate before producing any output
- State confidence levels (H/M/L) on every narrative claim
- Cite evidence with tier annotations (T1-T6) in claim tables
- Include adversarial self-critique and objection pre-embedding
- Follow the Output Template structure exactly
- Produce audience-adapted variants from the same structural spine

**MUST NOT:**
- Proceed with missing required context (ask for it instead)
- Present assertions as structural arguments (every positioning claim must be earned through analysis)
- Skip the Quality Check before delivering output
- Confuse a tagline or slogan with a strategic narrative (this produces narrative architecture, not copy)
- Build a narrative that requires a presenter to land (the document must stand alone)

---

## Execution Flow

This skill produces output in 8 steps: **Context Gate → Framework Selection → Narrative Arc Construction → Positioning Analysis → Why Now Analysis → Audience Adaptation → Objection Pre-Embedding → Quality Check**

Each phase builds on the previous. Do not skip phases or reorder them.

---

## Error Handling & Recovery

**Insufficient context:** If the Context Fitness Check (Step 0) fails — no product or strategy to narrate, no competitive context available, and no audience identified — STOP. Do not build a narrative in a vacuum. Ask the user: "What are we building a narrative for? Who is the audience? What decision should this narrative support?"

**Ambiguous scope:** If the narrative purpose could be interpreted multiple ways (e.g., "help me tell our story" could mean investor pitch, customer positioning, internal alignment, or press narrative), clarify the specific audience and purpose before proceeding. State the interpretation you are using and confirm.

**Low-confidence output:** If confidence drops below M (70% confident)**, **M (40-70%)**, **L (I->R->C->W cascade applies to ALL narrative recommendations**, not just final sections. Format: Observation [evidence tier] -> Implication [mechanism] -> Response [specific narrative action] -> Confidence [H/M/L + assumption] -> Watch Indicator [observable signal that the narrative is or isn't landing].

4. **Begin with Context Fitness Check and Framework Selection (Step 0 / Step 0b)** before applying any framework. Identify the narrative type; select the 3-5 load-bearing frameworks; note which to skip. Applying all 8 frameworks to a simple launch narrative dilutes signal and inflates length.

5. **Contradictions between frameworks are signal, not noise.** When Positioning analysis suggests one category and Competitive Narrative Analysis reveals the category is already owned by a competitor, surface the contradiction explicitly and state which to weight more heavily and why.

6. **Flag time-sensitive claims.** Any claim based on data older than 6 months must carry `[POTENTIALLY STALE -- verify before presenting]`. Market shifts, competitor moves, and regulatory changes erode narrative foundations. Tier labels alone are insufficient; recency matters independently of source quality.

7. **Flag thin-evidence conclusions.** If a key narrative claim rests only on Tier 4-6 evidence, prepend it with `[EVIDENCE-LIMITED: validate with Tier 1-2 before using in external-facing narrative]`.

8. **Every framework reference gets a one-line contextual explanation the first time it appears.** Not "April Dunford's Positioning Framework" but "Dunford's framework for defining what makes your product the best choice for a specific customer in a specific context -- we use it here to identify the positioning that makes competitors irrelevant rather than merely inferior." The framework name is for the author's rigor. The reader needs to know why this lens matters for *their* narrative.

9. **The document must be navigable by someone who didn't create it.** Include a reading guide (by time and by role), a notation key, and layered depth. A VP should be able to read only the Executive Narrative and use it verbatim. A PM should be able to read through the audience-adapted variants and select the right one. A comms lead should be able to dive into the evidence integration and testing protocol. No reader should encounter unexplained notation.

---

## Output Template (Mandatory Document Skeleton)

Every Strategic Narrative Document MUST follow this exact structure. Copy this skeleton and fill it in. Do not reorder sections, skip sections, or invent new top-level sections. If a framework was skipped in Step 0, note "Skipped -- not load-bearing for this narrative type" in that section.

```markdown
# Strategic Narrative Document: [Subject -- e.g., "Vanta Analytics Launch Positioning"]

> **Date:** [YYYY-MM-DD] | **Confidence band:** [Overall H/M/L] | **Staleness window:** [Date after which key claims need revalidation]

---

## Executive Narrative

[5-7 sentences max. This IS the narrative -- a VP reads only this and uses it verbatim in their next meeting. No framework names, no jargon, no evidence tier tags. Plain language that makes the product/strategy feel inevitable. Structure: tension -> shift -> opportunity -> your role -> proof -> call to action. Final sentence = the recommended positioning statement in bold.]

---

## How to Read This Document

**What this is:** A narrative engineering system -- not a tagline or a slide deck. It constructs the structural argument for why this product/strategy is inevitable, adapts it for every audience, weaves in evidence, anticipates objections, and provides a testing protocol.

**Reading by time available:**

| Time | Read | You'll get |
|---|---|---|
| **5 min** | Executive Narrative only | The story itself -- ready to use in a meeting |
| **15 min** | Executive Narrative + Narrative Arc (section 1) + Audience Variants (section 4) | The story + its structural logic + which version to use for which audience |
| **30 min** | Full document through Recommendations | Complete narrative system with evidence, objection handling, and competitive positioning |
| **Deep dive** | Everything including Appendix | Full framework applications, testing protocol, assumption stress-testing |

**Reading by role:**

| Role | Start with | Then read | Skip unless curious |
|---|---|---|---|
| VP / Exec | Executive Narrative | Audience Variants (section 4) for their specific context | Everything else -- the narrative is ready to use |
| PM Lead | Executive Narrative | Narrative Arc (section 1), Positioning (section 2), Why Now (section 3), Objection Handling (section 6) | Testing Protocol, Competitive Narrative deep dive |
| Comms / Marketing | Executive Narrative | Audience Variants (section 4), Evidence Integration (section 5), Testing Protocol (section 8) | Framework theory sections |
| Strategy / Analyst | Full document in order | Cross-Framework Contradictions, Adversarial Self-Critique | Nothing -- this is your primary artifact |

---

## Notation Key

**Confidence levels** -- applied to every narrative claim:
- **H (>70% confident)** -- Strong evidence supports this claim. Build the narrative on it.
- **M (40-70%)** -- Direction is probable but evidence is mixed. Use in narrative but flag internally as requiring validation.
- **L (I->R->C->W):
- **O**bservation -- What we see (with evidence tier)
- **I**mplication -- Why it matters for the narrative (the mechanism)
- **R**esponse -- What to do (specific narrative action + owner + timeline)
- **C**onfidence -- How sure we are (H/M/L + key assumption)
- **W**atch -- How to know if the narrative is landing or failing (observable signal)

**Flags:**
- `[POTENTIALLY STALE]` -- Source data is >6 months old; verify before using in narrative
- `[EVIDENCE-LIMITED]` -- Claim rests on T4-T6 evidence only; validate with stronger data before external use

---

## Step 0: Context Fitness Check

Before selecting frameworks, verify that a Strategic Narrative Document is the right artifact for this question.

| Question | If Yes | If No |
|---|---|---|
| **Do you have a clear product/strategy to narrate, or are you still deciding what to build?** | Proceed to Framework Selection | A narrative is premature. Use Problem Framing or Discovery first. Narrative without substance is spin. |
| **Do you have competitive analysis or market context as input?** | Narrative can incorporate competitive positioning and "why now" with evidence | Flag prominently: "This narrative is constructed without competitive context. Positioning claims are hypotheses -- validate against competitive landscape before external use." |
| **Is the primary goal external (market-facing) or internal (alignment)?** | External: weight Positioning, Audience Adaptation, Evidence Integration heavily. Internal: weight Narrative Arc, Why Now, Objection Anticipation heavily. | Both: produce both variants explicitly; they differ in emphasis, evidence standards, and tone. |
| **Do you have access to customer evidence (testimonials, case studies, usage data)?** | Narrative can use T1-T2 evidence for claims | Flag: "Narrative evidence is limited to T3-T6. Claims will need customer proof points before customer-facing use." |

**If any answer is "No":** State this prominently at the top of the Executive Narrative. Example: *"Note: This narrative is constructed without competitive analysis input. Positioning claims should be treated as hypotheses to be validated against the competitive landscape before external use."*

---

## Step 0b: Framework Selection

| Narrative type | Primary frameworks (apply in full) | Supporting frameworks (scan only) | Skipped (why) |
|---|---|---|---|
| [e.g., "Product launch positioning"] | [e.g., F1 Narrative Arc, F2 Positioning, F3 Why Now, F4 Audience Adaptation] | [e.g., F5 Evidence-Narrative Integration, F6 Objection Anticipation] | [e.g., "F7 Competitive Narrative Analysis -- no direct competitor narrative to reverse-engineer"] |

---

## 1. Narrative Arc

**Status Quo:** [What the world looks like today -- the tension the audience already feels]

**Disruption:** [What has changed -- the structural shift that makes the status quo untenable]

**New Reality:** [What the world looks like after the shift -- the inevitable destination]

**Your Role:** [How this product/strategy is the bridge from status quo to new reality]

**Proof:** [Evidence that this is already happening -- not aspirational, but demonstrated]

**Call to Action:** [What the audience should do next -- specific and immediate]

**Narrative Arc Scorecard:**

| Element | Score | Evidence Tier | Strength Assessment | Gap / Action Needed |
|---|:---:|:---:|---|---|
| Status Quo | 1-5 | TX | [Strong/Adequate/Weak] | [If =4 of 5 can reproduce the core argument (not word-for-word, but structurally accurate) | I->R->C->W Cascade)

**Recommendation 1: [Title]**
- **Observation** [TX]: [What we see in the narrative analysis]
- **Implication**: [Why it matters for the narrative's effectiveness]
- **Response**: [Specific narrative action + owner + timeline]
- **Confidence**: [H/M/L] -- assumes [key assumption]
- **Watch**: [Observable signal that this narrative move is working or failing]

**Recommendation 2: [Title]**
- **Observation** [TX]: ...
- **Implication**: ...
- **Response**: ...
- **Confidence**: ...
- **Watch**: ...

**Recommendation 3: [Title]**
[Same structure]

---

## Cross-Framework Contradictions

| Contradiction | Framework A says | Framework B says | Resolution / Which to weight |
|---|---|---|---|
| [e.g., "Category choice vs. competitive narrative"] | [Positioning: create new category] | [Competitive Narrative: competitor already owns that framing] | [Which matters more and why] |

---

## Assumption Registry

| # | Assumption | Framework it underpins | Confidence | Evidence | What would invalidate this |
|---|---|---|---|---|---|
| 1 | | | H/M/L | (TX) | |
| 2 | | | H/M/L | (TX) | |
| 3 | | | H/M/L | (TX) | |

---

## Adversarial Self-Critique

**Weakness 1: [Title]**
[Steelmanned argument against the narrative. What assumption is made? What evidence would disprove it? Scenario where this narrative backfires catastrophically.]

**Weakness 2: [Title]**
[Same depth]

**Weakness 3: [Title]**
[Same depth]

---

## Revision Triggers

| Trigger | What to re-assess | Timeline |
|---|---|---|
| [Observable event] | [Which sections break] | [

…

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [Avyayalaya](https://github.com/Avyayalaya)
- **Source:** [Avyayalaya/pm-skills-arsenal](https://github.com/Avyayalaya/pm-skills-arsenal)
- **License:** MIT
- **Homepage:** https://avyayalaya.github.io/pm-skills-arsenal/

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-avyayalaya-pm-skills-arsenal-narrative-building
- Seller: https://agentstack.voostack.com/s/avyayalaya
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.