New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Prd V09 Positioning Dunford

by mattgierhart in mattgierhart/PRD-driven-context-engineering

Define product positioning using April Dunford's 5-step framework during PRD v0.9 Go-to-Market.

MITAuto-check passedMarketing & SEO

Install Prd V09 Positioning Dunford

skills CLI
$ npx skills add mattgierhart/PRD-driven-context-engineering --skill prd-v09-positioning-dunford -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install mattgierhart/PRD-driven-context-engineering prd-v09-positioning-dunford --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/mattgierhart/PRD-driven-context-engineering.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/prd-v09-positioning-dunford .claude/skills/prd-v09-positioning-dunford && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
prd-v09-positioning-dunford
GitHub stars
180
Token cost
~2.5k tokens
SKILL.md length
1,092 words
Files
1
Skills in repo
45
Repo updated
First seen
Licence
MIT

At a glance

Define product positioning using April Dunford's 5-step framework during PRD v0.9 Go-to-Market.

  • Works in 6 steps: List competitive alternatives → Identify unique attributes [standard+] → Translate attributes to value → …
  • Requests to position the product
  • SKILL.md covers Execution Mode, Framework: Dunford's 5 Steps, Consumes and Produces, plus 6 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Prd V09 Positioning Dunford is an agent skill from mattgierhart/PRD-driven-context-engineering. Define product positioning using April Dunford's 5-step framework during PRD v0.9 Go-to-Market. Triggers on requests to position the product, define category, frame against competitors, or when user asks "what category are we?", "how do we position?", "Dunford positioning", "obviously awesome", "market frame of reference", "positioning statement". Outputs GTM- entries with Type=Positioning and BR-POS- positioning rules.

Its SKILL.md is about 2.5k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Marketing & SEO, covering Positioning and messaging, PRD writing and Go-to-market strategy. The repository describes itself as: PRD-Led Context Engineering — Memory as Infrastructure. An ontology layer for product teams building products that solve real problems — with AI agents that remember. Gated PRD… The licence is MIT.

When your agent uses it

  • Requests to position the product
  • Define category
  • Frame against competitors
  • User asks what category are we?

Example prompts

  • “what category are we?”
  • “how do we position?”
  • “Dunford positioning”
  • “/prd-v09-positioning-dunford”

Requirements

  • Pre-approved tools (allowed-tools): Read, Write, Edit, Glob, Grep, WebSearch

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. List competitive alternatives
  2. Identify unique attributes [standard+]
  3. Translate attributes to value
  4. Identify customers who care a lot
  5. Pick a market category
  6. Trends [deep only]

What it can do on your machine

Read from SKILL.md and the folder at commit 30ed1b0. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read
    • Write
    • Edit
    • Glob
    • Grep
    • WebSearch

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • aprildunford.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Prd V09 Positioning Dunford loads about 2.5k tokens when it runs. Until then it costs about 113 tokens; SKILL.md has 1,092 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~113
When it runs · the whole SKILL.md, loaded when a task matches
~2.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from mattgierhart/PRD-driven-context-engineering at commit 30ed1b0, republished under its MIT licence (© mattgierhart). 1,092 words, ~2,529 tokens.

Download SKILL.mdSave it as .claude/skills/prd-v09-positioning-dunford/SKILL.md (or your agent's skills folder).
name
prd-v09-positioning-dunford
description
Define product positioning using April Dunford's 5-step framework during PRD v0.9 Go-to-Market. Triggers on requests to position the product, define category, frame against competitors, or when user asks "what category are we?", "how do we position?", "Dunford positioning", "obviously awesome", "market frame of reference", "positioning statement". Outputs GTM-* entries with Type=Positioning and BR-POS-* positioning rules.
allowed-tools
Read, Write, Edit, Glob, Grep, WebSearch
context
fork
execution_modes.default
standard
execution_modes.supports
quick, standard, deep

Positioning (Dunford 5-Step)

Position in workflow: v0.8 Monitoring Setup → v0.9 Positioning (Dunford) → v0.9 Offer Construction (Hormozi) → v0.9 Launch Channels (ORB)

Execution Mode

Default is standard. See .claude/rules/08-skill-execution-modes.md for selection logic.

ModeWhat this skill produces
quickOne positioning statement; one best-fit segment; one category claim
standardFull 5 steps; one segment + ≥3 alternatives + 3–5 attributes mapped to value; category claim with frame of reference
deepMultiple segment variants; A/B positioning candidates to test; competitor positioning teardown; "best-fit" disqualification rules

Framework: Dunford's 5 Steps

From Obviously Awesome: How to Nail Product Positioning (April Dunford, 2019). Positioning is the act of deliberately defining how you are the best at something a defined market cares a lot about — not a feature list, not a tagline, not your founder's story.

The five steps run in order:

  1. Competitive alternatives — What would your customers use if you did not exist? (Status-quo wins as often as competitor products do.)
  2. Unique attributes — What capabilities or qualities do you have that those alternatives don't?
  3. Value (and proof) — Translate each attribute into the value it delivers to a customer. Anchor in evidence, not aspiration.
  4. Customers who care a lot — Among all possible buyers, which segment cares most about that value? This is your "best-fit" target.
  5. Market category — Pick the category (the frame of reference) that puts your unique strengths at the center and is intelligible to your best-fit customer.

A 6th step (relevant trends) is optional and used only when a current market trend reinforces the positioning. Skip it in quick mode.

The work product is a positioning statement plus a small set of positioning rules that downstream skills (Offer Construction, Launch Channels, GTM messaging) must honor.

Consumes

  • CFD-* competitive alternatives (from v0.2 Competitive Landscape Mapping) — Anchors step 1; without real alternatives, positioning is hypothetical
  • CFD-* customer interviews (from v0.1 + v0.4) — Source for "who cares a lot" in step 4; the strongest evidence for value claims in step 3
  • BR-* product type (from v0.2 Product Type Classification) — Clone/Unbundle/Undercut/Slice/Wrapper/Innovation shapes the kind of category claim that's credible
  • FEA-* feature list (from v0.3 Feature Value Planning) — Source for step 2 (unique attributes); attribute claims must trace to shipping features
  • PER-* personas (from v0.4 Persona Definition) — Step 4 best-fit segment is one of these PER- entries, sharpened

This skill assumes v0.2 (competitive landscape, product type) and v0.4 (personas) are complete.

Produces

  • GTM-* entries with Type=Positioning — The positioning statement, the category claim, and the frame of reference. Each downstream messaging GTM- must trace to one of these.
  • BR-POS-* positioning rules — Constraint-style rules: who we are, who we are not, what category we live in. These become guardrails for v0.9 Offer Construction, Launch Channels, and v1.0 adoption work.
  • CFD-* updates — When step 3 reveals value claims are weakly evidenced, surface them as research gaps with confidence ≤ 2/5.

Confidence guidance per P4: a positioning statement should reach 3/5 before downstream skills consume it (i.e., grounded in actual customer interviews, not internal opinion). Quick mode may produce 2/5 outputs but must tag them.

Execution

Run the five steps in order. Each step has a single deliverable.

Step 1: List competitive alternatives

Inventory CFD- entries that name alternatives. Include the status quo ("spreadsheet + email"), not just competitor products. Cluster into 2–4 alternative categories.

Deliverable: A ranked list of competitive alternatives with rough usage volume estimates.

Step 2: Identify unique attributes [standard+]

For each FEA- you ship, ask: "Does this alternative have it? At this quality?" Keep only attributes that are demonstrably yours. Quick mode picks the top 3.

Deliverable: 3–5 attributes that are uniquely yours vs. the alternatives.

Step 3: Translate attributes to value

For each attribute, write the value it creates for the customer. Anchor in CFD- evidence (interview quotes, beta data, usage metrics). Mark each value claim with a confidence score.

Deliverable: An attribute → value table with evidence and confidence per row.

Show full SKILL.md (451 more words)Show less
Step 4: Identify customers who care a lot

Cross-reference the value claims against your PER- personas. Which persona's pains are most addressed by your unique values? That is your best-fit segment. Write a "best-fit characteristics" list (firmographics, behaviors, triggers).

Deliverable: One sharpened best-fit PER- variant with "ideal customer" characteristics.

Step 5: Pick a market category

Choose the frame of reference — the category that puts your strengths at the center and is meaningful to your best-fit customer. Test against three checks:

  • Does it make the value claims feel inevitable?
  • Does it disqualify alternatives that aren't a good fit?
  • Would your best-fit customer recognize the category name?

Deliverable: One category claim ("we are the X for Y who need Z") and a one-paragraph positioning statement.

If a current market trend reinforces the positioning (e.g., "AI-native", "compliance-first"), name it. Otherwise skip — trends without product fit are noise.

Deliverable (deep mode): One sentence connecting the positioning to a current trend, with citation.

Output Template

GTM-XXX: Positioning Statement
Type: Positioning
Owner: Founder / Product Marketing
Status: Ready

Best-fit segment: PER-XXX (sharpened — see characteristics below)
Category: [the frame of reference, e.g., "Conversion-rate optimization platform"]
Statement:
  For [best-fit customer]
  Who [trigger / pain]
  [Product name] is the [category]
  That [unique value]
  Unlike [primary alternative], we [unique attribute → value].

Best-fit characteristics:
  - [Firmographic 1]
  - [Behavior 1]
  - [Trigger 1]

Competitive alternatives considered: CFD-001, CFD-002, CFD-003
Unique attributes: FEA-001, FEA-005, FEA-008
Value claims (with evidence):
  - [Attribute] → [Value] (CFD-XXX, confidence: X/5)

Linked IDs: PER-XXX (best-fit), CFD-XXX (alternatives + interviews), FEA-XXX (attributes), BR-POS-XXX (rules)
BR-POS-XXX: Positioning Rule
Type: Constraint
Status: Active

Rule: [What this rule says, e.g., "We do not market to enterprise procurement teams"]
Rationale: [Why — usually traces to the best-fit segment OR a positioning attribute]
Enforced by:
  - GTM-* messaging skills (no enterprise language)
  - Offer Construction (no procurement-friendly contract terms)
  - Launch Channels (no Gartner/analyst channels in launch wave)

Anti-Patterns

PatternSignalFix
Feature-list positioning"We have X, Y, Z"Translate each to value (step 3); cut what doesn't translate
Aspirational alternativesOnly listing competitors as alternativesInclude status quo and non-purchase ("spreadsheet + manual")
Best-fit = everyone"We're for SMBs and enterprise and individual users"Pick one; the others become "not for us"
Category claim too broad"We're the platform for X" (where X is huge)Tighten the frame of reference until it disqualifies bad-fit buyers
No evidence in step 3Value claims with confidence 1/5 across the boardStop and run more interviews before launching
Skipping step 1"Our positioning is..." without alternatives discussionStep 1 is mandatory — positioning without alternatives is internal monologue

Quality Gates

Before proceeding to Offer Construction:

  • All 5 steps have a deliverable (Step 6 optional, deep only)
  • Best-fit segment is one sharpened PER- (not 3 personas)
  • At least 3 competitive alternatives listed (including status quo)
  • At least 3 unique attributes, each with a value translation
  • Each value claim has CFD- evidence and confidence ≥ 2/5 (standard) or ≥ 3/5 (deep)
  • One positioning statement and one category claim, both ≤ 3 sentences
  • At least one BR-POS-* rule encoded (a "we do not" constraint)

Downstream Connections

ConsumerWhat it usesExample
Offer Construction (Hormozi)Best-fit segment + value claimsHormozi's value equation anchors on the value claims here
Launch Channels (ORB)Best-fit characteristics + category claimChannel selection must reach the sharpened best-fit segment
Launch MetricsPositioning statement = KPI- attribution baseline"Did messaging at category X drive signups?"
v1.0 Crossing the Chasm (Moore)Best-fit segment = beachhead anchorMoore's "bowling-alley beachhead" = Dunford's best-fit

Detailed References

  • April Dunford, Obviously Awesome: How to Nail Product Positioning (2019) — canonical source
  • Dunford's blog: aprildunford.com/positioning
  • (No bundled references/ — read the book for depth)

© mattgierhart, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/prd-v09-positioning-dunford of mattgierhart/PRD-driven-context-engineering.

Open the folder on GitHubat commit 30ed1b0

Compare with similar skills

Prd V09 Positioning Dunford next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Prd V09 Positioning Dunford compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Prd V09 Positioning Dunford this skillmattgierhart/PRD-driven-context-engineering180—~2.5kAutomated safety check: PassMIT
Startup Designferdinandobons/startup-skill1.2k—~8.1kAutomated safety check: PassMIT
Product Strategistnicepkg/auto-company1951 repos~2.4kAutomated safety check: PassNone
Obviously Awesomewondelai/skills2.4k—~4.6kAutomated safety check: PassMIT
Revenue Centric Designheliocosta-dev/revenue-centric-design740—~1.6kAutomated safety check: PassCustom licence
Crossing The Chasmwondelai/skills2.4k—~3.6kAutomated safety check: PassMIT

Similar skills

  • Startup Design

    ferdinandobons/startup-skill

    Design, validate, and plan a startup from scratch. An agent skill from ferdinandobons/startup-skill.

    1.2k GitHub stars~8.1k tokensUpdated 3 mo ago
    Marketing & SEOAuto-check passed

  • Product Strategist

    nicepkg/auto-company

    Expert product strategy covering market analysis, competitive positioning, go-to-market planning, and product-led growth.

    195 GitHub starsUsed in 1 repo~2.4k tokens
    Marketing & SEOAuto-check passed

  • Obviously Awesome

    wondelai/skills

    Define product positioning by mapping competitive alternatives, unique attributes, and best-fit customers to the right market category.

    2.4k GitHub stars~4.6k tokensUpdated 1 mo ago
    Marketing & SEOAuto-check passed

  • Revenue Centric Design

    heliocosta-dev/revenue-centric-design

    Playbook for designing SaaS and startup products that convert, retain, and monetize — landing pages & CRO, checkout & forms, onboarding/activation, churn reduction, pricing psychology, dashboards…

    740 GitHub stars~1.6k tokensUpdated 1 mo ago
    Marketing & SEOAuto-check passed

  • Crossing The Chasm

    wondelai/skills

    Navigate the technology adoption lifecycle from early adopters to mainstream market.

    2.4k GitHub stars~3.6k tokensUpdated 1 mo ago
    Marketing & SEOAuto-check passed

  • Landing Page GTM Copy

    ooiyeefei/ccc

    Builds or rewrites SaaS landing pages by researching the real product, positioning it against alternatives and writing buyer-focused copy, then implementing it in the codebase.

    495 GitHub stars~1.8k tokensUpdated 2 mo ago
    Marketing & SEOAuto-check passed

More from mattgierhart/PRD-driven-context-engineering

All 45 skills in this repo

  • Ghm Gate Check

    mattgierhart/PRD-driven-context-engineering

    Validates gate criteria before PRD lifecycle advancement by delegating to the readiness scoring pipeline (scripts/readiness.py).

    180 GitHub stars~1.3k tokensUpdated 1 mo ago
    Auto-check: notes

  • Ghm Harvest

    mattgierhart/PRD-driven-context-engineering

    Extracts durable insights from temp/ files to SoT during EPIC Phase E.

    180 GitHub stars~1.1k tokensUpdated 1 mo ago
    Auto-check passed

  • Ghm Id Register

    mattgierhart/PRD-driven-context-engineering

    Validates and registers new SoT IDs with cross-reference integrity.

    180 GitHub stars~1.5k tokensUpdated 1 mo ago
    Auto-check passed

  • Ghm Sot Builder

    mattgierhart/PRD-driven-context-engineering

    Creates new Source of Truth (SoT) files when existing templates don't fit your needs.

    180 GitHub stars~2k tokensUpdated 1 mo ago
    Auto-check passed

  • Prd V01 Problem Framing

    mattgierhart/PRD-driven-context-engineering

    Transform vague product ideas into evidence-anchored problem statements for PRD v0.1 Spark.

    180 GitHub stars~1.7k tokensUpdated 1 mo ago
    Auto-check passed

  • Prd V01 User Value Articulation

    mattgierhart/PRD-driven-context-engineering

    Transform validated pain points into articulated user value statements for PRD v0.1 Spark.

    180 GitHub stars~1.6k tokensUpdated 1 mo ago
    Auto-check passed

Categories

Questions about Prd V09 Positioning Dunford

What does Prd V09 Positioning Dunford do?

Define product positioning using April Dunford's 5-step framework during PRD v0.9 Go-to-Market. Prd V09 Positioning Dunford is an agent skill from mattgierhart/PRD-driven-context-engineering.9 Go-to-Market.

When should I use Prd V09 Positioning Dunford?

Prd V09 Positioning Dunford fits situations like: requests to position the product; define category; frame against competitors; user asks what category are we?.

How do I install Prd V09 Positioning Dunford in Claude Code?

Run `npx skills add mattgierhart/PRD-driven-context-engineering --skill prd-v09-positioning-dunford -a claude-code`. Or copy the skill folder (.claude/skills/prd-v09-positioning-dunford in mattgierhart/PRD-driven-context-engineering) into .claude/skills/prd-v09-positioning-dunford in your project. Claude Code loads it when a task matches its description.

How do I install Prd V09 Positioning Dunford in Codex?

Run `npx skills add mattgierhart/PRD-driven-context-engineering --skill prd-v09-positioning-dunford -a codex`. Or copy the skill folder (.claude/skills/prd-v09-positioning-dunford in mattgierhart/PRD-driven-context-engineering) into .agents/skills/prd-v09-positioning-dunford in your project. Codex loads it when a task matches its description.

Can I use Prd V09 Positioning Dunford in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add mattgierhart/PRD-driven-context-engineering --skill prd-v09-positioning-dunford -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/prd-v09-positioning-dunford, .gemini/skills/prd-v09-positioning-dunford, .github/skills/prd-v09-positioning-dunford and .opencode/skills/prd-v09-positioning-dunford in your project.

What does Prd V09 Positioning Dunford need to run?

SKILL.md names no scripts, command-line tools or credentials: Prd V09 Positioning Dunford is instructions for the agent only. Its frontmatter pre-approves these tools: Read, Write, Edit, Glob, Grep, WebSearch.

Does Prd V09 Positioning Dunford access the network?

SKILL.md names 1 domain. As links in the text: aprildunford.com. This is read from the text; nothing was executed.

Is Prd V09 Positioning Dunford safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Prd V09 Positioning Dunford use?

Prd V09 Positioning Dunford is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Prd V09 Positioning Dunford use?

About 2.5k tokens (SKILL.md is roughly 10k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Prd V09 Positioning Dunford?

Skills that share tags, products or a category with Prd V09 Positioning Dunford: Startup Design (ferdinandobons/startup-skill, 1.2k stars), Product Strategist (nicepkg/auto-company, 195 stars), Obviously Awesome (wondelai/skills, 2.4k stars) and Revenue Centric Design (heliocosta-dev/revenue-centric-design, 740 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Prd V09 Positioning Dunford?

mattgierhart (a GitHub user) maintains it in mattgierhart/PRD-driven-context-engineering, which has 180 GitHub stars. The repository holds 45 skills in this directory. The repository was last updated on August 31, 2026.

Source: mattgierhart/PRD-driven-context-engineering on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.