agentleFS
camrontaylorcamrontaylor/AI-OS-Template/.claude/skills/mkt-positioning/SKILL.md

mkt-positioning

Skill0 starsChanged 45 days agoMITView on GitHub

Find the angle that makes something sell. Use when launching a product, writing a landing page, crafting an offer, or when marketing feels flat. Searches competitor messaging to map the landscape, loads brand context, then generates 3-5 distinct positioning angles with a recommended pick. Writes chosen angle to brand_context/positioning.md. Optionally seeds an ad testing matrix. Triggers on: "find angles for", "how should I position", "what's the hook", "why isn't this selling", "make this stand out", "differentiate", "USP", "positioning". Foundation skill — run before execution skills that need an angle to write from. Does NOT trigger for voice extraction, audience research, or content writing.

The file

Show its rules and text

We split this skill into the rules it gives an agent

18 rules. About 0 are common, 11 are distinctive, and 7 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈11

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 7

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If it doesn't exist → proceed to Step 1.

    line 44
  2. Distinctive:

    Not the product. The transformation.

    line 50
  3. Distinctive:

    Ask: "What does your customer's life look like after using this?

    line 52
  4. Distinctive:

    Do nothing (live with the problem)

    line 61
  5. Distinctive:

    Search the web for real competitor messaging.

    line 73
  6. Very specific:

    Read references/competitive-search.md for the full search process and landscape map format.

    line 75
  7. Very specific:

    Read references/market-sophistication.md for Schwartz's 5 stages.

    line 83
  8. Very specific:

    Run the product through multiple angle frameworks.

    line 91
  9. Distinctive:

    Before presenting, check each angle: specific, differentiated against the landscape map, believable given the available proof, relevant to …

    line 99
  10. Distinctive:

    Ask: "Which angle resonates?

    line 103
  11. Very specific:

    After the user selects an angle, write brand_context/positioning.md.

    line 109
  12. Very specific:

    Read references/positioning-output.md for the exact format.

    line 110
  13. Distinctive:

    If the file already existed, show what changed and confirm before overwriting.

    line 112
  14. Distinctive:

    After saving, offer: "Want me to generate a 12-ad testing matrix for this angle?

    line 114
  15. Very specific:

    Ask: "How did this angle perform once you used it?" Log feedback to context/learnings.md under ## mkt-positioning with date and context.

    line 120
  16. Very specific:

    If the user flags an issue with the output, add a dated entry under ## Rules in this skill's SKILL.local.md (create it if missing) and log …

    line 133
  17. Distinctive:

    User can't articulate the transformation: Ask what their best customers say about the product — the transformation is in their words, not …

    line 139
  18. Distinctive:

    Positioning exists but feels stale: Run a fresh competitive search and compare — the market may have moved.

    line 142

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Positioning

The same product can sell dramatically better with a different angle. Not a different product — just a different way of framing what it already does. This skill finds those angles.

Outcome

brand_context/positioning.md containing: primary positioning angle, competitive landscape summary, market sophistication assessment, and all explored alternatives.

The structured data format is defined in references/positioning-output.md.

Context Needs

FileLoad levelHow it shapes this skill
brand_context/icp.mdFullAudience segments, pain points, and language patterns inform angle generation
brand_context/voice-profile.mdTone onlyEnsures angle language matches brand register
context/learnings.md## mkt-positioning sectionApply previous feedback on what converted

Load if they exist. Proceed without them if not.


Before You Start

Check if brand_context/positioning.md exists.

If it exists → Update mode. Read the file, show the current primary angle and statement, and ask: "Want to refine this with fresh competitive data, or start from scratch?" Refine mode runs a fresh competitive search and suggests adjustments. Start fresh runs the full process below.

If it doesn't exist → proceed to Step 1.


Step 1: Identify the Transformation

Not the product. The transformation. What does the customer's life look like after? What pain disappears? What capability appears?

Ask: "What does your customer's life look like after using this? What changes?"

A fitness program sells "fit into your old jeans." A SaaS tool sells "close your laptop at 5pm." The transformation is the raw material for angles.


Step 2: Map Alternatives

What would customers do if this didn't exist? Not just competitors — all alternatives:

  • Do nothing (live with the problem)
  • DIY (cobble together a solution)
  • Hire someone (consultant, freelancer, agency)
  • Buy a different category entirely
  • Buy a direct competitor

Each alternative has weaknesses. Those weaknesses become angle opportunities.


Step 3: Competitive Messaging Search

Search the web for real competitor messaging. This grounds angles in current market reality.

Read references/competitive-search.md for the full search process and landscape map format.

Key output: a map showing saturated claims (everyone says it), partially claimed territory, and white space (nobody is talking about it). Angles built on white space outperform echoed claims.


Step 4: Assess Market Sophistication

Read references/market-sophistication.md for Schwartz's 5 stages.

The market stage determines which angle type will work. A new category needs simple announcement. A crowded market needs mechanism explanation. A jaded market needs identity framing.


Step 5: Generate Angles

Run the product through multiple angle frameworks. Read references/angle-frameworks.md for the full set (Contrarian, Unique Mechanism, Transformation, Enemy, Speed/Ease, Specificity, Social Proof, Risk Reversal).

Generate 3-5 distinct options. For each:

  • Statement — one sentence positioning
  • Psychology — why this works with this audience at this market stage
  • Headline direction — how it would sound in copy
  • Best for — market conditions and audience segments

Before presenting, check each angle: specific, differentiated against the landscape map, believable given the available proof, relevant to the ICP, and concrete enough to picture as a headline or ad. Sharpen or drop any that fail.

Mark one with a recommendation and explain why it's the strongest fit given their competitive white space and market stage.

Ask: "Which angle resonates? Pick a number, or tell me to combine elements from multiple."


Step 6: Save Output

After the user selects an angle, write brand_context/positioning.md. Read references/positioning-output.md for the exact format.

If the file already existed, show what changed and confirm before overwriting.

After saving, offer: "Want me to generate a 12-ad testing matrix for this angle? I'll map 4 hooks across 3 formats."


Step 7: Collect Feedback

Ask: "How did this angle perform once you used it?" Log feedback to context/learnings.md under ## mkt-positioning with date and context.


Rules

Updated automatically when the user flags issues. Read before every run.


Self-Update

If the user flags an issue with the output, add a dated entry under ## Rules in this skill's SKILL.local.md (create it if missing) and log it to context/learnings.md under ## mkt-positioning. Write the general rule the correction implies, not the one-off fix.


Troubleshooting

User can't articulate the transformation: Ask what their best customers say about the product — the transformation is in their words, not the founder's. No competitors found: The product may be category-creating (Stage 1). Lead with simple announcement angles. All angles feel similar: The mechanism isn't clear enough. Go back to Step 1 and dig deeper on what makes their approach different. Positioning exists but feels stale: Run a fresh competitive search and compare — the market may have moved.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.