agentleFS
Sign inStart free
Ootto-AIOotto-AI/claude-content-skills/skills/competitor-positioning/SKILL.md

competitor-positioning

Skill417 starsChanged 3 months agoMITView on GitHub

Use when you need to compare supplied competitor messaging with your approved product facts and find a credible point of difference. Trigger phrases include "how are competitors positioned?", "compare our message to theirs", "where are we different?", "audit these competitor pages", and "what should we not say?". Do not use this to make unverified claims about competitors, copy their language, or write the final brand message in isolation; use agent-reach to collect public sources, positioning-audit to decide your message, and campaign-brief to apply it.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Ask which customer decision, category, and alternatives matter.

    line 12
  2. Distinctive:

    Do not state or imply false facts about a competitor's features, pricing, customers, policies, or results.

    line 28
  3. Distinctive:

    Never copy distinctive competitor language, structure, or creative expression.

    line 30
  4. Distinctive:

    Treat absence of evidence as unknown, not as proof a competitor cannot do something.

    line 31
  5. Distinctive:

    Do not use comparative claims in public copy without legal and product approval.

    line 32
  6. Distinctive:

    Use agent-reach before this skill when public evidence must be gathered.

    line 45

≈ “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

Competitor Positioning

Compare observable market messages without turning a competitor scan into a claim sheet or imitation exercise.

1. Define the comparison question

Ask which customer decision, category, and alternatives matter. Gather dated public pages, posts, pricing, documentation, or approved internal notes. Record source URLs or excerpts and dates. If a source cannot be verified, label it as an unverified lead rather than a fact.

2. Separate message from capability

For each alternative, map the audience it addresses, problem framing, promise, proof style, price or access signal if public, and visible limitations. Do not assume a marketing claim proves a feature, or that a missing page proves absence of a capability.

3. Compare against our real evidence

Map our approved product facts, customer language, proof, constraints, and category choice beside the alternatives. Look for a difference that is relevant to the audience and supported by something we can demonstrate. A useful difference may be a workflow, point of view, fit, or trade-off, not a superiority claim.

4. Produce positioning choices and guardrails

Return possible message territories with supporting evidence, risk, and the phrases or claims to avoid. Include the uncertainty that needs verification. Recommend one position to test through positioning-audit or campaign-brief, not a sweeping declaration that the market is settled.

Hard rules

  • Do not state or imply false facts about a competitor's features, pricing, customers, policies, or results.
  • Attribute public observations to their source and date; products and pages change.
  • Never copy distinctive competitor language, structure, or creative expression.
  • Treat absence of evidence as unknown, not as proof a competitor cannot do something.
  • Do not use comparative claims in public copy without legal and product approval.

Failure modes

FailureDo this instead
The scan becomes a feature checklistCompare the customer decision, promise, proof, and trade-offs.
Competitor claims are repeated as factsQuote or summarize the source as their stated message, with date.
The outcome is "we are better"Name one relevant, demonstrable difference and its boundary.
The team copies a rival's framingReturn to our evidence and customer language before choosing a position.

Where it sits

Use agent-reach before this skill when public evidence must be gathered. Use audience-personas and social-listening to ensure the comparison matters to real people. Use positioning-audit to choose our message, then campaign-brief and cross-platform-distribution to apply it.

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.

Check your setup, free