positioning-audit
Skill417 starsChanged 3 months agoMITView on GitHub
Audit a brand's social positioning from its profile, offer, customer proof, and competitor material. Use when the user says "audit our positioning", "review our profile", "why do we sound like everyone else", or "what should our social message be". NOT for inventing a new identity from intuition or writing a post; use audience-personas and social-proof-mining first, then hand approved positioning to the content skills.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- RBraga01/builder-growththeir own version, first seen Nov 1, 2026
- Fearofsnakes/pmm-skillsettheir own version, first seen Mar 21, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- Fearofsnakes/pmm-skillset★ 30same name
- RBraga01/builder-growth★ 2same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository54 other files it gives its agents.
- ab-hook-testerSkill
- agent-reachSkill
- ai-brainSkill
- analytics-readoutSkill
- audience-personasSkill
- best-time-schedulerSkill
- bio-profile-optimizerSkill
- b-roll-shot-listSkill
- campaign-briefSkill
- caption-and-hashtagsSkill
- carousel-builderSkill
- collab-outreachSkill
- comment-miningSkill
- comment-responderSkill
- community-engagement-planSkill
- competitor-positioningSkill
- competitor-teardownSkill
- content-auditSkill
- content-calendarSkill
- content-factorySkill
- content-pillar-builderSkill
- content-repurposerSkill
- content-researchSkill
- cover-thumbnail-briefSkill
- creator-outreachSkill
- cross-platform-distributionSkill
- cross-platform-reformatterSkill
- cta-writerSkill
- dm-script-writerSkill
- going-viralSkill
- hashtag-keyword-researchSkill
- hook-miningSkill
- humanizerSkill
- influencer-partnershipsSkill
- launch-retrospectiveSkill
- linkedin-thought-leadershipSkill
- on-screen-text-writerSkill
- paid-social-briefSkill
- profile-conversion-auditSkill
- reel-analyzerSkill
- reel-builderSkill
- reel-scripterSkill
- series-plannerSkill
- social-analytics-reportSkill
- social-listeningSkill
- social-proof-miningSkill
- story-sequencerSkill
- trend-spotterSkill
- ugc-creator-briefSkill
- utm-campaign-planSkill
- viral-carouselSkill
- viral-hook-writerSkill
- viralitySkill
- x-thread-strategySkill
The file
We split this skill into the rules it gives an agent
7 rules. About 0 are common, 7 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈7
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
- Distinctive: line 23
Ask for the current bio/profile, offer or landing-page copy, three to five customer quotes or outcomes approved for use, and two to five …
- Distinctive: line 25
If customer proof is absent, stop at a diagnosis.
- Distinctive: line 44
Write one positioning sentence in this shape: For [specific audience] who need [job], [brand] helps them get [outcome] through [mechanism], …
- Distinctive: line 48
Test the sentence against four questions:
- Distinctive: line 59
Do not invent customer outcomes, category leadership, demographics, or proof.
- Distinctive: line 60
Do not copy competitor wording.
- Distinctive: line 61
Do not call an unobserved gap "white space".
≈ “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.
Files
Positioning Audit
A profile can sound polished and still give a stranger no reason to care. This skill finds the actual promise, proof, audience, and category language already present, then identifies the smallest credible change. It does not manufacture differentiation.
1. Assemble the evidence
Ask for the current bio/profile, offer or landing-page copy, three to five customer quotes or outcomes approved for use, and two to five competitor profiles or posts. Ask what action the profile should earn: follow, DM, email signup, or purchase.
If customer proof is absent, stop at a diagnosis. A new promise without proof is copywriting, not positioning.
2. Map the current message
For the brand and each competitor, record:
- the audience named or implied
- the promised outcome
- the mechanism or category label
- proof shown, if any
- the next action requested
- repeated phrases and empty category language
Quote the source next to each finding. Mark an item "unclear" rather than filling it in from industry assumptions.
3. Find the credible difference
Compare the maps. Look for one of three things: a proof point competitors do not show, a specific audience they ignore, or a mechanism the brand can honestly explain. Do not treat silence in a small sample as market-wide white space.
Write one positioning sentence in this shape: For [specific audience] who need [job], [brand] helps them get [outcome] through [mechanism], with [proof]. Flag any missing proof in brackets.
4. Stress-test it on the profile
Test the sentence against four questions:
- Could a competitor say this unchanged?
- Is every noun understandable to the target audience?
- Is the outcome backed by a supplied fact or approved quote?
- Does the requested next action make sense after reading it once?
Return the smallest profile changes: name field, bio promise, proof, pinned-content role, and link CTA. Keep the current message when evidence does not justify a rewrite.
Hard rules
- Do not invent customer outcomes, category leadership, demographics, or proof.
- Do not copy competitor wording; map the technique, then use the brand's own language.
- Do not call an unobserved gap "white space".
- Separate facts about the current profile from proposed language.
- A public customer quote needs approval before use.
Failure modes
| Symptom | Cause | Fix |
| The position sounds generic | it names a broad category, not a job and proof | narrow the audience or bring in real proof |
| The claim is stronger than the evidence | the desired outcome replaced the observed one | bracket the claim and collect validation |
| Every competitor sounds the same | only bios were compared | add posts, customer proof, and actual offers |
| The bio improves but conversion does not | the next action is unclear | audit the link destination and pinned content |
Where it sits
social-listening finds demand language → audience-personas groups it → positioning-audit chooses the credible message → profile-conversion-audit tests the profile → campaign-brief carries the position into a campaign.
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
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.