profile-conversion-audit
Skill417 starsChanged 3 months agoMITView on GitHub
Use when an owned social profile needs an evidence-based audit of whether the right visitor can understand the account, trust it, and take the next approved step. Trigger phrases include "audit our Instagram profile", "fix our LinkedIn page", "why does this profile not convert?", "review this social bio", and "what should be clearer on our profile?". Do not use this to promise conversion lifts, change a platform account directly, or write a campaign message from scratch; use positioning-audit for the core message, social-proof-mining for approved proof, and campaign-brief for a launch-specific promise.
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
- positioning-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
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
- Distinctive: line 12
Ask for the profile URL or supplied screenshots, platform, audience context, current objective, linked destination, and constraints.
- Distinctive: line 28
Do not invent follower counts, customer logos, results, features, availability, or verification status.
- Distinctive: line 29
Never promise a conversion-rate improvement from a profile edit.
- Distinctive: line 30
Keep all claims aligned with the approved landing destination and product reality.
- Distinctive: line 31
Do not recommend deceptive urgency, misleading links, or hidden disclosures.
- Distinctive: line 45
Use positioning-audit to settle the central message and social-proof-mining to source permitted proof.
≈ “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
Profile Conversion Audit
Review the profile as a visitor journey: immediate understanding, credible evidence, useful navigation, and one truthful next step.
1. Capture the profile as a visitor sees it
Ask for the profile URL or supplied screenshots, platform, audience context, current objective, linked destination, and constraints. Review the visible name, category, bio, links, pinned material, highlights or featured items, recent posts, and contact route only as they actually appear.
2. Test the first-ten-seconds questions
Can the right visitor tell who the account helps, what it helps with, why it is credible, and what to do next? Record missing information, competing actions, jargon, unsupported claims, inaccessible media, and mismatches between the profile and linked destination.
3. Recommend evidence-backed changes
Prioritise changes by clarity and risk: identity, audience situation, approved promise, proof, navigation, and action. Supply proposed copy only from approved facts and proof. Explain why each change addresses a visitor question and what must remain unchanged for disclosure, brand, or platform policy.
4. Define a reversible validation plan
State what can be changed by the profile owner, what needs approval, and how to observe the result using the data actually available. Change one meaningful element at a time where possible. Treat outcomes as evidence for the next iteration, not a promised uplift.
Hard rules
- Do not invent follower counts, customer logos, results, features, availability, or verification status.
- Never promise a conversion-rate improvement from a profile edit.
- Keep all claims aligned with the approved landing destination and product reality.
- Do not recommend deceptive urgency, misleading links, or hidden disclosures.
- Respect platform constraints and accessibility for text, captions, images, and contact routes.
Failure modes
| Failure | Do this instead |
| The audit optimises the bio alone | Review the full visitor path: profile, proof, featured material, and destination. |
| A profile says everything to everyone | Choose the approved primary audience situation and one clear action. |
| Proof is added without permission | Use social-proof-mining and publish only cleared evidence. |
| Multiple changes hide what improved | Prioritise and validate one meaningful change at a time. |
Where it sits
Use positioning-audit to settle the central message and social-proof-mining to source permitted proof. Use campaign-brief when a temporary campaign changes the profile's purpose. Use social-analytics-report to review available profile and link outcomes, then return here for the next iteration.
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.