social-campaign-proof-tracker
Skill3 starsChanged 6 months agoMITView on GitHub
Plan, document, and follow up on public proof campaigns across LinkedIn, X, GitHub, websites, and videos. Use when the user wants carousel or thread copy, alt text, post/video captions, public link tracking, reply banks, engagement review, or a campaign proof trail after publishing project work.
In this repository47 other files it gives its agents.
- agents-md-writerSkill
- ai-image-run-pacingSkill
- automation-state-reconcilerSkill
- backup-readiness-auditorSkill
- brand-voice-linterSkill
- case-study-writerSkill
- client-delivery-auditorSkill
- client-intake-builderSkill
- client-workspace-scaffolderSkill
- code-deduplicatorSkill
- cold-outreach-writerSkill
- demo-animationSkill
- demo-animation-v2Skill
- discovery-briefSkill
- em-dash-removerSkill
- etsy-listing-optimizerSkill
- follow-up-radarSkill
- github-profile-proof-updaterSkill
- github-safe-publisherSkill
- idea-inboxSkill
- implement-client-feedbackSkill
- lead-scorerSkill
- llms-txt-generatorSkill
- local-app-public-demoSkill
- media-spec-checkerSkill
- obsidian-daily-noteSkill
- ops-status-reportSkill
- outreach-pipeline-designerSkill
- php-form-mailerSkill
- proposal-writerSkill
- release-announcement-writerSkill
- remove-ai-image-metadataSkill
- research-brief-curatorSkill
- research-to-articleSkill
- screen-recorderSkill
- session-handoffSkill
- skill-builderSkill
- skill-reviewerSkill
- skill-nameSkill
- thumbnail-legibility-checkSkill
- thumbnail-set-designerSkill
- vault-janitorSkill
- verify-public-claimsSkill
- web-scraperSkill
- website-change-verifierSkill
- windows-reinstall-plannerSkill
- write-evidence-backed-profileSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
14 rules. About 0 are common, 14 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈14
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 10
Use this skill to turn a project update into a public proof campaign with platform-specific copy, visual order, alt text, links, reply …
- Distinctive: line 37
Add accessibility and context:
- Distinctive: line 42
Create or update a local tracker:
- Distinctive: line 50
After publishing, record only public results unless the user explicitly provides private metrics for private analysis.
- Distinctive: line 54
Do not include private analytics exports, cookies, account IDs, unpublished client data, raw messages, private prompts, local paths, or …
- Distinctive: line 55
Do not invent engagement results.
- Distinctive: line 56
Do not imply client permission or measurable outcomes unless the user confirms them.
- Distinctive: line 57
Keep reply banks human-reviewed and non-spammy.
- Distinctive: line 58
Treat low comments as normal signal, not failure.
- Distinctive: line 63
Use concrete nouns: system, workflow, profile, proof layer, demo, skill, release.
- Distinctive: line 64
Avoid vague hype such as "game-changing" unless the user asks for a louder tone.
- Distinctive: line 65
Keep CTAs light: "I am building this in public", "open to feedback", "details on GitHub", or "happy to share the workflow".
- Distinctive: line 70
Use this structure by default:
- Distinctive: line 111
Follow-up actions and timing.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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
Social Campaign Proof Tracker
Overview
Use this skill to turn a project update into a public proof campaign with platform-specific copy, visual order, alt text, links, reply prompts, and follow-up tracking.
This skill organizes and drafts. It must not post, upload, comment, message, or submit externally unless the user explicitly asks and confirms the final action.
Workflow
- Identify the proof object:
- GitHub update
- demo
- video
- website page
- case study
- skill release
- automation milestone
- Gather only public-safe inputs:
- public links
- approved images or videos
- short outcome summary
- safe implementation categories
- approved calls to action
- Choose platform shape:
- LinkedIn: reflective post, carousel, document-style sequence, or video post
- X: short post, thread, image-led thread, or video-led post
- GitHub: README note, release note, proof trail, or demo link
- Draft platform copy.
- LinkedIn: clearer context, stronger hook, more reflective tone.
- X: short lines, one idea per post, direct links.
- Add accessibility and context:
- alt text for each image
- caption for video if needed
- link labels
- comment/reply prompts
- Create or update a local tracker:
- campaign name
- date
- asset list
- published links
- follow-up windows
- engagement notes
- useful replies
- After publishing, record only public results unless the user explicitly provides private metrics for private analysis.
Public Safety Rules
- Do not include private analytics exports, cookies, account IDs, unpublished client data, raw messages, private prompts, local paths, or credential-adjacent details.
- Do not invent engagement results.
- Do not imply client permission or measurable outcomes unless the user confirms them.
- Keep reply banks human-reviewed and non-spammy.
- Treat low comments as normal signal, not failure. Track proof value, reuse potential, and follow-up ideas.
Copy Rules
- Lead with the public proof angle or the useful lesson.
- Use concrete nouns: system, workflow, profile, proof layer, demo, skill, release.
- Avoid vague hype such as "game-changing" unless the user asks for a louder tone.
- Keep CTAs light: "I am building this in public", "open to feedback", "details on GitHub", or "happy to share the workflow".
- For X, prefer a thread over unrelated comments when multiple visuals belong to one story.
Tracker Shape
Use this structure by default:
# Campaign Tracker
Campaign:
Date:
Proof object:
Primary link:
## Assets
| Asset | Platform | Status | Notes |
| --- | --- | --- | --- |
## Published Links
| Platform | URL | Notes |
| --- | --- | --- |
## Follow-Up
| Window | Action | Status |
| --- | --- | --- |
## Reply Bank
- Thank-you reply:
- Technical reply:
- Client-value reply:
- Quiet-engagement follow-up:Output Format
Return:
- Campaign recommendation.
- Platform copy.
- Asset order and alt text.
- Tracker or proof-trail updates made.
- Follow-up actions and timing.
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.

