agentleFS
jqaisystemsjqaisystems/jqai-ai-skills/skills/social-campaign-proof-tracker/SKILL.md

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.

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
  1. Distinctive:

    Use this skill to turn a project update into a public proof campaign with platform-specific copy, visual order, alt text, links, reply …

    line 10
  2. Distinctive:

    Add accessibility and context:

    line 37
  3. Distinctive:

    Create or update a local tracker:

    line 42
  4. Distinctive:

    After publishing, record only public results unless the user explicitly provides private metrics for private analysis.

    line 50
  5. Distinctive:

    Do not include private analytics exports, cookies, account IDs, unpublished client data, raw messages, private prompts, local paths, or …

    line 54
  6. Distinctive:

    Do not invent engagement results.

    line 55
  7. Distinctive:

    Do not imply client permission or measurable outcomes unless the user confirms them.

    line 56
  8. Distinctive:

    Keep reply banks human-reviewed and non-spammy.

    line 57
  9. Distinctive:

    Treat low comments as normal signal, not failure.

    line 58
  10. Distinctive:

    Use concrete nouns: system, workflow, profile, proof layer, demo, skill, release.

    line 63
  11. Distinctive:

    Avoid vague hype such as "game-changing" unless the user asks for a louder tone.

    line 64
  12. Distinctive:

    Keep CTAs light: "I am building this in public", "open to feedback", "details on GitHub", or "happy to share the workflow".

    line 65
  13. Distinctive:

    Use this structure by default:

    line 70
  14. Distinctive:

    Follow-up actions and timing.

    line 111

≈ “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.

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

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

  1. Identify the proof object:
    • GitHub update
    • demo
    • video
    • website page
    • case study
    • skill release
    • automation milestone
  2. Gather only public-safe inputs:
    • public links
    • approved images or videos
    • short outcome summary
    • safe implementation categories
    • approved calls to action
  3. 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
  4. Draft platform copy.
    • LinkedIn: clearer context, stronger hook, more reflective tone.
    • X: short lines, one idea per post, direct links.
  5. Add accessibility and context:
    • alt text for each image
    • caption for video if needed
    • link labels
    • comment/reply prompts
  6. Create or update a local tracker:
    • campaign name
    • date
    • asset list
    • published links
    • follow-up windows
    • engagement notes
    • useful replies
  7. 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:

  1. Campaign recommendation.
  2. Platform copy.
  3. Asset order and alt text.
  4. Tracker or proof-trail updates made.
  5. Follow-up actions and timing.

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.