agentleFS
carlosbuelvas1carlosbuelvas1/openclaw-skills/swipefile-compiler/SKILL.md

swipefile-compiler

Skill0 starsChanged 6 months agoMITView on GitHub

Compile tracked creator signals, content patterns, and distribution tactics into one structured weekly swipefile for reuse. Use when the operator wants a consolidated reference of hooks, CTAs, formats, and tactics observed across recent signal tracking.

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 8 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈8

    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:

    When asked to "compile the swipefile", "summarize creator signals", or "what patterns are we tracking?"

    line 13
  2. Distinctive:

    Before content planning sessions to ground packaging decisions in observed data.

    line 14
  3. Distinctive:

    Does not fetch new URLs or external content.

    line 25
  4. Distinctive:

    Does not generate new content — only compiles and classifies observed signals.

    line 26
  5. Distinctive:

    Does not publish or distribute the swipefile.

    line 27
  6. Distinctive:

    Does not overlap with x-link-best-effort (no fetch logic here).

    line 28
  7. Distinctive:

    If memory logs are sparse (<5 signal entries), report "insufficient signals for compilation" rather than padding.

    line 66
  8. Distinctive:

    If a signal entry has no clear hook or CTA, classify as "insight" rather than forcing a category.

    line 67

≈ “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

Swipefile Compiler

Reads recent signal tracking notes and memory logs, then produces one structured swipefile artifact summarizing patterns, hooks, CTA types, and reuse notes.

When to Use

  • Weekly or on-demand signal synthesis.
  • When asked to "compile the swipefile", "summarize creator signals", or "what patterns are we tracking?"
  • Before content planning sessions to ground packaging decisions in observed data.

What This Skill Does

  1. Reads the most recent memory logs from ~/.openclaw/workspace/memory/ (last 7 days).
  2. Extracts: hooks, CTAs, format patterns, platform tactics, and recurring themes.
  3. Classifies each item by category (hook, CTA, format, tactic, insight).
  4. Outputs one structured markdown file with pattern counts and reuse notes.

What This Skill Does NOT Do

  • Does not fetch new URLs or external content.
  • Does not generate new content — only compiles and classifies observed signals.
  • Does not publish or distribute the swipefile.
  • Does not overlap with x-link-best-effort (no fetch logic here).

Output Format

# Weekly Swipefile — [date range]

## Summary
[X] signals compiled. [Y] unique patterns identified.

## Hooks (top 10)
1. [hook text] — source: [date], pattern: [curiosity | contrarian | data-shock | story]
...

## CTA Types
- [CTA pattern]: [frequency], [example]
...

## Format Patterns
- [format]: [platform], [notes]
...

## Reuse Notes
- [Which patterns to apply to current content pipeline items]
- [Which hooks to test next]

Save to: ~/.openclaw/workspace/mission-control/operations/swipefile-[date].md

Acceptance Test

  • Given the last 3 days of memory logs contain at least 10 tracked signal entries with hooks and CTAs.
  • When the skill is invoked.
  • Then the output file contains categorized hooks, CTA types, format patterns, and at least 3 reuse notes.
  • Pass: file saved, all 4 categories present, no uncategorized items >20%.

Edge Cases

  • If memory logs are sparse (<5 signal entries), report "insufficient signals for compilation" rather than padding.
  • If a signal entry has no clear hook or CTA, classify as "insight" rather than forcing a category.
  • Skip memory entries that are purely operational (system logs, build notes) — only extract content/distribution signals.

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.