agentleFS
aryaminusaryaminus/socials-assistant/skills/weekly-digest/SKILL.md

weekly-digest

Skill0 starsChanged 3 months agoMITView on GitHub

Generates a cross-platform weekly analytics digest (TikTok, Instagram, Facebook, YouTube) from real vault data with wins, losses, and next actions. Use when the user asks for a digest, weekly report, scorecard, performance summary, "how did I do this week", or what to do next with their content.

6 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use session-search.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • KISHOR403Skill

    session-search

    This skill should be used when searching Claude Code session transcripts with semantic understanding. Triggers on queries like "find sessions about X", "when did I work on Y", "search previous conversations". Supports natural language queries with synonym matching.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 1 is distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 5 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Call socials-mcp:profile_get (cheap) — niche and goals frame the "do next week" actions.

    line 13
  2. Very specific:

    Call socials-mcp:digest_data with days: 7.

    line 14
  3. Very specific:

    Call socials-mcp:top_content (days: 14, limit 10) and socials-mcp:audience_overview for color.

    line 15
  4. Distinctive:

    Keep the whole digest under ~400 words.

    line 50

“Common” is measured: kept by at least 6 in 10 of the 5 edited versions of this file we could read. “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

weekly-digest — cross-platform scorecard

Reads ONLY real vault data via socials-mcp tools. Never invent or estimate numbers. If data is missing, say what's missing and suggest socials-mcp:snapshot / socials-mcp:import_tiktok_csv.

Steps

  1. Call socials-mcp:profile_get (cheap) — niche and goals frame the "do next week" actions; skip silently if empty.
  2. Call socials-mcp:digest_data with days: 7. Add socials-mcp:compare_periods for metrics the user cares about (views, followers_gained, reach).
  3. Call socials-mcp:top_content (days: 14, limit 10) and socials-mcp:audience_overview for color.
  4. Compose the digest:
## 📊 Week {week} — {start} → {end}

### Headline
One sentence: the single most important change (biggest % move, or best/worst content).

### Per platform
- **TikTok** — views {cur} ({+/-x%}), followers gained {n}, top video: "{title}" ({views} views)
- **YouTube** — views {…}, watch time {…}, traffic-mix shifts (if present)
- **Instagram** — reach {…}, top reel: "{title}" ({views} plays)
- **Facebook** — impressions {…}
Include only platforms that returned data. Never pad missing metrics with zeros.

### What worked / what died
- Best content (title, platform, views, engagement rate) + the *why* when retention/traffic data exists (e.g. "held 70% at 3s — strong hook")
- Flop content — same, plus one concrete hypothesis (hook too slow? off-niche? posting time?)

### Audience notes
Top country/age splits that changed vs prior week (if available).

### Do next week
2–3 specific, data-backed actions tied to numbers above.
  1. Offer follow-ups: save to digests/, email it (self only), or hand targets to the brand-outreach skill.

Interpretation rules

  • changePct: null means no prior baseline — say "no baseline yet"; never compute one.
  • Engagement rate = (likes+comments+shares)/views. Benchmark context lives in references/benchmarks.md — read it when comparing rates.
  • Viral outliers distort averages: call them out explicitly instead of averaging them away.
  • TikTok retention/traffic exist only if CSVs were imported; if absent, remind about the weekly export → import_tiktok_csv.
  • Keep the whole digest under ~400 words; link or offer detail rather than dumping tables.

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.