agentleFS
MattSezginMattSezgin/unofficial-smartlead-cli/.claude/skills/weekly-report/SKILL.md

weekly-report

Skill8 starsChanged 6 months agoMITView on GitHub

Generate a weekly performance summary across all active Smartlead campaigns — sends, opens, replies, positive replies, bounce rates, top performers, mailbox health flags. Use when the user asks for a weekly recap, performance summary, status report, end-of-week wrap-up, or "how did we do this week".

51 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use agency-clients, cross-post-video and 10 more.

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.
  • posteverywhereSkill

    agency-clients

    Work safely across several clients or brands in PostEverywhere. Use when the user manages social media for more than one client, brand or business, mentions a client by name, asks to switch clients, or when the connected accounts belong to different companies.

    Also in 4 projects that use this

  • posteverywhereSkill

    cross-post-video

    Post one video to several platforms with PostEverywhere, with the right title and caption for each. Use when the user wants to share a video, Reel, Short or TikTok across TikTok, Instagram Reels, YouTube Shorts, LinkedIn and Facebook Reels, or asks to "post this video everywhere".

    Also in 4 projects that use this

  • CodeWithSulemanSkill

    approval-workflow

    Manage human-in-the-loop approval workflows for sensitive actions like payments, emails to new contacts, social media posts, and other actions requiring human oversight.

    Also in 4 projects that use this

  • flintfromthebasementSkill

    write-blog-post

    Write or edit a long-form blog post in a specific author's voice, then run it through six editorial passes (substance, structure, human voice, de-AI scrub, house style + O'Reilly word list, fresh-context critic) before delivering. Handles drafting from a brief, filling an outline, editing a draft, refreshing an old post, and applying revision notes. Use when the user wants a blog post that sounds like a real person wrote it, not a one-shot generation.

    Also in 4 projects that use this

  • +8 more from posteverywhere

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 27 edited versions we read keep these.

  • 2

    Distinctive

    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:

    If the user specified a client:

    line 23
  2. Distinctive:

    If Big Tech (google.com, meta.com, microsoft.com, figma.com, etc.) dominates the bounce list, flag it:

    line 101

“Common” is measured: kept by at least 6 in 10 of the 27 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

Before running: verify exact flag names with smartlead <command> --help. Flag shapes shown below are illustrative — confirm against the actual CLI.

/weekly-report

You're producing a weekly performance digest for the user.

What you need from the user

  • Scope — all campaigns, or a specific client?
  • Time window — default: last 7 days ending today

Step 1 — Pull active campaigns

smartlead campaigns list --status ACTIVE --output json > active.json

If the user specified a client:

smartlead campaigns list --status ACTIVE --client-id <id> --output json > active.json

Step 2 — Pull per-campaign analytics

jq -r '.[] | .id' active.json | while read cid; do
  smartlead campaigns analytics $cid --since "$(date -v-7d +%Y-%m-%d)" --output json
done > analytics.json

Step 3 — Pull mailbox-level health

smartlead analytics email-wise-health --output json --since "$(date -v-7d +%Y-%m-%d)" > mailbox-health.json

Step 4 — Compute headline metrics

TOTALS (last 7 days)
─────────────────────────────────
Sends:           12,847
Delivered:       12,231 (95.2%)
Opens:           3,891 (31.8%, take with grain of salt post Apple MPP)
Replies:         287 (2.34%)
Positive reps:   58 (0.47% of sends, 20.2% of replies)
Bounces:         616 (4.8%)
Out of office:   42 (handled automatically)

Flag concerning numbers in red:

  • Bounce rate >5% → 🔴
  • Reply rate <1% → 🟡 (copy issue, not infra)
  • Positive reply rate <0.2% → 🟡 (targeting or copy)

Step 5 — Top + bottom performing campaigns

TOP 3 CAMPAIGNS BY POSITIVE REPLY RATE
─────────────────────────────────
1. Q1 Founders Outbound          0.93%  (12 / 1287)
2. SaaS Mid-Market V2            0.71%  (8 / 1126)
3. Industry Event Follow-up      0.68%  (5 / 740)

BOTTOM 3 (consider pausing or reworking)
─────────────────────────────────
1. Cold List 2024                0.04%  (1 / 2400)  🔴 1% bounce rate is 8.2% — pause
2. Big Tech Push                 0.12%  (3 / 2500)  🟡 Bounces high (12%)
3. Q4 Recap                      0.18%  (2 / 1100)

Step 6 — Mailbox health flags

MAILBOX FLAGS
─────────────────────────────────
🔴 3 mailboxes bouncing >10%:
   - sender12@example.com (16% bounce)  → likely DKIM issue, /spam-test
   - sender07@example.com (12% bounce)  → check reputation
   - sender19@example.com (11% bounce)  → check IP blacklist

🟡 5 mailboxes with low reply rate (<0.5%):
   (less urgent — could be audience-specific)

✅ 142 mailboxes healthy

Step 7 — Bounces by recipient ESP (catches Big Tech issues)

jq -r '.[] | select(.bounced) | .email' analytics.json | \
  awk -F@ '{print $2}' | sort | uniq -c | sort -rn | head -10

If Big Tech (google.com, meta.com, microsoft.com, figma.com, etc.) dominates the bounce list, flag it:

⚠ BIG TECH BOUNCE CONCENTRATION
─────────────────────────────────
   78 @google.com  (28% of all bounces)
   34 @meta.com    (12%)
   29 @microsoft.com (10%)

These bounce ~2x the rest of your list. Likely email-finder catch-all guesses
(see docs/learnings/esp-matching-analysis.md).
Recommend: drop @google.com guesses, use verified-only email providers.

Step 8 — Action items

End the report with 3-5 specific next steps:

ACTIONS FOR NEXT WEEK
─────────────────────────────────
1. Pause "Cold List 2024" — bounce rate is killing sender reputation
2. /spam-test on the 3 bouncing mailboxes above
3. Re-enrich Big Tech leads with verified-only provider
4. /clone-campaign top performer for Q2 audience

Output format

By default, render as text in chat. If the user wants a file:

# Save as Markdown report
smartlead-cli-report > weekly-2026-W21.md

Or as a Notion page (if they have the Notion CLI):

notion page create "Weekly Report 2026-W21" --content @weekly-2026-W21.md

Reference

  • docs/learnings/esp-matching-analysis.md — Big Tech bounce patterns
  • docs/learnings/mailbox-warmup-best-practices.md — what healthy looks like

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.