liam-weekly

liam-weekly is a skill for Claude Code, Codex from stan-rym/liam-linkedin-ads-MCP. It costs 80 tokens per session (726 once invoked), scanned A, original, MIT.

A weekly summary of LinkedIn advertising results, comparing the last seven full days with the seven days before them. It highlights major changes, new ads, warnings, and up to three suggested actions.

In plain words
What is it for?
Use it for weekly ad snapshots, Monday updates, scheduled reports, or recurring checks of how LinkedIn ads performed.
Why use it?
It gives each week the same short format, making changes easier to spot without reading a long report. It also connects performance changes with ads or campaigns added or changed that week.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Claude Code.

Good fit Use it for weekly ad snapshots, Monday updates, scheduled reports, or recurring checks of how LinkedIn ads performed.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/stan-rym/liam-linkedin-ads-mcp/liam-weekly
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add stan-rym/liam-linkedin-ads-MCP --skill liam-weekly
Clone the repo
git clone --depth 1 https://github.com/stan-rym/liam-linkedin-ads-MCP

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for liam-weekly

README.md
[![agentmods](https://agentmods.dev/badge/skills/stan-rym/liam-linkedin-ads-mcp/liam-weekly/github.svg)](https://agentmods.dev/skills/stan-rym/liam-linkedin-ads-mcp/liam-weekly)
Your own site
<a href="https://agentmods.dev/skills/stan-rym/liam-linkedin-ads-mcp/liam-weekly"><img src="https://agentmods.dev/badge/skills/stan-rym/liam-linkedin-ads-mcp/liam-weekly/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for liam-weekly

Your own site · 80×15
<a href="https://agentmods.dev/skills/stan-rym/liam-linkedin-ads-mcp/liam-weekly"><img src="https://agentmods.dev/badge/skills/stan-rym/liam-linkedin-ads-mcp/liam-weekly.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 80 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 726 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00080 $0.00726
Opus 5.5 $0.00032 $0.00290
Sonnet 5.5 $0.00016 $0.00145
Haiku 4.5 $0.00008 $0.00073

Measured 2mo ago against content hash 7d66c0f3461e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

liam-weekly scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/liam-weekly/SKILL.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Liam: weekly snapshot

A snapshot, not a report. The same shape every week so weeks are comparable at a glance, short enough to read in a Slack message. Target under 40 lines of output.

How to reach Liam

Prefer the liam MCP tools if they are loaded. This skill wants two exact 7-day windows, so use get_performance with explicit startDate/endDate (YYYY-MM-DD): the last 7 full days, and the 7 before those. On the CLI, liam report summary -p last_7_days plus liam report trend <level> <id> -b weekly approximates it. Also pull list_campaigns (structure and statuses), list_ads on active campaigns if ad-level movers are wanted, and list_ad_changes for what was changed this week. Read-only.

What goes in

  1. Scoreboard: spend, impressions, CTR, conversions, cost per conversion for this week, each with the week-over-week delta.
  2. Movers: entities whose CTR, spend, or cost per conversion moved more than ~20% week over week, on at least ~1,000 impressions in both weeks. Cap at 3 up, 3 down.
  3. New this week: ads or campaigns that appeared (from list_campaigns / list_ads), and journaled changes (list_ad_changes) so the reader connects moves to outcomes.
  4. Flags: ACTIVE campaigns with zero delivery, audiences still matching or under 300 members, creatives with CTR down two-plus weeks running, conversion counts likely still lagging for the last 2 days.
  5. Do this week: at most 3 actions, imperative, each tied to a number above.

Rules

  • Same section order every week; never add sections ad hoc.
  • Deltas as signed percentages; money in account currency.
  • No verdicts on entities below the volume floor; skip them silently here (the deep dives are liam-performance and liam-leads, and the snapshot should say so only when something big warrants it).
  • If the week was quiet, say it in one line and keep the snapshot short rather than inflating noise into findings.

Report format

LinkedIn ads, <start> to <end>
Spend $X (+Y%) | Leads N (+Y%) | CPL $X (+Y%) | CTR X% (+Y%)

Up: ...
Down: ...
New: ...
Flags: ...

Do this week:
1. ...

Read the full file on GitHub · 66 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2mo ago First seen · 66 lines · 80 tokens per session scan A 7d66c0f3461e

Subscribe to this mod's changes

liam-weekly is a skill published in the GitHub repository stan-rym/liam-linkedin-ads-MCP (23 stars, last pushed 2mo ago), licensed MIT. It adds 80 tokens to every session and 726 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

liam-weekly compared with skills from other repositories

liam-weekly next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
liam-weeklystan-rym/liam-linkedin-ads-MCPSkill232mo agoMITA80Claude Code, Codex
imagegenopenai/codexSkill136ktodayApache-2.0A113Codex
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill80kyesterdayMITA200Claude Code, Codex
playwright-climicrosoft/playwrightSkill101ktodayApache-2.0A19Claude Code
browser-automationopenclaw/openclawSkill395ktodayMITA36Claude Code
free-llm-apismnfst/awesome-free-llm-apisSkill14ktodayCC0-1.0A113Claude Code, Codex
next-cache-components-adoptionvercel/next.jsSkill144kyesterdayMITA95Claude Code