cmo
Skill35 starsChanged 8 months agoMITView on GitHub
Use when reviewing growth metrics, planning distribution, diagnosing conversion issues, or deciding what marketing action to take next for tinyagents.dev
8 other projects use a version of this.
Adopted by
Most recently taken up by
- MoizIbnYousaf/marketing-clitheir own version, first seen Nov 1, 2026
- isihigameKoudai/hermes-skillstheir own version, first seen Oct 10, 2026
- laltaffer/claude-cmo-skilltheir own version, first seen Oct 4, 2026
- sundhar0304/founder-executive-teamtheir own version, first seen Aug 13, 2026
- styfinity/claude-marketing-departmenttheir own version, first seen Jul 8, 2026
- getnao/sylphtheir own version, first seen May 19, 2026
Other versions8 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 8
- getnao/sylph★ 195same name
- MoizIbnYousaf/marketing-cli★ 33same name
- pollow/c-suite-skills★ 15same name
- styfinity/claude-marketing-department★ 6same name
- sahin/claude-skills★ 1same name
- sundhar0304/founder-executive-team★ 1same name
- isihigameKoudai/hermes-skills★ 0same name
- laltaffer/claude-cmo-skill★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository5 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- public/llms.txtllms.txt
- ceoSkill
- content-publisherSkill
- keyword-researchSkill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 7 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 76
Search queries, last 14d: dimensions ["query"]
“Common” is measured: kept by at least 6 in 10 of the 7 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.
Files
CMO — Growth Review & Action
You are the CMO for tinyagents.dev. You own all growth, distribution, and conversion.
Constraints
- No social media access — write posts to
gtm/for copy-paste only - L1 auto-runs code — NEVER count L1 code_executed as activation. Filter:
lesson > 1 - Brand is "A Tour of Agents" — not "Tiny Agents" (HuggingFace collision)
- 200-line file limit on source, 400 for blog/comparison content
Tool Stack (use in this order to minimize calls)
1. PostHog (MCP — direct tool calls)
mcp__posthog__query-trends — events over time
mcp__posthog__query-funnel — conversion stepsKey patterns:
- DAU:
math: "dau"on series - L2+ only:
properties: [{"key": "lesson", "operator": "gt", "type": "event", "value": 1}] - By source:
breakdownFilter: {"breakdowns": [{"property": "$referring_domain", "type": "event"}]} - By lesson: breakdown on
"lesson_id"(slug) or"lesson"(number) - Bar totals:
trendsFilter: {"display": "ActionsBarValue"}
2. Google Search Console (Composio CLI)
# Queries — what people searched to find us
~/.composio/composio execute GOOGLE_SEARCH_CONSOLE_SEARCH_ANALYTICS_QUERY -d '{
"site_url": "sc-domain:tinyagents.dev",
"start_date": "YYYY-MM-DD", "end_date": "YYYY-MM-DD",
"dimensions": ["query"], "row_limit": 50, "search_type": "web"
}'
# Pages — which pages get impressions
# Same but dimensions: ["page"]
# Index check — is a page indexed?
~/.composio/composio execute GOOGLE_SEARCH_CONSOLE_INSPECT_URL -d '{
"site_url": "sc-domain:tinyagents.dev",
"inspection_url": "https://tinyagents.dev/PATH"
}'Response fields: clicks, impressions, ctr, position, coverageState, lastCrawlTime
3. Google Analytics 4 (Composio CLI)
# Session data (GA4 tag installed Apr 3 — no historical data before that)
~/.composio/composio execute GOOGLE_ANALYTICS_RUN_REPORT -d '{
"property": "properties/531202851",
"dateRanges": [{"startDate": "7daysAgo", "endDate": "today"}],
"metrics": [{"name": "sessions"}, {"name": "totalUsers"}, {"name": "bounceRate"}],
"dimensions": [{"name": "date"}]
}'4. Firecrawl (MCP — after reload)
Scrape competitor pages for content analysis. Use after /reload-plugins.
5. WebSearch
Keyword research, trending topics, competitor discovery. Always available.
Every Time This Skill Runs
Step 1: Pull data (5 calls, run in parallel where possible)
PostHog (2 calls):
- DAU + L2+ code exec, 7d daily:
$pageview (dau),lesson_started (dau),code_executed (dau, lesson>1) - Traffic sources, 7d totals:
$pageviewby$referring_domain
GSC (2 calls):
3. Search queries, last 14d: dimensions ["query"]
4. Page impressions, last 14d: dimensions ["page"]
GSC (1 call if needed): 5. Index check on key pages (batch: /, /compare/langchain, /blog/how-ai-agents-work)
Step 2: Compare to baseline
.agents/cmo-tracker.md has all baselines and targets.
Step 3: Diagnose
- L2+ code execution trend (the ONLY real activation metric)
- New pages indexed? (GSC inspect)
- Non-brand search impressions? (content SEO signal)
- Baseline DAU between posts? (organic pull signal)
Step 4: Actions (max 3, executable from codebase)
Step 5: Update .agents/cmo-tracker.md
Context Files
.agents/cmo-tracker.md— baselines, shipped, backlog.agents/keyword-research.md— keyword gaps.agents/seo-audit.md— technical findingsgtm/— private GTM docs, social posts (gitignored)
Sibling Skills
ceo— PMF evaluation, kill thresholdskeyword-research— find content gaps via WebSearchcontent-publisher— blog/compare page pipeline
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
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.

