deploy-telemetry
Set up analytics and tracking infrastructure for growth loops. Use when the user says "deploy telemetry", "set up analytics", "tracking", "events", "push to supabase", or "skene push".
pinned to #e2173a9updated 2 weeks ago
Ask your AI client: “install skills/deploy-telemetry”.
Requires the metahub MCP server installed in your client. Set up MCP.
mh install skills/deploy-telemetrymetahub onboarded this repo on the author's behalf.
If you own github.com/SkeneTechnologies/skene on GitHub, claim the listing to take over publishing. Your claim preserves the existing eval history and badges; only the curator label is replaced with verified-publisher on your next publish.
Stars
120
Last commit
2 weeks ago
Latest release
published
- #ai-tools
- #anthropic
- #automation
- #cli
- #cli-tool
- #code-documentation
- #codebase-analysis
- #developer-tools
- #gemini
- #growth-hacking
- #llm
- #mcp
- #mcp-server
- #openai
- #plg
- #product-led-growth
- #pydantic
- #python
- #python3
- #tech-stack-detection
About this skill
Pulled from SKILL.md at publish time.
Set up analytics infrastructure via the Skene CLI.
Evaluation report
WarningsAutomated checks the publisher passed at publish time — structure, docs, safety, and whether the artifact behaves as claimed.e2173a9· 2 weeks ago
Kind-specific
31Skill: SKILL.md present
found at cursor-plugin/skills/deploy-telemetry/SKILL.md · frontmatter source: SKILL.md
Skill: body content present
352 words · 2,533 chars · 4 sections
Skill: triggers declaredwarn
No `trigger` phrases in SKILL.md frontmatter
Add `trigger:` lines so Claude knows when to activate this skill — e.g. `when building MCP servers` or `for diagram creation`.
Skill: allowed-tools scope
no allowed-tools restriction (Claude may use anything)
Release history
1- releasecurrente2173a9warn2 weeks ago
Contents
Set up analytics infrastructure via the Skene CLI.
Agent behavior rules
- Autonomous. Run CLI commands, report results, suggest next step. No mid-flow questions except for genuine blockers.
- CLI is the source of truth. Do NOT fabricate migration schemas or client code if the CLI fails.
- User cannot type into agent terminals. Pipe safe defaults for routine prompts. Kill stuck terminals.
- Upstream push can be a genuine blocker. Ask the user in chat to confirm before running
uvx skene push— it POSTsskene-context/engine.yaml,{output_dir}/feature-registry.jsonwhen present, and the latest trigger migration to Skene Cloud (it does not generate SQL; runuvx skene buildfirst if artifacts are missing).
Steps
-
Discover CLI options Run
uvx skene push --helpto see available flags. Use only flags that appear in the output. -
Verify prerequisites
skene-context/engine.yamlmust exist; trigger SQL lives undersupabase/migrations/as*_skene_triggers.sqlafteruvx skene build(older projects may use legacy*skene_trigger*/*skene_telemetry*filenames).- Feature registry: default
skene-context/feature-registry.json(or{output_dir}from config; legacyskene/feature-registry.jsonauto-detected). If missing, push still runs but omits the registry untilbuildcreates it. - If engine or migrations are missing: tell the user to run
uvx skene buildfirst, then retry deploy. ls supabase/ 2>/dev/null— if missing: "No Supabase directory. Set up Supabase first."
-
Ask user to confirm Tell the user: "
uvx skene pushuploads engine, feature-registry.json (if present), and latest*_skene_triggers.sqlto upstream. Proceed?" Wait for confirmation. -
Run push After user confirms, run
uvx skene pushwith appropriate flags from --help output. Report which migration file was packaged (latest eligible undersupabase/migrations/) and that upstream received the deploy. -
Report result Engine path, registry path (if packaged), trigger migration path, next step: apply DB migrations locally if needed (
supabase db push), then "Run/skene-statusto verify." -
Privacy reminder (one line) "Remember GDPR/CCPA consent management before production tracking."
Error handling
- CLI failure: Report error, suggest fix.
- Permission errors: Give user the command for their terminal.
Output
Deploy result (or error), paths used, next step (/skene-status).
Reviews
No reviews yet. Be the first.
Related
Gpt Researcher
An autonomous agent that conducts deep research on any data using any LLM providers
Browser Use
🌐 Make websites accessible for AI agents. Automate tasks online with ease.
Frontend Slides
Create beautiful slides on the web using Claude's frontend skills
mh install skills/deploy-telemetry