Skip to content
WireLog WireLog

Claude Code Skills

View as markdown

SKILL.md files teach coding agents domain-specific capabilities. The agent reads the file on activation and gains knowledge of the WireLog DSL, instrumentation patterns, or project setup — no tool registration, no API integration.

GitHub: github.com/wirelogai/wirelog-skills

Available skills

wirelog (query)

Teaches the agent the full pipe DSL: sources, stages, fields, identity semantics, and the discovery-first workflow. After activation, the agent can write WireLog queries, explain results, and iterate on analysis.

Covers:

  • All source types (*, event names, funnel, retention, paths, sessions, user, users, formula)
  • All stages (where, last, from/to, count, unique, sum, avg, list, sort, limit, top, by)
  • All fields (event_type, distinct_id, event_properties.KEY, user.KEY, system fields)
  • Special-character event sources (landing:cta_click, docs.view, checkout/success) and quoted source syntax
  • where in list literals in both forms: in (...) and in [...]
  • Identity stitching (distinct_id = coalesce(user_id, mapped_user_id, device_id))
  • Discovery-first workflow (always run * | last 30d | count by event_type | top 20 before writing event-specific queries)

If the project is script-tag-only, the skill also includes page-view-first starter queries:

page_view | last 7d | count by day
page_view | last 7d | unique distinct_id by day
page_view | last 30d | count by _path | top 20
page_view | where _path in ["/","/pricing","/docs"] | last 7d | count
paths from page_view | last 30d | by _path
sessions | last 30d | count by session.utm_source
retention page_view | last 90d

wirelog-instrument

Teaches the agent how to add event tracking and user identification to code. Covers the HTTP API, Script Tag, TypeScript client, Python client, and Go client.

Covers:

  • API key types (pk_, sk_, aat_) and where each is safe to use
  • POST /track — single events and batch
  • POST /identify — device binding, profile ops ($set, $set_once, $add, $unset)
  • Script Tag setup (<script> tag, wl.track(), wl.identify())
  • Server-side examples (curl, Python stdlib, Node.js fetch, Go)
  • Recommended profile fields for B2B and B2C

wirelog-setup

Teaches the agent how to set up a new WireLog project from scratch: sign up, create a project, get API keys, send a test event, verify with a query, and configure identity.

Install via Claude Code

Terminal window
/install-skill github.com/wirelogai/wirelog-skills

This installs all three skills. The agent activates the relevant skill based on context.

Manual install

Copy the SKILL.md files to your project’s skills/ directory:

skills/
  wirelog/SKILL.md
  wirelog-instrument/SKILL.md
  wirelog-setup/SKILL.md

The agent picks up skills from the skills/ directory automatically.

How it works

  1. The agent encounters a task related to analytics (querying data, adding tracking, setting up a project).
  2. The agent reads the relevant SKILL.md file.
  3. The skill provides complete domain knowledge: syntax, API endpoints, examples, and best practices.
  4. The agent writes queries, instruments code, or sets up projects using the skill’s guidance.

No runtime dependency. No API keys in the skill. The skill is pure knowledge — the agent uses it with whatever API key the user provides.

Example: agent writes a query using the wirelog skill

User: "What are the top events this week?"


Agent reads: skills/wirelog/SKILL.md
Agent runs:
  curl -X POST https://api.wirelog.ai/query \
    -H "X-API-Key: sk_..." \
    -H "Content-Type: application/json" \
    -d '{"q": "* | last 7d | count by event_type | top 10"}'


Agent returns the Markdown table to the user.

Next steps