Lumen Metrics

What it does

When your agent uses it

• Asked to design a metrics framework
• What should we measure
• Build a metrics system
• Define our KPIs

Example prompts

• “design a metrics framework”
• “what should we measure”
• “build a metrics system”
• “/lumen-metrics”

Requirements

• Pre-approved tools (allowed-tools): Read, Write, Edit, Bash, Glob, Grep, WebFetch, WebSearch, Task, TodoWrite, AskUserQuestion

Workflow steps

6 steps, taken from the step headings in SKILL.md.

1. 1Define the North Star Metric
2. 2Build the Input Metrics Tree
3. 3Instrumentation Spec
4. 4Action Triggers
5. 5Counter-Metrics
6. 6Stage-Appropriate Scope

What it can do on your machine

Read from SKILL.md and the folder at commit cfae287. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Read
  • Write
  • Edit
  • Bash
  • Glob
  • Grep
  • WebFetch
  • WebSearch
  • Task
  • TodoWrite

  …and 1 more on the same allowed-tools line.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md.

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Lumen Metrics loads about 2.4k tokens when it runs. Until then it costs about 96 tokens; SKILL.md has 703 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~96

When it runs · the whole SKILL.md, loaded when a task matches

~2.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

• NotePre-approves every shell command (allowed-tools: Bash)SKILL.md

  allowed-tools: Read, Write, Edit, Bash, Glob, Grep, WebFetch, WebSearch, Task, TodoWrite, AskUserQuestion

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from jeremylongshore/tons-of-skills-marketplace at commit cfae287, republished under its MIT licence (© jeremylongshore). 703 words, ~2,398 tokens.

name

lumen-metrics

description

Metrics architecture — produce a complete metrics plan given a product description. North Star, input metrics tree, instrumentation spec, action triggers, and counter-metrics. Use when asked to "design a metrics framework", "what should we measure", "build a metrics system", "define our KPIs", "what are our success metrics", "metrics strategy", or "what do we track".

allowed-tools

Read, Write, Edit, Bash, Glob, Grep, WebFetch, WebSearch, Task, TodoWrite, AskUserQuestion

version

0.6.4

author

tonone-ai <hello@tonone.ai>

license

MIT

NORTH STAR: [metric] — [definition]
│
├── ACQUISITION
│     Metric:  [e.g., qualified signups per week — signups who complete step 1 of onboarding]
│     Owner:   [Growth / Marketing]
│     Lever:   [landing page conversion, channel mix, referral program]
│     Tracked: [yes / no — needs instrumentation]
│
├── ACTIVATION
│     Metric:  [e.g., % new users who reach first value moment within session 1]
│     Owner:   [Product]
│     Lever:   [onboarding flow, time-to-value, empty state design]
│     Tracked: [yes / no]
│
├── RETENTION
│     Metric:  [e.g., D7 return rate by signup cohort / weekly habit rate]
│     Owner:   [Product]
│     Lever:   [habit loop, re-engagement triggers, notification strategy]
│     Tracked: [yes / no]
│
├── REVENUE (if applicable)
│     Metric:  [e.g., free-to-paid conversion rate / MRR expansion rate]
│     Owner:   [Product / Sales]
│     Lever:   [paywall placement, upgrade triggers, trial experience]
│     Tracked: [yes / no]
│
└── REFERRAL / EXPANSION (if applicable)
      Metric:  [e.g., % users who invite ≥1 other user within 14 days]
      Owner:   [Product]
      Lever:   [invite mechanic, sharing surfaces, viral loops]
      Tracked: [yes / no]

┌─────────────────────────────────────────────────────┐
│  METRICS ARCHITECTURE — [Product Name]              │
│  Stage: [Pre-PMF / Post-PMF / Scaling]              │
└─────────────────────────────────────────────────────┘

NORTH STAR
  [Metric] — [definition] — reviewed [cadence]

INPUT METRICS TREE
  Funnel Stage   Metric                    Owner      Tracked
  ──────────────────────────────────────────────────────────
  Acquisition    [metric]                  [owner]    [✓/✗]
  Activation     [metric]                  [owner]    [✓/✗]
  Retention      [metric]                  [owner]    [✓/✗]
  Revenue        [metric]                  [owner]    [✓/✗]

INSTRUMENTATION GAPS
  ✗ [metric] — needs [event name] fired at [trigger point]
  ✗ [metric] — needs [event name] fired at [trigger point]
  → Hand off to [Spine / Flux] with this spec

ACTION TRIGGERS
  [metric] below [threshold] → [specific action]
  [metric] below [threshold] → [specific action]

COUNTER-METRICS
  [optimized metric] → guarded by [counter-metric]

FIRST 30 DAYS
  Week 1–2: Verify instrumentation is firing correctly. Establish baselines.
  Week 3–4: First cohort retention read (D7). First activation rate read.
  Decision point: If activation rate <20%, stop all other optimization — fix onboarding first.

© jeremylongshore, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in plugins/ai-agency/tonone/skills/lumen-metrics of jeremylongshore/tons-of-skills-marketplace.

• SKILL.md
• .claude-plugin/plugin.json

Open the folder on GitHubat commit cfae287