Telemetry Coverage Audit

Organization

zero-lab-ai

telemetry-coverage-audit

Audits supplied sanitized passive telemetry evidence for policy-defined visibility, retention, custody, and investigation readiness. Use when reviewing evidence quality or profile-specific telemetry usability without contacting sources or claiming detection coverage.

Overview

Publisher	zero-lab-ai
Repository	`skills`
Skill name	`telemetry-coverage-audit`
Stars	232
Forks	14
Bundled files	2
License	Apache-2.0
Links	Skill source Repository Homepage

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
2 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by zero-lab-ai on GitHub. Read the source before you install it.

Installation

Install the Telemetry Coverage Audit AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/zero-lab-ai/skills/tree/main/plugins/detection-validation/skills/telemetry-coverage-audit
Enable the skill in any chat where you want it available.

Store

Installed

Skills

Add skills

Import one or more skills from a public GitHub folder or a local .skill or .zip archive, or SKILL.md file.

From GitHub URLFrom .skill, .zip, or SKILL.md

GitHub repo or folder

https://github.com/zero-lab-ai/skills/tree/main/plugins/detection-validation/skills/telemetry-coverage-audit

Points to a single skill folder, or any folder that contains multiple skills. Public repos only.

CancelContinue

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/zero-lab-ai/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/plugins/detection-validation/skills/telemetry-coverage-audit .claude/skills/telemetry-coverage-audit

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Telemetry Coverage Audit in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Telemetry Coverage Audit on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Telemetry Coverage Audit is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Telemetry coverage audit

When to Use

Reviewing evidence quality or profile-specific telemetry usability without contacting sources or claiming detection coverage.
Use only within explicit authorization and the stated rules of engagement.

When NOT to Use

Do not treat this skill as permission to access, test, or change a target.
Do not convert missing evidence into a clean result or a stronger claim.

Purpose

Validate an already-supplied passive evidence ledger. A complete review means only that the ledger is internally consistent with supplied policy. It does not prove detection coverage, effectiveness, activity absence, or operational readiness.

Boundary

Never contact, poll, query, sample, or test a source. Never write queries or rules, configure collectors or sensors, execute techniques, or propose live tests. Do not accept raw events, live identifiers, product names, hosts, accounts, tenants, addresses, paths, endpoints, locators, credentials, configuration bodies, target details, commands, scripts, or payloads. Never map results to ATT&CK, threats, rules, or detection effectiveness.

Workflow

Obtain the supplied ledger, policy receipt, requirement bundle, investigation profiles, and sanitized passive evidence.
Stop on operational content. Do not quote a rejected value.
Preserve opaque source, profile, scope, and evidence identifiers. Do not enrich them from outside the ledger.
Keep the twelve supplied-policy dimensions separate. Evidence for one role never substitutes for another.
Configuration cannot prove delivery; current health cannot prove historical continuity; field presence cannot prove populated required fields.
Policy retention cannot prove retained or retrievable data; access cannot prove retrieval; event absence cannot prove collection or activity absence.
Require exact source fingerprint, scope, policy digest, bundle digest, profile digest, dimension, NA reason, authority, and window bindings.
Require every source to participate in a nonempty profile. Count every source-profile-dimension cell in the denominator; never shrink it for missing, stale, gap, or prohibited evidence.
Use not-applicable only with an allowed reason and exact current policy proof. Neutralize all operational evidence in that cell.
Derive each cell as supported, partial, gap, unknown, stale, or not-applicable; never calculate a score.
Derive each source-profile usability from its weakest required cell: usable, limited, unusable, unknown, or stale.
Do not generalize usability between profiles, even on the same source.
Require one immutable open gap for every gap cell. This ledger cannot close a gap.
Keep handoffs defensive, exact-bound, and non-authorizing. A recorded handoff transfers review work only.

Coverage-state decision table

State	Use when
`supported`	Current, exact-bound evidence supports every required role for the cell
`partial`	Some required roles are supported and the missing roles are named
`gap`	Required evidence shows the capability is absent or unusable
`unknown`	Required evidence was not supplied or cannot be joined exactly
`stale`	Evidence exists but falls outside the policy freshness window
`not-applicable`	Current policy explicitly excludes the cell with an allowed reason

Unknown, stale, and gap remain in the denominator. Do not improve a state because another profile or source performed better.

Report

State the ledger reviewed, coverage-state counts, profile usability, exact evidence gaps, limitations, and open gap IDs. Add: “Internal ledger consistency only; no source was contacted and no detection effectiveness is claimed.”

Rationalizations to reject

“The collector is configured, so delivery is covered.” Configuration and delivery require different evidence roles.
“Health is green now, so continuity was good.” A point-in-time health record cannot establish history.
“The schema contains the field.” Presence does not prove population.
“Retention policy says thirty days.” Policy does not prove retained or retrievable data.
“The reviewer has access.” Access does not prove successful retrieval.
“No event was found.” Absence proves neither collection nor activity absence.
“This source worked for another profile.” Usability is profile-specific.
“One score is easier.” A score hides which independent claim is weak.
“We can test the source to settle this.” This skill is passive only.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

agents/openai.yaml1 KB
assets/zero-lab-mark.svg11 KB

Frequently asked questions

What does the Telemetry Coverage Audit AI skill do?

Why use Telemetry Coverage Audit on TypingMind?

Because you install it once and use it with any model. Telemetry Coverage Audit is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Telemetry Coverage Audit in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/zero-lab-ai/skills/tree/main/plugins/detection-validation/skills/telemetry-coverage-audit. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Telemetry Coverage Audit?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Telemetry Coverage Audit?

As many as you like. As long as a model supports skills, you can use Telemetry Coverage Audit with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Telemetry Coverage Audit AI skill free?

Yes. It is published on GitHub by zero-lab-ai under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Executing Plans

obra

CommunityPopular

Use when you have a written implementation plan to execute in a separate session with review checkpoints

Using Superpowers

Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions

Context And Decisions

affaan-m

CommunityPopular

Govern stable domain context with a narrowly scoped CONTEXT.md when needed, and route hard-to-reverse decisions to ECC's existing architecture-decision-records skill. Use when domain terms require…

Docs Governance

Route broad documentation-governance requests to existing ECC skills and run an opt-in, read-only audit of mapped documentation roles, links, ADR indexes, and evidence references. Use when a user asks…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Telemetry coverage audit

When to Use

When NOT to Use

Purpose

Boundary

Workflow

Coverage-state decision table

Report

Rationalizations to reject

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now