Physical Recon logo

Physical Recon

Organization
zero-lab-ai
physical-recon

Assesses supplied daylight physical-security observations from authorized public vantage points at opaque site and control level. Use when reviewing physical reconnaissance without entering property, tracking people, collecting identifiers, planning approaches, or generating intrusion methods.

Overview

Publisherzero-lab-ai
Repositoryskills
Skill namephysical-recon
Stars
232
Forks
14
Bundled files
2
LicenseApache-2.0
Links
  • 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 Physical Recon AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

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.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/zero-lab-ai/skills/tree/main/plugins/recon-operations/skills/physical-recon
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

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/recon-operations/skills/physical-recon .claude/skills/physical-recon
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Physical Recon 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 Physical Recon 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 Physical Recon 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.

Physical recon

Physical reconnaissance can reveal visible control surfaces and documentation gaps. A defensive assessment records bounded observations without converting them into routes, schedules, identities, or intrusion instructions.

This skill analyzes supplied observation records. It does not direct collection, enter property, follow or contact people, photograph private areas, identify people or vehicles, collect discarded material, operate drones, transmit RF, rank sites or shifts, select approach routes, or design entry, badge-cloning, bypass, concealment, or evasion methods.

When to Use

  • Reviewing physical reconnaissance without entering property, tracking people, collecting identifiers, planning approaches, or generating intrusion methods.
  • 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.

Workflow

  1. Record digest-addressed written authority, approving opaque role, valid assessment and observation windows, public-right-of-way-only mode, daylight-only observation, opaque identities, bounded retention, and every prohibited method.
  2. Inventory opaque sites and public-right-of-way observation points. Bind each point and permitted method to an approved authorization; store no address, coordinate, map, route, tenant, person, vehicle, or schedule.
  3. Import supplied evidence with a unique artifact reference, original-origin evidence, class, time, site and point binding, privacy state, disposition, and limitations.
  4. Record each field session with its exact authorized site, point, window, daylight visual method, safety receipt, required stop conditions, and explicit false values for target contact, property entry, and material collection.
  5. Separate client policy requirements from direct observation. Policy evidence can define expected control design but cannot prove a visible condition; imported OSINT cannot prove one either.
  6. Exclude material with unknown site, time, vantage, custody, scope, or privacy status. Public visibility does not repair missing provenance.
  7. Record controlled observations as visible, not-observed, or indeterminate. Never use absence: non-observation is not proof that a control does not exist.
  8. Derive each site/control assessment from all current policy requirements and direct observations: consistent, potential-variance, inconclusive, or not-assessed. Potential variance is a review trigger, not a confirmed vulnerability.
  9. Keep one custody record for every artifact-bearing evidence item. Bound retention to the engagement ceiling; require chronological receipts for redaction or destruction.
  10. Create defensive handoffs for internal control review, remediation, or a separately authorized assessment. Carry opaque assessment IDs, never routes, targets, or methods.
  11. Cover authority, public boundary, provenance, policy baseline, time, privacy, custody, safety, seven physical-control classes, and defensive handoff for every site. Proof must match its class.

Boundary with adjacent skills

  • Use osint-scanner to classify remote third-party acquisition and target contact.
  • Use social-engineering-recon for human-layer roles, processes, channels, and relationships; this skill stores no person or behavioral profile.
  • Use wireless-assessment-plan for RF receiving or transmission; both are prohibited here.
  • Use social-engineering-engagement-plan before any interaction with staff.
  • Physical entry, tailgating, cloning, bypass, covert routes, and on-site validation require a separate capability and explicit method-level authority; this skill never supplies them.

Rationalizations to reject

  • "It is visible from public space, so anything is fair game." Privacy, scope, time, custody, retention, and harm constraints still apply.
  • "One open door proves a recurring gap." A transient observation proves only itself.
  • "Two observers used the map, so it is corroborated." Copies of one origin are one.
  • "A photo is evidence even without metadata." Unknown site, time, vantage, or custody prevents a defensible physical conclusion.
  • "Shift ranking is just prioritization." It turns control assessment into person and schedule targeting.
  • "A route explains the finding." Approach and evasion guidance is operational planning.
  • "Passive includes drones or receive-only RF." This contract permits neither; use a separately authorized capability.
  • "The sponsor asked for badge cloning." Sponsor pressure does not expand recorded scope.
  • "No visible control means no control exists." Missing public evidence is not absence.
  • "a complete record authorizes a field action." It validates a supplied record only.

Bundled files

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

Frequently asked questions

What does the Physical Recon AI skill do?

Assesses supplied daylight physical-security observations from authorized public vantage points at opaque site and control level. Use when reviewing physical reconnaissance without entering property, tracking people, collecting identifiers, planning approaches, or generating intrusion methods.

Why use Physical Recon on TypingMind?

Because you install it once and use it with any model. Physical Recon 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 Physical Recon in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/zero-lab-ai/skills/tree/main/plugins/recon-operations/skills/physical-recon. 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 Physical Recon?

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 Physical Recon?

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

Is the Physical Recon 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

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇