agentleFS
Sign inStart free
Faaz17Faaz17/Agents-and-Skills/skills/unity/capture/SKILL.md

capture

Skill1 starsChanged 2 months agoMITView on GitHub

Plan a photogrammetry capture session (shot list, lighting, checklist) or log a completed one into docs/CAPTURE_LOG.md. Use before going to UOWD with the phone, or right after returning with a scan.

57 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use weekly, ingest and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • gaiaaiagentSkill

    weekly

    Generate a weekly digest rolling up dailies into higher-level pattern analysis

    Also in 4 projects that use this

  • JaimeGBASkill

    ingest

    Digest an external source (article, paper, transcript, URL, book chapter) and integrate its content into the knowledge base

    Also in 8 projects that use this

  • AnthropicSkill

    brief

    Generate contextual briefings for legal work — daily summary, topic research, or incident response. Use when starting your day and need a scan of legal-relevant items across email, calendar, and contracts, when researching a specific legal question across internal sources, or when a developing situation (data breach, litigation threat, regulatory inquiry) needs rapid context.

    Also in 6 projects that use this

  • QuixiAISkill

    weekly-review

    Review the past week across goals, tasks, calendar, journal, and commitments, then propose the next week

    Also in 5 projects that use this

  • dubwoahSkill

    ask

    Answer questions about the codebase without generating or modifying any code. Use when the user wants to understand how something works, find where something is defined, or explore the project structure. Invoked with /ask.

    Also in 4 projects that use this

  • termdockSkill

    recall

    Retrieves cross-session memories about past decisions, lessons, and patterns. Use when user asks about prior work, past decisions, or mentions a feature. Triggers include check memory, what did we decide, how did we solve.

    Also in 6 projects that use this

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 6 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 55 edited versions we read keep these.

  • 6

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Ask: which location, what time of day, expected weather, and roughly how large the area is (metres).

    line 12
  2. Distinctive:

    Route: start point, walking direction, number of loops (minimum two loops at different heights).

    line 14
  3. Distinctive:

    Scene check: wait out moving people/cars — they become mesh ghosts.

    line 18
  4. Distinctive:

    Ask for: date, location, device, app + mode, photo count, processing result, and a 1–5 quality gut-rating.

    line 24
  5. Distinctive:

    If the capture failed or looks poor, diagnose using the failure-modes table in the threed-modelling agent (holes → overlap, ghosts → …

    line 27
  6. Distinctive:

    One location: If the plan drifts toward "and while I'm there I'll also scan…", push back — that's the #1 scope trap in this project.

    line 31

“Common” is measured: kept by at least 6 in 10 of the 55 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

/capture — Photogrammetry Session Planner & Logger

Two modes. Ask which one applies if it isn't obvious from the conversation.

Mode 1: Plan (before the capture)

  1. Ask: which location, what time of day, expected weather, and roughly how large the area is (metres).
  2. Produce a one-page capture plan:
    • Route: start point, walking direction, number of loops (minimum two loops at different heights).
    • Distance: 1–3 m from surfaces for building exteriors.
    • Photo target: 50–150 photos; 70% overlap between adjacent shots.
    • Lighting check: overcast is ideal; avoid harsh midday sun and long morning/evening shadows. Same light for the whole session.
    • Scene check: wait out moving people/cars — they become mesh ghosts.
    • Scale reference: include something of known size in a few shots (an A4 sheet, a 30cm ruler) — Polycam free tier doesn't guarantee real-world scale, and this makes the Blender rescale trivial.
  3. End with a pre-flight checklist: phone charged, Polycam photo mode (not LiDAR), storage free, weather checked.

Mode 2: Log (after the capture)

  1. Ask for: date, location, device, app + mode, photo count, processing result, and a 1–5 quality gut-rating.
  2. Append an entry to docs/CAPTURE_LOG.md following the entry format defined at the top of that file.
  3. Remind the user to copy the raw export into models/source/ with a descriptive filename (e.g. courtyard_2026-07-10_polycam.glb) before doing anything else with it.
  4. If the capture failed or looks poor, diagnose using the failure-modes table in the threed-modelling agent (holes → overlap, ghosts → movement, smearing → speed) and plan the re-shoot.

Rules

  • One location. If the plan drifts toward "and while I'm there I'll also scan…", push back — that's the #1 scope trap in this project.
  • Captures are Phase 1 work: don't plan one until Phase 0's deliverable (Unity installed, Roll-a-Ball done) exists.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free