recognize-pose-or-gesture SKILL.md skillA
recognize-pose-or-gesture from borda/vision-delivery is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add borda/vision-delivery/recognize-pose-or-gesture@git:20261005.f3ff836Pins git:20261005.f3ff836 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- borda/vision-delivery
- Path
claude-skills/recognize-pose-or-gesture/SKILL.md- Versions recorded
- 3
- Latest version
- git:20261005.f3ff836, committed Oct 5, 2026
- First version recorded
- Aug 10, 2026
- Size
- 5,709 bytes
- Repository stars
- 4
- License
- Apache-2.0
Build keypoint-based pose, gesture, action, ergonomics, posture, or fall analysis. TRIGGER when: user asks for body/hand pose, gestures, action recognition, skeletons, keypoints, joint angles, raised hands, bending, squats, falls, sign language, or posture compliance. SKIP when: user needs an exact body contour/mask (segment-and-analyze), per-person PPE without keypoints (detect-and-analyze), whole-image compliance (classify-or-flag), identity/path tracking without pose (track-and-count), OCR…
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
<objective> Turn keypoints or temporal keypoint sequences into a pose/gesture decision that clears independent acceptance. Keep pose estimation, identity association, and business-rule classification as separately measured stages. </objective> <methodology> **Platform execution boundary.** Read `../../resources/roboflow-platform-lookup.md` before any provider-specific search, dataset, training, inference, workflow, or deployment action. Use installed official Roboflow skills or current MCP resources only for read-only discovery and sourced action-brief inputs; never invoke provider execution outside the host-gated path. Do not freeze model families, IDs, or platform recipes in Sentinel. Follow `../../resources/fde-methodology.md`; apply these keypoint-specific rules. ## 1. Define the action and time window Inspect footage, annotations, rules, code, and camera placement. Clarify whether the output is a per-frame posture, a hand/body gesture, a timed action, an ergonomics measurement, or a safety alert. Ask: - Which joints/keypoints and time window determine the action? - Must identity persist across frames? - Which error is worse for the operator: a miss or false alert? …
Read the whole file at its exact version.
How to install
mdr add borda/vision-delivery/recognize-pose-or-gesture@sha256:4a08c9d6d5aeaec3The line at the top of this page pins the label git:20261005.f3ff836, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_24a5klz6a6ixm5bf)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 3 versions of this file, between Aug 10, 2026 and Oct 5, 2026, about one every 28 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261005.f3ff836 latest | 2026-10-05 | f3ff836 | 5,709 B | A | view · diff |
| git:20260811.bdc99ff | 2026-08-11 | bdc99ff | 5,625 B | A | view · diff |
| git:20260810.60199a4 | 2026-08-10 | 60199a4 | 5,299 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (5709 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
borda/vision-delivery · 4 stars · license Apache-2.0 · pushed 2026-10-05 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_24a5klz6a6ixm5bf GET https://markdownregistry.com/api/v1/resolve?ref=borda/vision-delivery/recognize-pose-or-gesture GET https://markdownregistry.com/api/v1/blob/4a08c9d6d5aeaec34b6354994b068215fdaf3d8b621205debb8cb3488549a934
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.
More from borda/vision-delivery
Every file in borda/vision-delivery