camsnap

Capture frames or clips from RTSP/ONVIF cameras.

4.00x

Quality

70%

Does it follow best practices?

Impact

100%

4.00x

Average score across 3 eval scenarios

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./openclaw/skills/camsnap/SKILL.md

The canonical home for this skill is camsnap in openclaw/openclaw

Quality

Content

86%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is an exemplary lean command reference: fully concrete, zero padding, sensibly sectioned. The only real gaps are the elided `--action '...'` placeholder in the motion-watch command and the unspecified config.yaml format, which keep actionability and workflow clarity just short of top marks.

Suggestions

Replace the `--action '...'` placeholder with one real example action (e.g. `--action 'save --out motion.mp4'`) so the motion-watch command is actually runnable.

Show a minimal `~/.config/camsnap/config.yaml` example so manual config editing is as actionable as the CLI.

Add one line making validation explicit in the workflow, e.g. 'If a capture fails or hangs, run `camsnap doctor --probe` before adjusting settings.'

Dimension	Reasoning	Score
Conciseness	Every line is a command, path, or operational note ("camsnap snap kitchen --out shot.jpg", "Requires ffmpeg on PATH"); there is no padding and no explanation of concepts Claude already knows. This matches the lean anchor 5 exactly.	5 / 5
Actionability	Commands are copy-paste ready for add/discover/snap/clip/doctor, matching anchor 4 (mostly executable, minor gaps). Not a 5 because `--action '...'` is a literal elided placeholder rather than a runnable example, and the expected structure of `~/.config/camsnap/config.yaml` is never shown.	4 / 5
Workflow Clarity	A clear setup-then-use sequence is present (Setup → Common commands) with `camsnap doctor --probe` as a diagnostic and "Prefer a short test capture before longer clips" as a soft checkpoint, matching anchor 4. Not a 5 because validation is offered as an optional command rather than an explicit step in the capture workflow (e.g. run doctor when a capture fails).	4 / 5
Progressive Disclosure	The skill is under 50 lines with no need for external references, and its well-organized sections (Setup, Common commands, Notes) cover it cleanly — the rubric's simple-skill guidance says this earns a 5. No bundle files exist to reference, and none are needed.	5 / 5
	Total	18 / 20 Passed

Description

53%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is concise and names a specific domain, but it reads as a bare capability statement: no trigger guidance, only two of the skill's actual capabilities (motion events, camera setup are in the body only), and few natural synonyms. It is functional but sits at the midpoint of the rubric.

Suggestions

Add an explicit trigger clause, e.g. 'Use when working with RTSP/ONVIF or IP security cameras, or when the user wants snapshots, clips, or motion events from a camera.'

Include natural synonyms users would actually say — snapshot, IP camera, CCTV, security camera, webcam — alongside the RTSP/ONVIF protocol terms.

Mention the other concrete capabilities shown in the body (add/configure cameras, motion-event watching) to raise specificity from two actions to comprehensive coverage.

Dimension	Reasoning	Score
Specificity	"Capture frames or clips" names the domain (RTSP/ONVIF cameras) and two concrete actions, matching the anchor for 1-2 concrete actions without comprehensive coverage. It is not a 4 because 'several specific actions' are not listed — motion events and camera configuration are omitted from the description.	3 / 5
Completeness	The 'what' is clear ("Capture frames or clips from RTSP/ONVIF cameras") but there is no 'Use when...' clause or equivalent trigger guidance; the rubric explicitly caps completeness at 3 in that case. Not a 2 because the 'what' is concrete rather than vague.	3 / 5
Trigger Term Quality	Relevant keywords like "frames", "clips", and "cameras" are present, but common natural variations users would say — snapshot, IP camera, CCTV, security camera — are missing, and RTSP/ONVIF leans toward technical jargon. This fits anchor 3 (some relevant keywords, missing synonyms) rather than 4.	3 / 5
Distinctiveness Conflict Risk	Protocol-specific camera capture ("RTSP/ONVIF cameras") carves out a mostly distinct niche with only minor overlap risk against generic screenshot/video tools, matching anchor 4. Not a 5 because the action words 'capture frames or clips' alone could brush against generic screen-capture skills.	4 / 5
	Total	13 / 20 Passed

Validation

81%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: trpc-group/trpc-agent-go
Path: openclaw/skills/camsnap/SKILL.md
Commit: 9bb1c42

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.