camsnap
Capture frames or clips from RTSP/ONVIF cameras.
74
63%
Does it follow best practices?
Impact
100%
4.00xAverage score across 3 eval scenarios
Risky
Do not use without reviewing
Optimize this skill with Tessl
npx tessl skill review --optimize ./openclaw/skills/camsnap/SKILL.mdQuality
Discovery
40%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 identifies a clear and distinctive niche (RTSP/ONVIF camera capture) but is too terse. It lacks a 'Use when...' clause, misses common user-facing trigger terms like 'IP camera' or 'security camera', and could benefit from listing more specific capabilities beyond just 'frames or clips'.
Suggestions
Add a 'Use when...' clause such as 'Use when the user needs to capture snapshots or video clips from IP cameras, security cameras, or video streams using RTSP or ONVIF protocols.'
Include common natural-language trigger terms like 'IP camera', 'security camera', 'video stream', 'snapshot', 'surveillance', and 'live feed' to improve discoverability.
Expand the capability list with more specific actions, e.g., 'connect to camera streams, capture individual frames or video clips, configure stream parameters, save recordings in various formats'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (RTSP/ONVIF cameras) and two actions (capture frames, capture clips), but doesn't elaborate on additional capabilities like configuration, streaming, saving formats, or other concrete operations. | 2 / 3 |
Completeness | Describes what the skill does (capture frames/clips from cameras) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per rubric guidelines, missing 'Use when' caps completeness at 2, and the 'what' is also thin, warranting a 1. | 1 / 3 |
Trigger Term Quality | Includes relevant technical keywords like 'RTSP', 'ONVIF', 'frames', and 'clips' that users familiar with IP cameras would use, but misses common variations like 'IP camera', 'security camera', 'video stream', 'snapshot', or 'surveillance'. | 2 / 3 |
Distinctiveness Conflict Risk | RTSP/ONVIF camera frame/clip capture is a very specific niche that is unlikely to conflict with other skills. The protocol-specific terms (RTSP, ONVIF) clearly distinguish it. | 3 / 3 |
Total | 8 / 12 Passed |
Implementation
87%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-crafted, concise skill that provides clear, actionable CLI commands for camera capture operations. Its main weakness is the lack of an explicit workflow sequence with validation steps—particularly important since captures can fail silently with bad credentials or network issues. The 'doctor' command exists but isn't integrated into a recommended workflow.
Suggestions
Add a brief recommended workflow sequence: discover → add → doctor/probe → test snap → longer operations, with explicit validation checkpoints (e.g., 'Run `camsnap doctor --probe` to verify connectivity before capturing').
Consider noting what to check if a command fails (e.g., ffmpeg not found, camera unreachable) to create a feedback loop for error recovery.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Very lean and efficient. No unnecessary explanations of what RTSP/ONVIF cameras are or how ffmpeg works. Every line provides actionable information. | 3 / 3 |
Actionability | Provides specific, copy-paste ready commands for every operation: adding cameras, discovering, snapshotting, clipping, and motion watching with concrete flags and arguments. | 3 / 3 |
Workflow Clarity | The commands are listed but there's no explicit sequenced workflow (e.g., discover → add → test → snap). The note about preferring a short test capture hints at validation but doesn't formalize it as a checkpoint. For a tool involving potentially long-running captures, a clearer sequence with validation would be beneficial. | 2 / 3 |
Progressive Disclosure | For a simple, single-purpose skill under 50 lines, the content is well-organized into logical sections (setup, commands, notes) with no unnecessary nesting or monolithic blocks. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
72%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 8 / 11 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 | 8 / 11 Passed | |
- Repository
- trpc-group/trpc-agent-go
- Commit
09cce3e
- Reviewed
Table of Contents
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.