CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

homeassistant-bridge

Bidirectional Home Assistant integration — HA cameras in, detection results out

Quality

64%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/integrations/homeassistant-bridge/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

58%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 admirably lean and well-sectioned, but it stops at setup: it never explains how to run the bridge, lacks any operational workflow or validation, and references files (requirements.txt, external modules) that are not in the bundle. Adding an invocation example and a run/verify sequence would materially improve it.

Suggestions

Add a 'Run' section with an executable example, e.g. 'python3 scripts/bridge.py --ha-url $HA_URL --ha-token $HA_TOKEN --cameras camera.front_door,camera.backyard'.

Include a short numbered workflow with a verification checkpoint (e.g. confirm the 'ready' event on stdout before expecting frames), since the bridge is a long-running polling process.

Resolve the missing requirements.txt reference or inline the pip dependencies, and either link or remove the vague DeepCamera module pointers.

DimensionReasoningScore

Conciseness

The body is lean: a single-sentence overview, an ASCII data-flow diagram, a one-line 'Wraps' note, and a two-line setup block, with no padding or explanation of concepts Claude already knows. Every token earns its place, matching the score-5 anchor; it is not merely 'mostly efficient' (score 4).

5 / 5

Actionability

The Setup block ('python3 -m venv .venv && ...', 'pip install -r requirements.txt') is executable, but the body never shows how to invoke scripts/bridge.py, gives no example config or camera arguments, and references a requirements.txt that is not in the bundle. This is concrete but incomplete guidance, matching score 3 rather than the mostly-complete score 4.

3 / 5

Workflow Clarity

The 'How It Works' diagram shows a conceptual data flow (cameras → pipeline → results back) but there is no operational sequence for running the bridge, no validation/checkpoints, and the continuous frame-capture loop is undocumented. This fits score 2 ('rough sequence present but many gaps; validation absent') better than score 3, which expects listed steps.

2 / 5

Progressive Disclosure

The body is organized into clear sections and the capability references scripts/bridge.py (which exists), but it also references a missing requirements.txt and vaguely points at external DeepCamera modules without links, so references are present but not clearly signaled. This matches score 3 rather than 4, where references would be mostly clear with only minor gaps.

3 / 5

Total

13

/

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 clear niche with two concrete directional actions, but it omits any 'Use when' trigger guidance and relies on somewhat technical phrasing ('detection results out'). Adding explicit trigger phrases would lift completeness and trigger-term quality.

Suggestions

Add a 'Use when...' clause with concrete triggers, e.g. 'Use when integrating Home Assistant cameras with Aegis, sending camera frames for detection, or surfacing results as HA entities.'

Replace pipeline jargon like 'detection results out' with user-facing terms such as 'image_processing entities' and 'HA automations' to improve trigger-term naturalness.

Mention the return path explicitly (results surface as HA image_processing entities for automations) to broaden specificity coverage.

DimensionReasoningScore

Specificity

Quotes 'Bidirectional Home Assistant integration', 'HA cameras in', and 'detection results out' — it names the domain plus two concrete directional actions, but coverage is not comprehensive (no mention of the return path's entity types, automations, or polling). This matches the score-3 anchor ('names domain and 1-2 concrete actions') and falls below score 4, which requires several specific actions with only minor gaps.

3 / 5

Completeness

The 'what' is clearly stated (bidirectional HA integration with cameras in / detection results out), but there is no 'Use when...' clause or equivalent trigger guidance, so per the judging guideline completeness is capped at 3. It does not reach score 4, which requires both an explicit 'what' and an explicit 'when'.

3 / 5

Trigger Term Quality

It includes the natural term 'Home Assistant' and 'cameras', but 'detection results out' is pipeline jargon and there are no common synonyms or file/entity-style triggers (e.g. 'image_processing', 'HA automations'). This aligns with score 3 ('some relevant keywords but missing common variations') rather than 4, which expects good coverage with only a few natural terms missing.

3 / 5

Distinctiveness Conflict Risk

'Bidirectional Home Assistant integration — HA cameras in, detection results out' occupies a clear, narrow niche that is unlikely to fire for unrelated skills, with only minor overlap risk against generic camera or HA skills. It stops short of score 5 because it lacks explicit trigger phrases that would make it unmistakably distinct.

4 / 5

Total

13

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

SharpAI/DeepCamera

Path

skills/integrations/homeassistant-bridge/SKILL.md

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.