CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

ble-session-appliance

Control BLE Session Appliance through the generated BLE device CLI.

Quality

74%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./testdata/golden/expected/generate-device-ble-session/ble-session-appliance/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

82%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 efficient, fully executable runbook: concrete install/verify steps with failure recovery, and a complete catalog of exact CLI invocations including a dry-run/confirm safety loop for the physical-effect command. Its main weaknesses are presentational — the command catalog is one dense paragraph with no grouped sections or explicit end-to-end sequence.

DimensionReasoningScore

Conciseness

The body is dense and operational — "**You must verify the CLI is installed before invoking any command from this skill.**", the exact npx install line, and PATH failure recovery all earn their tokens — with only minor trimmable padding such as "install Node or use the category-specific Go fallback after publish". Not a 5 because that time-sensitive fallback sentence and the re-explanation of PATH visibility add a little slack.

4 / 5

Actionability

Every main instruction is a copy-paste-ready command with exact flags: "npx -y @mvanhorn/printing-press-library install ble-session-appliance --cli-only", "ble-session-appliance-pp-cli --version", "capabilities --json", "start --dry-run --json", "session start --json", "telemetry capture --json", covering the common cases. The only non-concrete guidance is the rare Go-fallback path, which does not rise to a gap.

5 / 5

Workflow Clarity

The install sequence is numbered with explicit validation (verify version, check PATH, "Do not proceed with skill commands until verification succeeds"), and the risky physical-effect operation has a validate-then-confirm loop ("pass --confirm-physical-effect after checking the dry-run output"), so the destructive-operation cap does not apply. Not a 5 because the main operational flow (capabilities → dry-run → confirm → session → telemetry) is only implicitly ordered in a paragraph rather than an explicit sequenced workflow.

4 / 5

Progressive Disclosure

At ~20 lines with no external references needed, the skill qualifies for the simple-skill exception, but organization is only good rather than excellent: one clear section header ("Prerequisites: Install the CLI") is followed by a single wall-of-text paragraph holding the entire command catalog. Splitting that catalog into grouped subsections or a table would reach anchor 5.

4 / 5

Total

17

/

20

Passed

Description

52%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, in third person, and highly distinctive thanks to the unique appliance and CLI names, but it is thin: one generic action verb, no enumerated capabilities, and no 'Use when...' trigger guidance. It reads like a title rather than a triggerable skill description.

Suggestions

Add a 'Use when...' clause with concrete trigger phrases, e.g., 'Use when the user mentions the BLE Session Appliance, Bluetooth device control, or asks to start/inspect a BLE session.'

Enumerate 2-3 concrete capabilities from the CLI, e.g., 'Start BLE sessions, capture telemetry, scan for devices, and inspect capability and session status via the ble-session-appliance-pp-cli.'

Include natural synonyms such as 'Bluetooth' / 'Bluetooth Low Energy' alongside 'BLE' so the description matches how users actually phrase requests.

DimensionReasoningScore

Specificity

"Control BLE Session Appliance through the generated BLE device CLI" names the domain and mechanism but relies on a single generic umbrella verb ("Control") with no concrete operations enumerated, matching the anchor 'Names the domain but actions are minimal or generic'. It is not a 3 because no 1-2 concrete actions (e.g., start sessions, capture telemetry, scan devices) are stated.

2 / 5

Completeness

The description clearly answers "what" (control the appliance via the generated BLE device CLI) but contains no "Use when..." clause or any equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. Not a 4 because the "when" is entirely absent rather than merely imprecise.

3 / 5

Trigger Term Quality

The terms "BLE", "Session Appliance", and "CLI" are relevant keywords a user of this appliance would say, but common variations and synonyms such as "Bluetooth" or "Bluetooth Low Energy" are absent, matching 'Some relevant keywords but missing common variations or synonyms'. Not a 4 because coverage is essentially one acronym cluster.

3 / 5

Distinctiveness Conflict Risk

The unique appliance name ("BLE Session Appliance") and the named CLI binary ("ble-session-appliance-pp-cli") establish a clear niche with distinct triggers and minimal conflict risk with other skills. Even the neighboring anchor 4's 'minor overlap risk' does not apply since no other skill would plausibly target this device.

5 / 5

Total

13

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

mvanhorn/cli-printing-press

Path

testdata/golden/expected/generate-device-ble-session/ble-session-appliance/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.