CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

iot-operator-specialist-methods

Evidence-led iot operator technical methods and evidence interpretation for the relevant environment.

Quality

59%

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 ./packages/decepticon/decepticon/skills/standard/iot/specialist-methods/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

72%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 a tight, high-signal reference: it scopes what it does and does not cover, embeds concrete evidentiary limits and safety constraints, and avoids all padding. Its weaknesses are the absence of any executable specifics or explicit step sequence, which keep actionability and workflow clarity at the midpoint.

Suggestions

Include one or two executable anchors, e.g., example commands for hashing a firmware image or recording radio parameters, so the guidance is not entirely deferred to other skills.

Convert the evidentiary principles into a short ordered checklist (acquire → verify provenance → trace consumers → compare against benign control) so the implicit checkpoints become an explicit sequence.

DimensionReasoningScore

Conciseness

The body is lean and dense: every sentence carries non-obvious domain knowledge (provenance requirements for firmware evidence, test-fixture caveats for key-like strings, per-protocol identity/replay distinctions, benign-control comparison rules) with no padding and no explanation of concepts Claude already knows. This matches 'every token earns its place'; score 4 would require trimmable over-explanation, which is absent.

5 / 5

Actionability

Concrete heuristics are present ('trace consumers and configuration before claiming exposure', 'Compare effects against a benign control without involving neighboring devices or production safety systems'), but there are no commands or code, and implementation is deferred to other skills ('Use the relevant existing technique skills for implementation details'). This matches anchor 3 ('some concrete guidance but incomplete'), not 4, because no executable specifics are given in this file.

3 / 5

Workflow Clarity

The content is organized as evidentiary principles rather than a sequenced workflow, but risk-relevant checkpoints are present implicitly — verify before claiming exposure, compare against a benign control, exclude production safety systems. This fits anchor 3 (checkpoints implicit, sequence not explicit) better than 2, since validation is not absent, and better than 4, since no clear step sequence is laid out.

3 / 5

Progressive Disclosure

The body is under 50 lines, no bundle files exist or are needed, and it is divided into well-organized sections ('Firmware and hardware evidence', 'Radio and backend boundaries') with a scoping intro. Per the simple-skill guidance, this warrants 5 — the mentions of other skills (e.g., binwalk-extract) point to external skills, not bundle files, and are clearly signaled.

5 / 5

Total

16

/

20

Passed

Description

28%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 identifies a niche domain but reads as an abstract label rather than a capability statement: no concrete actions, no trigger terms a user would naturally say, and no 'when to use' guidance. The filler phrase 'for the relevant environment' adds vagueness without adding information.

Suggestions

Add an explicit trigger clause, e.g., 'Use when conducting an authorized IoT operator investigation involving firmware/hardware evidence, radio protocol testing, or backend access claims.'

Replace the abstract label with concrete actions: name what the skill covers (e.g., firmware acquisition provenance, BLE/Zigbee/Z-Wave/LoRaWAN testing limits, benign-control comparison) instead of 'technical methods and evidence interpretation'.

Drop the filler 'for the relevant environment' and add natural trigger terms users would actually say, such as 'IoT devices', 'firmware analysis', 'BLE', or 'sensor'.

DimensionReasoningScore

Specificity

The description names its domain ("iot operator technical methods and evidence interpretation") but lists no concrete actions, and "for the relevant environment" is generic filler. It matches the anchor 'Names the domain but actions are minimal or generic', not score 3, because not even 1-2 specific actions (e.g., firmware acquisition, radio protocol testing) are stated.

2 / 5

Completeness

The 'what' is a vague topic label rather than a statement of what the skill does, and the 'when' is entirely absent — matching anchor 2 ('Has a vague what and no when'). It cannot score 3 because the what is not clear and concrete, and the missing 'Use when...' clause caps completeness at 3 regardless.

2 / 5

Trigger Term Quality

"iot" is a natural term, but "evidence-led", "evidence interpretation", and "technical methods" are jargon users would not naturally say, and common variations (IoT devices, firmware, BLE, sensor) are missing. Only one or two generic keywords are present, matching score 2 rather than 3's 'some relevant keywords' with partial synonym coverage.

2 / 5

Distinctiveness Conflict Risk

"iot operator" carves out a recognizable niche, but "technical methods and evidence interpretation for the relevant environment" is generic enough to overlap with other evidence-analysis or security skills. This fits 'Somewhat specific but could still overlap with similar skills' rather than 4's mostly-distinct profile with distinct triggers.

3 / 5

Total

9

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

Total

14

/

16

Passed

Repository

PurpleAILAB/Decepticon

Path

packages/decepticon/decepticon/skills/standard/iot/specialist-methods/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.