CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

wireless-overview

Top-level index for the Decepticon 802.11 wireless attack suite. Routes the WirelessOperator to the correct leaf skill based on the target AP's crypto column (PSK / SAE / MGT / WPS) and engagement posture. BLE, Zigbee, Z-Wave, LoRaWAN, and sub-GHz live under iot/ by design — link provided below to prevent duplication.

Quality

75%

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 ./packages/decepticon/decepticon/skills/standard/wireless/SKILL.md
SKILL.md
Quality
Evals
Security

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.

A lean, well-structured operator index that routes on concrete airodump column values, gates execution on hardware mode with an explicit blocked outcome, and cross-references OPSEC posture per technique. The only shortcomings are minor: the elided airodump command and the absence of error-recovery guidance after a failed capture or check.

DimensionReasoningScore

Conciseness

The body is dense routing signal — a playbook table, a column-to-leaf decision tree, a hardware-mode gate, a node-contract table, and an OPSEC matrix — with zero padding and no explanation of concepts Claude already knows (no "what is WPA2" prose). Every section earns its place, matching the 'lean and efficient; every token earns its place' anchor.

5 / 5

Actionability

Concrete, executable routing logic throughout: "airodump-ng --write-interval 1 --output-format csv ... Read the ENC/CIPHER/AUTH columns", explicit mappings like "ENC=WPA3, AUTH=SAE → wpa3-sae", and a real config path "plan/roe.json:machine_enforcement.wireless.mode" with per-mode behavior. It falls short of fully copy-paste-ready only because the airodump invocation is elided with "..." and "ssh <dropbox> -- '<cmd>'" is a placeholder pattern — minor gaps, so anchor 4 rather than 5.

4 / 5

Workflow Clarity

A coherent sequence with explicit checkpoints: pre-flight verification ("Verify the configured hardware mode and authorized wireless scope before using a leaf skill"), a refuse gate ("'none' → refuse, return outcome=blocked"), and a post-selection checklist ("After selecting the primary leaf, always check: deauth-pmf... krack-fragattacks"). Missing error-recovery feedback loops (e.g., what to do when the WPS column is empty or monitor mode fails) keeps it below the anchor-5 bar; the checkpoints are explicit, so it is above anchor 3.

4 / 5

Progressive Disclosure

This is a pure index with well-signaled, one-level-deep references: each of the seven leaf skills is linked once from the playbook table (e.g., "[wpa2-psk](wpa2-psk/SKILL.md)") with its trigger and MITRE mapping, no detail is inlined that belongs in a leaf, and non-802.11 RF is delegated to the iot/ suite. No bundle files exist in this skill, and navigation via the trigger table is trivial — a clear match for the anchor-5 example of an overview with clean one-level references.

5 / 5

Total

18

/

20

Passed

Description

57%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 carves out a clearly distinct niche and even preemptively resolves overlap with the iot/ suite, which is exemplary for conflict risk. However, it omits an explicit 'Use when' trigger clause and the natural trigger terms (Wi-Fi, WPA2/WPA3, evil twin, deauth) that live only in metadata, leaving completeness and trigger quality at the midpoint.

Suggestions

Add an explicit trigger clause to the description, e.g. "Use when attacking Wi-Fi / 802.11 targets: PSK or SAE cracking, enterprise EAP capture, WPS, evil-twin, or deauth operations" — this lifts completeness from 3 to 4-5.

Fold the natural synonyms currently only in metadata.when_to_use ("Wi-Fi", "WPA2", "WPA3", "evil-twin", "deauth", "rogue AP", "airspace") into the description text itself so trigger matching works from the description alone.

Briefly enumerate the routing outcomes ("routes to leaf skills for wpa2-psk, wpa3-sae, enterprise EAP, WPS Pixie-Dust, evil-twin/KARMA, deauth/PMF, and KRACK/fragmentation") so the capability list is comprehensive rather than a single routing action.

DimensionReasoningScore

Specificity

"Routes the WirelessOperator to the correct leaf skill based on the target AP's crypto column (PSK / SAE / MGT / WPS) and engagement posture" is one concrete, well-parameterized action, and the exclusion clause ("BLE, Zigbee, Z-Wave, LoRaWAN, and sub-GHz live under iot/") adds scope detail — matching the '1-2 concrete actions' anchor. It does not list several distinct actions (anchor 4), though it is far more concrete than the generic anchor 2.

3 / 5

Completeness

The 'what' is clear ("Top-level index for the Decepticon 802.11 wireless attack suite. Routes the WirelessOperator to the correct leaf skill..."), but there is no "Use when..." clause or equivalent explicit trigger guidance in the description — 'when' is only weakly implied by "based on the target AP's crypto column", which caps completeness at 3 per the rubric guideline.

3 / 5

Trigger Term Quality

Relevant domain keywords are present ("802.11 wireless attack", "PSK / SAE / MGT / WPS", "BLE, Zigbee, Z-Wave, LoRaWAN"), but the most natural phrases an operator would say — "Wi-Fi", "WPA2", "WPA3", "evil twin", "deauth", "rogue AP" — appear only in metadata.when_to_use, not in the description itself. This is 'some relevant keywords but missing common variations or synonyms' rather than good coverage with only a few gaps.

3 / 5

Distinctiveness Conflict Risk

The niche is unambiguous (802.11 attack-suite router keyed on PSK/SAE/MGT/WPS) and it explicitly de-conflicts with the neighboring suite: "BLE, Zigbee, Z-Wave, LoRaWAN, and sub-GHz live under iot/ by design — link provided below to prevent duplication." Minimal conflict risk with a clear distinct trigger surface.

5 / 5

Total

14

/

20

Passed

Validation

81%

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

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

relative_links

Relative link issues: 7 missing

Warning

Total

13

/

16

Passed

Repository

PurpleAILAB/Decepticon

Path

packages/decepticon/decepticon/skills/standard/wireless/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.