crypto-decode

Cipher detection + automated decryption via Ciphey, Cyberchef recipes, hashcat hash-ID, format conversion, common encoding chains.

Quality

53%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./packages/decepticon/decepticon/skills/standard/exploit/crypto/SKILL.md

Quality

Content

68%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 playbook is lean, command-dense, and actionable, with strong tables for cipher signatures and hashcat modes and a sensible identify-first workflow. Its main weakness is the absence of explicit validation/recovery checkpoints in the decode and hash-cracking workflows, and a few illustrative-but-not-executable recipe chains.

Suggestions

Add validation checkpoints to the unfolding workflow (e.g. 'After each decode, verify the result is printable/structured before recursing; stop and flag if confidence is low').

Make the CyberChef recipe chains executable by showing the cyberchef-cli invocation or a concrete exported-JSON example rather than only recipe-name strings.

Move the full hashcat mode table to a reference file and keep only the most common modes inline, with a one-level-deep pointer to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is dense and command/table-driven with almost no padding of concepts Claude already knows ('A*-search across 16+ decoders ... BERT plaintext detector to know when to stop' is the main explanatory bit); a few sentences could be trimmed, so it sits at 4 rather than 5.	4 / 5
Actionability	Mostly copy-paste-ready commands and concrete tables (hashid invocations, hashcat modes, JWT/base64 decode one-liners); the CyberChef chains are illustrative recipe names rather than fully executable commands, which keeps it just below 5.	4 / 5
Workflow Clarity	Sections 1-5 give a recognizable identify-then-crack sequence and section 5 is a numbered unfolding workflow, but there are no explicit validation checkpoints or error-recovery feedback loops for a process that involves automated decryption and hash cracking; the batch/destructive-style cap guidance supports 3.	3 / 5
Progressive Disclosure	Content is well organized into clearly labeled sections with cross-references to sibling skills (jwt, dcsync) and upstream repos; no bundle files exist so structure is judged on the body, which is appropriately sectioned with only minor content that could live elsewhere (e.g. the hashcat mode table).	4 / 5
	Total	15 / 20 Passed

Description

37%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 names a coherent cryptanalysis niche and several concrete actions but is written as a noun-phrase list with no 'Use when' trigger guidance, and its keywords lean toward tool names rather than natural user phrasing. Trigger terms are also partly siloed in metadata rather than the description itself.

Suggestions

Add an explicit 'Use when ...' clause naming natural triggers (e.g. 'Use when you encounter unknown ciphertext, encoded blobs, or need to identify/crack a hash').

Replace tool-name-only keywords with natural user phrases ('decode', 'decrypt', 'base64', 'caesar cipher', 'identify this hash') alongside the tool references.

Lead with a third-person verb phrase ('Detects ciphers and automatically decodes ...') instead of a bare noun-phrase list.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions ('Cipher detection', 'automated decryption via Ciphey', 'Cyberchef recipes', 'hashcat hash-ID', 'format conversion', 'common encoding chains'), but the noun-phrase list form is not a comprehensive enumeration of capabilities, sitting between anchors 3 and 4.	3 / 5
Completeness	There is a clear 'what' (detection + decryption + format conversion) but no 'Use when...' or equivalent explicit trigger guidance, and judging guidelines cap completeness at 3 for a missing trigger clause; the absence of any 'when' phrasing pulls it to 2.	2 / 5
Trigger Term Quality	Terms like 'Ciphey', 'Cyberchef', 'hashcat hash-ID', and 'encoding chains' are tool/jargon names rather than natural phrases a user would say; the natural trigger terms ('decode', 'base64', 'caesar', 'decrypt') live in metadata.when_to_use instead of the description.	2 / 5
Distinctiveness Conflict Risk	The cryptanalysis niche (Ciphey/Cyberchef/hashcat) is clearly distinct from general skills with only minor overlap risk against a generic decode or web-jwt skill; not a 5 because the description lacks explicit triggers that fully disambiguate.	4 / 5
	Total	11 / 20 Passed

Validation

93%

Warnings & errors only

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

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: PurpleAILAB/Decepticon
Path: packages/decepticon/decepticon/skills/standard/exploit/crypto/SKILL.md
Commit: 0cf691e

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

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.