analyst-overview

Root pointer for the analyst's vulnerability research playbooks. Load this first at iteration start to see the full catalog of vuln-class and chain-building skills.

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./packages/decepticon/decepticon/skills/standard/analyst/SKILL.md

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.

An exemplary lean routing catalog that embodies progressive disclosure and assumes Claude's competence, with only minor gaps in explicit validation checkpoints and end-to-end executable detail.

Dimension	Reasoning	Score
Conciseness	The body is lean throughout — compact 'Use for' tables, no explanation of what SQL injection or SSRF is, and a terse 5-step workflow; every token earns its place and Claude's domain competence is assumed.	5 / 5
Actionability	Concrete guidance is present (specific sub-skill paths to load, real commands like `kg_stats` and `plan_attack_chains(promote=True)`), but as a routing skill it stops short of fully copy-paste-ready recipes, leaving minor gaps versus the 5 anchor.	4 / 5
Workflow Clarity	A clear 5-step sequence runs from recon to chain-building with a soft gate ('When enough vulns exist'), but explicit validation checkpoints are implicit rather than spelled out, matching the 'clear sequence, minor validation gaps' anchor.	4 / 5
Progressive Disclosure	This is a textbook progressive-disclosure overview: sectioned catalog pointing one level deep to individual sub-skill SKILL.md files via well-signaled tables, with the detail correctly pushed into the referenced skills rather than inlined here.	5 / 5
	Total	18 / 20 Passed

Description

66%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.

A clear, distinct routing description that answers both what and when, though its keyword coverage is somewhat technical and its concrete actions are minimal because the skill is a pointer rather than a doer.

Suggestions

Broaden trigger terms with natural synonyms users say (e.g. 'exploit research', 'pentest playbooks', 'CVE hunting') to lift trigger-term quality.

Add a 'Use when ...' clause naming multiple trigger situations (e.g. starting an iteration, deciding which vuln class to hunt) to push completeness toward 5.

Consider naming one or two concrete capabilities beyond 'load this' to raise specificity.

Dimension	Reasoning	Score
Specificity	Names the domain ('vulnerability research playbooks') and one concrete action ('Load this first at iteration start to see the full catalog'), but does not enumerate several specific capabilities — fitting the '1-2 concrete actions, not comprehensive' anchor rather than the 'several specific actions' anchor at 4.	3 / 5
Completeness	Both 'what' (root pointer / catalog of vuln-class and chain-building skills) and 'when' ('Load this first at iteration start') are present and concrete, but the trigger is a single narrow phrase rather than the multiple explicit trigger phrases that define the 5 anchor.	4 / 5
Trigger Term Quality	Relevant keywords appear ('vulnerability research', 'playbooks', 'catalog', 'chain-building', 'iteration start') but common synonyms a user might say ('exploit', 'pentest', 'CVE') are missing, matching the 'some relevant keywords but missing common variations' anchor rather than the broader coverage at 4.	3 / 5
Distinctiveness Conflict Risk	The description carves a clear niche — the analyst's vuln-research playbook catalog and routing entry point — with distinct triggers and minimal overlap risk against other skills.	5 / 5
	Total	15 / 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/analyst/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.