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

73%

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

72%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-organized, token-efficient routing catalog with clean progressive disclosure via per-skill references. Its main gap is a missing validation/verification checkpoint around the chain-persisting step in the workflow.

Suggestions

Add an explicit verify step after plan_attack_chains(promote=True) (e.g. confirm the persisted chain node exists before moving on) to satisfy the destructive/batch feedback-loop requirement.

For the routing tables, consider stating the one concrete first action each sub-skill should take, so the overview is actionable on its own rather than only delegating.

Dimension	Reasoning	Score
Conciseness	The body is lean: tight tables of skill paths with one-line use-cases and a compact numbered workflow, with no padding or explanation of concepts Claude already knows.	3 / 3
Actionability	It gives concrete routing targets (explicit SKILL.md paths) and named commands ('kg_stats', 'plan_attack_chains(promote=True)'), but as a routing skill the actionable instruction is mostly 'go load the matching skill', so guidance here is not itself fully executable.	2 / 3
Workflow Clarity	A clear 5-step numbered sequence is present, but the state-modifying step 'call plan_attack_chains(promote=True) to persist complete chains' has no explicit validation/verification checkpoint, capping this dimension at 2 per the rubric's feedback-loop guidance.	2 / 3
Progressive Disclosure	The SKILL.md acts as a clean catalog overview with clearly signaled one-level-deep references (per-skill SKILL.md paths in organized tables), and no deeper nesting or bundle dirs to mismanage.	3 / 3
	Total	10 / 12 Passed

Description

75%

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, well-scoped routing description that answers both what it does and when to load it, with a distinct niche. It is slightly held back by jargon-heavy trigger phrasing and a thinner list of concrete capabilities.

Suggestions

Replace internal jargon like 'iteration start' with natural user-facing triggers (e.g. 'when starting a vulnerability research session') to improve trigger term quality.

Add a couple of concrete capability terms (e.g. 'route to SQLi, SSRF, deserialization, and chain-building playbooks') to lift specificity toward the top anchor.

Dimension	Reasoning	Score
Specificity	Names a concrete niche ('vulnerability research playbooks', 'vuln-class and chain-building skills') and a concrete action ('Load this first ... see the full catalog'), but does not list multiple specific capabilities the way the top anchor does.	2 / 3
Completeness	Explicitly answers both what ('Root pointer ... full catalog of vuln-class and chain-building skills') and when ('Load this first at iteration start'), matching the top anchor's what-and-when pattern.	3 / 3
Trigger Term Quality	Includes relevant natural terms ('vulnerability research', 'playbooks', 'chain-building'), but leans on internal jargon like 'iteration start' and lacks broader common-user variations, so it stops short of full coverage.	2 / 3
Distinctiveness Conflict Risk	It occupies a clear niche as the analyst's catalog root pointer with distinct routing triggers, making it unlikely to fire for the wrong skill.	3 / 3
	Total	10 / 12 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: e34afba

Reviewed: about 15 hours 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.