attack-chain

Use for authorized multi-stage attack-path planning and orchestration when a task spans reconnaissance, initial access, privilege escalation, lateral movement, or impact assessment. Route single-stage tasks directly to their specialist skill.

Quality

67%

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 ./skills/attack-chain/SKILL.md

Quality

Content

50%Weight 40%Scale 1-3

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

Highly actionable and well-sequenced, but the body is a bloated inline command catalog that duplicates reference files and spells out knowledge Claude already has, with weak per-step validation in its destructive phases. Splitting the phase material into the existing reference files and tightening the overview would materially improve it.

Suggestions

Move the per-phase command catalogs into references/attack-playbooks.md and references/evasion-cheatsheet.md, leaving SKILL.md as a concise overview that links to them — the files already exist but are unreferenced.

Add explicit validate→fix→retry checkpoints within destructive/batch phases (e.g. confirm a foothold before lateral movement, verify persistence survived reboot) rather than only top-level phase gates.

Trim commands and technique explanations that a security-capable model already knows, keeping only the non-obvious playbooks and tool-specific flags.

Dimension	Reasoning	Score
Conciseness	The ~650-line body is an exhaustive inline command manual spelling out standard pentest commands (subfinder, sqlmap, mimikatz, certipy, Kerberoasting) that a capable model largely already knows, with explanatory tables and tips — it does not assume Claude's competence and every token does not earn its place.	1 / 3
Actionability	Packed with concrete, executable commands and copy-paste-ready examples across all phases (e.g. 'sqlmap -u ... --batch --dbs', 'mimikatz# sekurlsa::logonpasswords', 'certipy req -u ... -template VulnTemplate') with specific tool flags.	3 / 3
Workflow Clarity	A clear 7-phase sequence and a path-planning decision tree exist, plus auth gates and a self-check, but the destructive/batch operational phases (lateral movement, persistence, anti-forensics) lack per-step validate→fix→retry feedback loops, capping the score at 2 per the rubric's batch-operations note.	2 / 3
Progressive Disclosure	Sections are cleanly organized and references are one level deep, but the 7-phase reference manual is inlined in SKILL.md rather than split out, and two of three bundle files (attack-playbooks.md, evasion-cheatsheet.md) exist but are never linked from the body.	2 / 3
	Total	8 / 12 Passed

Description

85%Weight 40%Scale 1-3

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 strong, specific description that clearly bounds the skill's orchestration niche and separates it from single-stage specialists, with explicit what-and-when triggers. Its only gap is relying on formal phase names rather than the more colloquial trigger phrasings a user might actually type.

Suggestions

Add natural-language triggers users would actually say — e.g. 'Use for full penetration tests, red team engagements, or end-to-end kill-chain planning' — alongside the formal phase names.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities — 'reconnaissance, initial access, privilege escalation, lateral movement, or impact assessment' plus 'planning and orchestration' and routing single-stage tasks — rather than vague language.	3 / 3
Completeness	Explicitly answers both 'what' ('authorized multi-stage attack-path planning and orchestration') and 'when' ('when a task spans reconnaissance, initial access...') with explicit triggers, plus routing guidance for single-stage tasks.	3 / 3
Trigger Term Quality	Covers the formal phase terms (reconnaissance, privilege escalation, lateral movement) that a pentester would say, but misses common colloquial variations like 'penetration test', 'red team', 'kill chain', or 'full chain' that the body itself uses.	2 / 3
Distinctiveness Conflict Risk	Clear niche as a multi-stage orchestrator that explicitly distinguishes itself from single-stage specialist skills ('Route single-stage tasks directly to their specialist skill'), making conflicts unlikely.	3 / 3
	Total	11 / 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
skill_md_line_count	SKILL.md is long (652 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: zhaoxuya520/reverse-skill
Path: skills/attack-chain/SKILL.md
Commit: 6aa1362

Reviewed: 7 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.