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

78%

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

63%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.

Highly actionable and well-sequenced with strong validation gates, but the body is a verbose monolithic recipe dump that duplicates its own reference files rather than acting as a progressive overview.

Suggestions

Move the inlined evasion/anti-forensics and persistence recipe sections into the existing references (evasion-cheatsheet.md, attack-playbooks.md) and keep SKILL.md as a lean overview pointing to them.

Trim generic technique-category explanations that restate knowledge Claude already has; retain only the concrete commands and tool mappings.

Consolidate the duplicated tool lists (in-body cheatsheet vs. routing table) into one tool-index reference to cut token overhead.

Dimension	Reasoning	Score
Conciseness	The ~650-line body over-explains technique categories Claude already knows and inlines large recipe sections (evasion, anti-forensics, persistence, full tool cheatsheet) that duplicate the existing evasion-cheatsheet.md and attack-playbooks.md references rather than deferring to them.	2 / 5
Actionability	Dense with concrete, copy-paste-ready commands and code across recon, exploitation, privesc, lateral movement, and cloud attacks, plus tables mapping techniques to tools and outcomes.	5 / 5
Workflow Clarity	An 'ACTION REQUIRED' sequenced checklist with stage gates and auth.status checks, a decision tree, and the lifecycle-checklist.md reference provide clear sequencing and validation checkpoints, though some in-body gate detail is implicit.	4 / 5
Progressive Disclosure	Section headers and three one-level reference files exist, but the bulk of the technique material is inlined directly in SKILL.md instead of being split out, so the overview is not a lean pointer to detailed materials.	3 / 5
	Total	14 / 20 Passed

Description

92%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 tight, well-scoped description that names concrete attack-chain phases, gives explicit 'when' trigger guidance, and cleanly separates itself from single-stage specialist skills via a routing clause.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capability domains (reconnaissance, initial access, privilege escalation, lateral movement, impact assessment) plus an explicit routing action, giving comprehensive coverage of the attack-chain phases.	5 / 5
Completeness	Explicitly answers both what (multi-stage attack-path planning and orchestration) and when ('Use for...when a task spans...') with concrete trigger phases.	5 / 5
Trigger Term Quality	Natural multi-stage trigger phrasing ('Use for... when a task spans reconnaissance, initial access, privilege escalation, lateral movement') and good pentest vocabulary, though it omits common synonyms like 'red team' or 'pentest'.	4 / 5
Distinctiveness Conflict Risk	Clear multi-stage-orchestration niche with an explicit carve-out ('Route single-stage tasks directly to their specialist skill') that minimizes overlap with sibling skills.	5 / 5
	Total	19 / 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
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: 7e2097f

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.