red-team

Use when planning or executing authorized red team engagements, attack path analysis, or offensive security simulations. Covers MITRE ATT&CK kill-chain planning, technique scoring, choke point identification, OPSEC risk assessment, and crown jewel targeting.

Quality

89%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

—

The risk profile of this skill

Quality

Content

82%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.

A well-organized, highly actionable skill body built around a real bundled tool and reference file, with clear workflows and authorization/OPSEC checkpoints. The main improvement room is tightening the intro and moving more reference-grade tables into the existing reference file.

Suggestions

Trim the opening paragraph — it restates the frontmatter description; lead directly with the skill's distinctive purpose or the authorization gate.

Move the full 'Technique Scoring Reference' and 'Attack Path Graph Construction' tables into references/attack-path-methodology.md, keeping only the formula and one short example inline in SKILL.md.

Add an explicit validate→fix→retry feedback loop for engagement_planner.py runs (e.g., on exit code 1 or 2, inspect the error, adjust techniques/scope, re-run) to raise workflow_clarity to 5.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient — tables, formulas, and copy-paste commands that assume Claude's security knowledge without explaining what MITRE ATT&CK or LSASS is — but the opening paragraph re-derives the description's framing and several reference tables (effort formula, attack-path graph) overlap content offloaded to the reference file.	4 / 5
Actionability	Provides fully executable, copy-paste-ready invocations of engagement_planner.py with concrete flags, access levels, and exit codes across three workflows, plus a defined scoring formula and specific technique tables that cover the common cases.	5 / 5
Workflow Clarity	Three workflows are clearly sequenced (numbered steps, week-by-week phases, the kill-chain ordering principle, and the OPSEC checklist as a per-phase gate), with verification via the --authorized gate, exit codes, and detection-event logging; minor gap is the absence of an explicit validate→fix→retry feedback loop for plan generation failures.	4 / 5
Progressive Disclosure	Well-structured with a table of contents and clearly signaled one-level-deep references to the real references/attack-path-methodology.md and scripts/engagement_planner.py bundle files; the main body is somewhat long with several inlined reference tables that could live in the reference file, keeping it just short of the lean overview ideal.	4 / 5
	Total	17 / 20 Passed

Description

96%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 strong description that clearly states both what the skill does and when to use it, with concrete capability enumeration and natural trigger terms. The only gap is that distinctiveness from pen-testing is asserted in the body rather than the description itself.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities — 'kill-chain planning, technique scoring, choke point identification, OPSEC risk assessment, and crown jewel targeting' — alongside the actions 'planning or executing', giving comprehensive coverage rather than a single generic action.	5 / 5
Completeness	Explicitly answers both 'what' ('Covers MITRE ATT&CK kill-chain planning...') and 'when' ('Use when planning or executing authorized red team engagements...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Covers the natural phrases users say — 'red team engagements', 'attack path analysis', 'offensive security simulations' — plus domain terms like 'MITRE ATT&CK', 'kill-chain', 'OPSEC', and 'crown jewel', including synonyms.	5 / 5
Distinctiveness Conflict Risk	The 'authorized red team engagements' / 'attack path analysis' / 'offensive security simulations' framing carves a clear niche distinct from generic security work, but the description itself does not disambiguate from closely related pen-testing, leaving minor overlap risk (the body handles this but the description does not).	4 / 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
relative_links	Relative link issues: 4 suspicious	Warning

	Total	15 / 16 Passed

Repository: alirezarezvani/claude-skills
Path: engineering-team/skills/red-team/SKILL.md
Commit: 19392f7

Reviewed: ~9 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.