Name: agent-security-manager
Rating: 39.6 (1 reviews)
Author: ruvnet

Blog Docs Log in Get started

agent-security-manager

Agent skill for security-manager - invoke with $agent-security-manager

1.54x

Quality

12%

Does it follow best practices?

Impact

82%

1.54x

Average score across 3 eval scenarios

Securityby

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/agent-security-manager/SKILL.md

The canonical home for this skill is agent-security-manager in ruvnet/claude-flow

Quality

Content

25%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.

The body is an extensive catalog of non-executable reference code with minimal actionable guidance, no sequenced workflow, and no progressive disclosure structure. It functions as padded background material rather than a usable skill instruction set.

Suggestions

Replace the pseudocode with concise, executable snippets or remove the classes and instead describe concrete commands/APIs Claude can actually run.

Add a sequenced workflow with explicit validation checkpoints for destructive operations (e.g. key rotation: verify threshold -> rotate -> validate -> deactivate old key only on success).

Split the large code catalogs into referenced reference files (e.g. CRYPTO.md, ATTACK_DETECTION.md) and keep SKILL.md as a concise overview pointing to them.

Dimension	Reasoning	Score
Conciseness	The body is roughly 600 lines dominated by large code blocks interspersed with explanatory comments restating cryptographic concepts Claude already knows, making it noticeably verbose with several padded sections; it is not score-1 severe padding because the prose itself is sparse, but clearly below midpoint efficiency.	2 / 5
Actionability	The code is non-executable: it references undefined helpers (initializeCurve, generateSecretPolynomial, EllipticCurve, BehaviorAnalyzer, etc.) and gives only high-level structure, matching the minimal-concrete-guidance anchor with missing execution details.	2 / 5
Workflow Clarity	There is no sequenced multi-step workflow; instead the body is a catalog of class implementations, and destructive/batch operations like key rotation and key deactivation lack explicit validation checkpoints or fix-retry loops, capping this below the score-3 validation-gap level.	2 / 5
Progressive Disclosure	The content is a monolithic wall of inlined code with no section-based navigation to separate files and no references to supporting material that clearly belongs in separate files (e.g. the full API reference), matching the minimal-structure anchor.	2 / 5
	Total	8 / 20 Passed

Description

0%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.

The description is boilerplate invocation text that fails to convey the skill's purpose, capabilities, or trigger conditions. It reads as an auto-generated wrapper label rather than a meaningful skill description.

Suggestions

Replace the description with a concrete statement of what the skill does, e.g. 'Implements threshold signatures, zero-knowledge proofs, and attack detection for distributed consensus protocols.'

Add an explicit 'Use when...' trigger clause naming natural phrases a user would say, such as 'Use when securing consensus rounds, rotating distributed keys, or detecting Byzantine/Sybil attacks.'

Use third-person active voice describing capabilities and remove the invocation-syntax filler ('invoke with $agent-security-manager').

Dimension	Reasoning	Score
Specificity	The description 'Agent skill for security-manager - invoke with $agent-security-manager' names no concrete actions, only an invocation hint; it is entirely vague abstract language matching the score-1 anchor.	1 / 5
Completeness	It states neither what the skill does nor when to use it; it only describes how to invoke it, so both 'what' and 'when' are effectively missing, matching the score-1 anchor.	1 / 5
Trigger Term Quality	It contains only the invocation syntax '$agent-security-manager' and the label 'security-manager' — no natural keywords a user would say when needing the skill, matching the no-natural-keywords anchor.	1 / 5
Distinctiveness Conflict Risk	'Agent skill for security-manager' is entirely generic boilerplate indistinguishable from any other agent-skill wrapper and would conflict with virtually any similarly-named skill, matching the score-1 anchor.	1 / 5
	Total	4 / 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 (627 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: ruvnet/ruflo
Path: .agents/skills/agent-security-manager/SKILL.md
Commit: fa13ee4

Reviewed: about 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.