common-protocol-enforcement

Enforce Red-Team verification and adversarial protocol audit. Use when verifying tasks, performing self-scans, or checking for protocol violations. Load as composite for all sessions.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

62%

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

The content is a well-sequenced verification checklist with explicit checkpoints and a fix loop, scoring well on workflow clarity. It is held back by redundant sections, references to undefined project constructs, and an empty References section that fails to surface the available bundle file.

Suggestions

Collapse the overlapping Red Flags, Rationalization Prevention, and Anti-Patterns sections into one to remove redundancy and tighten the token budget.

Either link references/example.md from the body's References section or remove the empty heading so the bundle file is actually discoverable.

Replace project-specific examples ("shared fakes", "design tokens", "Pre-Write Audit Log") with generic, self-contained guidance or define those terms inline so the skill is actionable outside its original project.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean bullet points, but the Anti-Patterns section repeats Red Flags and Rationalization Prevention (e.g., "No Reliance on Memory" restates "Stop if you relied on memory"), so it could be tightened; not level 3 due to the redundancy.	2 / 3
Actionability	It gives a concrete checklist ("Search for Standard Defaults", "Read diff or file content"), but references undefined project-specific constructs ("shared fakes", "design tokens", "Pre-Write Audit Log") that leave guidance incomplete for a generic skill, matching level 2.	2 / 3
Workflow Clarity	The protocol is a clearly numbered sequence (Audit, Protocol Check, Evidence Check, Bias Check) with explicit checkpoints ("Stop if...") and a feedback loop ("Fix: Re-edit immediately if violation detected"), matching the level-3 anchor for a checklist with validation.	3 / 3
Progressive Disclosure	Sections are well organized, but the trailing "## References" heading is empty and the existing bundle file references/example.md is never linked from the body, so references are present but not clearly signaled — level 2 rather than 3.	2 / 3
	Total	9 / 12 Passed

Description

60%

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 answers both what and when with an explicit trigger clause, but its actions are abstract and its triggers are jargon-heavy. The instruction to load it for all sessions creates severe conflict risk with other skills.

Suggestions

Remove "Load as composite for all sessions" — it guarantees conflict with every other skill; instead scope triggers to genuine protocol-audit moments.

Replace abstract verbs ("Enforce", "audit") with concrete actions a user would recognize (e.g., "Run a pre-write checklist that verifies files were re-read and protocols were followed").

Use natural trigger phrasing a user would actually say (e.g., "before marking a task done", "self-check my work") instead of jargon like "self-scan" or "pre-write audit".

Dimension	Reasoning	Score
Specificity	Names the domain and several actions ("verifying tasks, performing self-scans, or checking for protocol violations"), but the verbs are abstract ("Enforce", "audit") rather than concrete operations, so it stops short of level 3.	2 / 3
Completeness	Explicitly answers what ("Enforce Red-Team verification and adversarial protocol audit") and when ("Use when verifying tasks, performing self-scans, or checking for protocol violations"), matching the level-3 anchor with an explicit Use-when clause.	3 / 3
Trigger Term Quality	Includes relevant keywords ("self-scan", "protocol check", "verify done", "red-team"), but these are specialized meta-jargon a user would rarely say naturally; missing common variations keeps it at level 2 rather than 3.	2 / 3
Distinctiveness Conflict Risk	The phrase "Load as composite for all sessions" combined with generic triggers ("scan", "task complete", "retrospective") would conflict with nearly every other skill, matching the level-1 anchor for very generic, high-conflict descriptions.	1 / 3
	Total	8 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	14 / 16 Passed

Repository: HoangNguyen0403/agent-skills-standard
Commit: 611f52a

Reviewed: 4 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.