nanoclaw-traffic-guardian

NanoClaw runtime traffic monitoring baseline for host-side proxy inspection with container-safe MCP and IPC status surfaces.

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/nanoclaw-traffic-guardian/SKILL.md

Quality

Content

77%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.

The body is actionable and workflow-clear, especially the signed-release verification procedure with explicit validation checkpoints. It is somewhat heavy on inline shell and could benefit from moving the verification script into a referenced file for better progressive disclosure.

Suggestions

Move the signed-release verification shell block into a referenced script (e.g. scripts/verify-release.sh) and link to it, keeping only the invocation in SKILL.md to improve conciseness and progressive disclosure.

Strengthen cross-file navigation by clearly signaling what SPEC.md and each placeholder folder contain as one-level-deep references.

Dimension	Reasoning	Score
Conciseness	Overview prose is lean and purposeful, but the large signed-release verification shell block is heavy and could be deferred to a referenced script to reduce token load.	2 / 3
Actionability	Provides fully executable shell with concrete commands, real release URLs, and a fingerprint check — copy-paste ready guidance.	3 / 3
Workflow Clarity	Clear sequenced verification workflow with explicit validation checkpoints and error-exit feedback loops, plus a guard ('Only install or extract after this verification succeeds').	3 / 3
Progressive Disclosure	Sections are well-organized and reference SPEC.md and placeholder folders, but the cross-file navigation is not strongly signaled and the inline verification block could live in a referenced file.	2 / 3
	Total	10 / 12 Passed

Description

67%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.

The description is specific to a distinct niche and uses appropriate third-person voice, but omits an explicit 'Use when...' trigger clause, leaving the 'when to use' half unanswered. Trigger terms are decent but not comprehensive enough for natural user phrasing.

Suggestions

Add an explicit 'Use when...' clause stating when Claude should invoke this skill, e.g. when the user needs host-side proxy inspection or runtime traffic monitoring for NanoClaw.

Broaden trigger terms with natural user phrasings (e.g. 'traffic monitoring', 'proxy inspection', 'outbound exfiltration detection') so the skill matches how users actually describe the need.

Dimension	Reasoning	Score
Specificity	Names the domain and multiple concrete surfaces — "host-side proxy inspection", "container-safe MCP", "IPC status surfaces" — listing several specific capabilities.	3 / 3
Completeness	Clearly states what the skill does but provides no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 2.	2 / 3
Trigger Term Quality	Includes relevant niche terms ("runtime traffic monitoring", "host-side proxy inspection") but lacks common user-facing variations and phrasings users would naturally say.	2 / 3
Distinctiveness Conflict Risk	NanoClaw-specific niche with host-side proxy inspection framing makes it clearly distinguishable and unlikely to trigger for the wrong skill.	3 / 3
	Total	10 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: prompt-security/clawsec
Path: skills/nanoclaw-traffic-guardian/SKILL.md
Commit: c6194eb

Reviewed: 14 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.