CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

nanoclaw-traffic-guardian

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

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

Quality

Content

71%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 well-structured and notably strong on executable verification (a complete signed-manifest check script with fail-fast validation), and its safety contract and scope sections are lean and specific. Its main weakness is that the detailed builder guidance is deferred to files (SPEC.md, placeholder folders) that are not present in the bundle, so the promised deep layer is missing.

Suggestions

Ship the referenced `SPEC.md` (or inline its essential content) — the body instructs "Read `SPEC.md` before implementing" but the file does not exist in the bundle, leaving the skill's core second level missing.

Create the placeholder folders (`lib/`, `host-services/`, `mcp-tools/`, `test/`) or remove/reframe the Builder Entry Points table, since none of the mapped paths currently exist.

Move the ~70-line release-verification script into a `scripts/verify-release.sh` with a one-line invocation, keeping SKILL.md as a lean overview and improving token efficiency.

DimensionReasoningScore

Conciseness

Sections are terse bullet lists that assume the reader's competence (Safety Contract, Scope, Out of Scope), and the long shell script consists of non-derivable specifics (URLs, pubkey hash) rather than padding. Not a 5 because the ~70-line verification script and the Vercel install section are installer-facing material that inflates the main file beyond what the core builder guidance needs.

4 / 5

Actionability

The verification section ships a fully executable, copy-paste-ready script with a concrete install command, and the "Required First Implementation Behavior" list gives specific, checkable requirements. Not a 5 because key guidance points to artifacts that don't exist in the bundle ("Read `SPEC.md` before implementing" — no SPEC.md present), and the placeholder-folder table describes directories that are not shipped.

4 / 5

Workflow Clarity

The release-verification workflow has explicit validation checkpoints with fail-fast error messages (fingerprint mismatch, signature verify, per-file checksum) and a gating rule ("Only install or extract the archive after this verification succeeds"), and implementation behavior starts with "Validate config without starting the proxy". Not a 5 because the builder-side sequence is a requirements list without feedback/recovery loops, and the SPEC.md that would carry the detailed process is missing.

4 / 5

Progressive Disclosure

Sections are well-organized and clearly signaled, but the body's central instruction ("Read `SPEC.md` before implementing") references a file absent from the bundle, and the Builder Entry Points table maps nonexistent placeholder folders. Not a 2 because the structure itself is good and nothing is deeply nested; not a 4 because the primary deep-content reference is broken, leaving no usable second level at all.

3 / 5

Total

15

/

20

Passed

Description

46%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 names a specific, niche domain with a couple of concrete capability surfaces, but it reads as a jargon-heavy noun stack with no action verbs and no "Use when" trigger guidance. It is distinct from other skills, yet a user would struggle to know when to invoke it.

Suggestions

Add an explicit trigger clause, e.g. "Use when monitoring NanoClaw runtime traffic, inspecting host proxy traffic, or checking container MCP/IPC status" — currently the "when" is entirely missing, which caps completeness at 3.

Replace jargon nouns with concrete verbs users would actually say ("detects outbound exfiltration", "inspects HTTP(S) proxy traffic", "reports redacted findings") to raise specificity.

Include natural synonyms and variations of trigger terms (traffic monitoring, proxy inspection, exfiltration detection, IPC status) instead of compound technical phrases like "container-safe status surfaces".

DimensionReasoningScore

Specificity

Names the domain ("runtime traffic monitoring") and 1-2 concrete capabilities ("host-side proxy inspection", "MCP and IPC status surfaces"), but these are noun phrases rather than concrete actions, and coverage is not comprehensive. Not a 2 because the inspection surfaces are more concrete than generic domain-naming; not a 4 because no concrete verbs/actions (detect, log, report) are listed.

3 / 5

Completeness

The "what" is stated (traffic monitoring baseline with proxy inspection and MCP/IPC status surfaces), but there is no "when"/"Use when" guidance at all, which caps this dimension at 3. Not a 4 because the "when" is entirely absent rather than merely weak; not a 2 because the "what" is reasonably clear, not vague.

3 / 5

Trigger Term Quality

"traffic monitoring" and "proxy inspection" are semi-natural, but the phrase leans on technical jargon ("baseline", "container-safe", "status surfaces") and offers no synonyms, variations, or natural user phrasings. Not a 1 because a user could plausibly say "traffic monitoring" or "proxy inspection"; not a 3 because even those terms are wrapped in jargon with no common variations.

2 / 5

Distinctiveness Conflict Risk

The NanoClaw-specific niche (runtime traffic monitoring, host-side proxy, MCP/IPC surfaces) is highly distinct with minimal overlap risk against generic skills. Not a 5 because the description does not articulate distinct triggers, and it could overlap with the closely related `clawsec-nanoclaw` advisory suite referenced in the body.

4 / 5

Total

12

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

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

Reviewed

Table of Contents

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.