CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

picoclaw-traffic-guardian

Picoclaw runtime traffic monitoring baseline for lightweight AI gateway proxy inspection, egress detection, and posture integration.

Quality

69%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/picoclaw-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-organized, lean, and unusually strong on executable security verification, with a clear safety contract and sequenced implementation requirements. Its main weaknesses are a dangling SPEC.md reference and placeholder folder pointers that do not resolve to real bundle files, plus bulk inline script content that should live in scripts/.

Suggestions

Ship an actual SPEC.md (or remove the 'Read SPEC.md before implementing' instruction) — the instruction currently points to a file that does not exist in the bundle.

Move the ~70-line release-verification script into scripts/verify-release.sh and invoke it from SKILL.md with a one-line summary, trimming the main body substantially.

Either populate the lib/, scripts/, and test/ placeholder folders referenced in the Builder Entry Points table, or replace the table with a brief note that these are to be created by the implementer, and format file references as markdown links so they are clearly signaled.

DimensionReasoningScore

Conciseness

The body is lean in prose — it does not explain concepts Claude already knows, and sections like Scope, Safety Contract, and Out of Scope are terse bullet lists. The ~70-line release-verification script, while executable and purposeful, is bulk that arguably belongs in the (currently empty) scripts/ folder, keeping this just below the level-5 'every token earns its place' anchor. It is clearly above level 3, which flags unnecessary explanation.

4 / 5

Actionability

The install command and the signed-release verification script are fully executable, copy-paste-ready shell with real error handling ('set -euo pipefail', fingerprint mismatch checks, 'exit 1' paths). However, the core 'Required First Implementation Behavior' items are descriptive rather than backed by runnable code, and the referenced SPEC.md is missing from the bundle — minor gaps that fit the level-4 anchor 'mostly executable guidance with minor gaps' rather than level 5.

4 / 5

Workflow Clarity

The release-verification workflow is a clear sequence with explicit validation checkpoints and failure exits, gated by 'Only install or extract the archive after this verification succeeds', and the implementation section sequences config validation as step 1. It falls short of level 5 because the seven required-behavior steps lack feedback loops (validate -> fix -> retry) and there are no validation checkpoints for the implementation path itself.

4 / 5

Progressive Disclosure

Section structure is good, but the body points to 'Read SPEC.md before implementing' and a table of lib/, scripts/, and test/ folders — none of which exist in the bundle (scripts/ holds only a .gitkeep; SPEC.md, lib/, test/ are absent). References are plain text rather than clearly signaled links, and the large inline verification script is content that belongs in a separate file. This matches 'Some structure but could be better organized; references present but not clearly signaled' rather than level 4.

3 / 5

Total

15

/

20

Passed

Description

53%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 domain and a few actions but is written in vendor jargon rather than natural trigger language, and it entirely omits any 'when to use' guidance. It is serviceable but would rarely be selected by a user's natural phrasing.

Suggestions

Add an explicit trigger clause, e.g., 'Use when monitoring AI gateway traffic, inspecting outbound LLM requests, or detecting data exfiltration from Picoclaw runtimes.'

Replace jargon ('posture integration', 'monitoring baseline') with concrete user-facing actions such as 'inspect proxied HTTP traffic, log redacted findings as JSONL, and export security profiles'.

Include natural synonyms users would say (traffic inspection, egress monitoring, exfiltration detection, proxy logs) to improve trigger matching.

DimensionReasoningScore

Specificity

The description names its domain ("Picoclaw runtime traffic monitoring baseline") and lists 2-3 actions ("lightweight AI gateway proxy inspection, egress detection, and posture integration"), but "posture integration" and "baseline" are jargon-abstract rather than concrete, comprehensive actions. It matches the anchor 'Names domain and 1-2 concrete actions, but not comprehensive' better than the level-4 anchor, which expects several specific actions with only minor gaps.

3 / 5

Completeness

There is a reasonable 'what' (proxy inspection, egress detection, posture integration), but there is no 'when' at all — no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines. It cannot score 4, which requires both what and a present-but-imprecise when.

3 / 5

Trigger Term Quality

Terms like "traffic monitoring" and "egress detection" are relevant keywords a security engineer might say, but the description is dominated by technical jargon ("posture integration", "runtime traffic monitoring baseline") and misses natural variations and synonyms users would actually say (e.g., "inspect AI traffic", "monitor outbound requests", "proxy logs"). This fits 'Some relevant keywords but missing common variations or synonyms' rather than level 4's 'Good keyword coverage'.

3 / 5

Distinctiveness Conflict Risk

The 'Picoclaw' prefix and traffic-monitoring focus give it a clear niche that is mostly distinct from generic skills, but 'posture integration' overlaps with the sibling picoclaw-security-guardian skill's posture-profiling role (which the body confirms). Minor overlap risk with a closely related skill matches the level-4 anchor; it lacks the fully distinct trigger phrases of level 5.

4 / 5

Total

13

/

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/picoclaw-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.