CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

clawsec-suite

ClawSec suite manager with embedded advisory-feed monitoring, cryptographic signature verification, approval-gated malicious-skill response, and guided setup for additional security skills.

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./skills/clawsec-suite/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 highly actionable and workflow-safe, with executable verification-first install flows and approval-gated destructive actions. Its weaknesses are length (redundant config examples and inline detail that belongs in reference files) and a couple of dangling file references.

Suggestions

Move the Advisory Suppression config format, matching rules, and shared-config example into a reference file (e.g. references/allowlist.md) and keep a short summary in SKILL.md.

Drop one of the two overlapping JSON suppression examples and the repeated SUITE_DIR assignment blocks to cut token overhead.

Ensure referenced bundle files (HEARTBEAT.md, advisories/feed.json) ship with the skill, or remove/qualify the references.

DimensionReasoningScore

Conciseness

The body is mostly operational rather than explanatory, but at ~410 lines it carries noticeable padding: two overlapping JSON config examples in the Advisory Suppression section, repeated SUITE_DIR blocks, and feed-default lists that could be tightened to fit the 'mostly efficient but could be tighter' anchor.

3 / 5

Actionability

Every flow ships copy-paste-ready executable bash with set -euo pipefail, explicit fingerprint and signature verification, and exit-on-error checks, and all four referenced setup/guard/discovery scripts verified present in scripts/.

5 / 5

Workflow Clarity

Flows are clearly sequenced with real validation checkpoints (fingerprint then signature then checksum before install; exit code 42 plus --confirm-advisory rerun for the double-confirmation install), but most flows print an error and exit without fix-and-retry recovery guidance, so the feedback-loop anchor is not fully met.

4 / 5

Progressive Disclosure

Sections are well organized and script references are one level deep and real, but HEARTBEAT.md and advisories/feed.json are referenced yet absent from the bundle, and large config-format/suppression detail is inlined in SKILL.md rather than split into a reference file.

3 / 5

Total

15

/

20

Passed

Description

58%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 specific and third-person, naming several distinct capabilities, but it lacks any 'when to use' trigger guidance and relies on suite jargon over natural user phrasing. It would benefit most from an explicit use-when clause.

Suggestions

Add an explicit trigger clause, e.g. 'Use when checking installed skills against security advisories, verifying a skill's signature before install, or responding to a malicious-skill alert.'

Swap jargon-heavy noun phrases for natural user-facing verbs (e.g. 'monitors the advisory feed for malicious skills' instead of 'embedded advisory-feed monitoring').

Include common user phrasings and synonyms ('malicious skill', 'skill safety', 'security advisory') to improve trigger-term coverage.

DimensionReasoningScore

Specificity

The description lists four distinct concrete capabilities ('advisory-feed monitoring', 'cryptographic signature verification', 'approval-gated malicious-skill response', 'guided setup for additional security skills'), matching the several-specific-actions anchor, though coverage has minor gaps (heartbeat checks, catalog discovery, and suppression features are not mentioned).

4 / 5

Completeness

The 'what' is clearly stated, but there is no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

Domain-relevant keywords like 'advisory', 'security skills', 'malicious-skill', and 'signature verification' are present, but the natural phrases a user would say ('is this skill safe to install', 'check my installed skills') and common synonyms are missing, and the phrasing leans on suite jargon.

3 / 5

Distinctiveness Conflict Risk

'ClawSec suite manager' carves a distinct niche, but 'guided setup for additional security skills' creates minor overlap risk with the closely related ClawSec protection skills this suite manages.

4 / 5

Total

14

/

20

Passed

Validation

87%

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

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

relative_links

Relative link issues: 1 suspicious

Warning

Total

14

/

16

Passed

Repository

prompt-security/clawsec

Path

skills/clawsec-suite/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.