Tessl • The management layer for AI agent skills

Blog Docs Log inGet started

SkillPublic

shield

Security scanner for code, addresses, and transactions

Quality

75%

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 ./src/skills/bundled/shield/SKILL.md

Quality

Content

87%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 content is exceptionally lean and provides fully executable command syntax, scoring perfectly on conciseness, actionability, and progressive disclosure. Its only weakness is the absence of a sequenced workflow with validation checkpoints and feedback loops for the destructive/risky transaction-validation operations.

Suggestions

Add a short workflow section for /shield validate that sequences pre-flight checks, surfaces validation failures, and describes the fix-and-retry feedback loop.

Document what a failed validation looks like and how to proceed (e.g., warn the user and halt, or suggest corrections) so risky transaction operations have explicit validation checkpoints.

Optionally include one example output for /shield check or /shield validate so users and Claude can verify a correct invocation.

Dimension	Reasoning	Score
Conciseness	The body is a one-line overview plus a compact command table with zero padding and no explanation of concepts Claude already knows, matching the score-5 'lean and efficient; every token earns its place' anchor.	5 / 5
Actionability	The command table gives fully executable, copy-paste-ready syntax with arguments (e.g. '/shield validate <dest> <amt> [token]') covering the common cases, matching the score-5 anchor.	5 / 5
Workflow Clarity	Commands are listed clearly but the skill performs transaction validation and address safety checks (risky operations) with no sequenced workflow, validation checkpoints, or error-recovery feedback loops, and the rubric caps workflow clarity at 3 when validation is missing for such operations.	3 / 5
Progressive Disclosure	The body is under 50 lines, single-purpose, has no external bundle files to reference, and is organized under a clear ## Commands section, so it qualifies for the score-5 simple-skill exception.	5 / 5
	Total	18 / 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 clearly states what the skill does and targets a distinct security-scanning niche, but it omits any 'Use when...' trigger guidance, which caps completeness. Trigger keywords are domain-relevant but lack the natural phrasings a user would say.

Suggestions

Add a 'Use when...' clause naming concrete trigger phrases, e.g. 'Use when the user asks to scan code for malicious patterns, check whether an address or transaction is safe, or look up known scam addresses.'

Include scam detection in the description to match the body's /shield scams command and broaden natural trigger coverage.

Surface natural user phrases like 'is this address safe' or 'validate this transaction' as trigger terms rather than only the technical nouns.

Dimension	Reasoning	Score
Specificity	Names the security-scanning domain plus three concrete targets ('code, addresses, and transactions'), matching the score-3 anchor for naming the domain with concrete actions; it is not score 4 because the listed items are scan targets rather than a comprehensive set of distinct actions and scam detection is omitted.	3 / 5
Completeness	The 'what' is clearly stated ('Security scanner for code, addresses, and transactions') but there is no 'Use when...' trigger clause, and the rubric caps completeness at 3 when trigger guidance is missing.	3 / 5
Trigger Term Quality	Domain keywords ('security scanner', 'code', 'addresses', 'transactions') are present but the natural phrases users would say ('is this address safe', 'check for scams', 'validate this transaction') are missing, fitting score 3 rather than 4.	3 / 5
Distinctiveness Conflict Risk	The combination of 'code, addresses, and transactions' signals a distinct web3/blockchain security niche with low conflict risk, fitting score 4 ('mostly distinct; minor overlap risk'); it is not 5 because scam detection is absent and overlap with generic security tools remains possible.	4 / 5
	Total	13 / 20 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: alsk1992/CloddsBot
Path: src/skills/bundled/shield/SKILL.md
Revision: c930628

Reviewed: 1 month ago

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.

shield

Table of Contents

Is this your skill?