Name: amlbot
Rating: 55.2 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

amlbot

AMLBot integration. Manage data, records, and automate workflows. Use when the user wants to interact with AMLBot data.

Quality

63%

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/amlbot/SKILL.md

Quality

Content

68%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 a solid, mostly executable CLI integration guide with good structure and a real connection-state feedback loop. Its weaknesses are a redundant 'Popular actions' section, placeholder-only examples without concrete real values, and missing verification steps for destructive action/proxy operations.

Suggestions

Add a verification/check step after running actions and proxy requests (e.g., inspect the output field, confirm the record changed, handle error states) so destructive operations have a feedback loop and workflow_clarity is not capped.

Replace or augment the misleading 'Popular actions' section with 2-3 concrete example AMLBot actions (e.g., a real actionId for checking a wallet) instead of restating the discovery command.

Fix the step numbering (label 'Step 1a'/'Step 1b'/'Step 2' consistently or drop the dangling 'skip to Step 2' reference) and trim the introductory 'what AMLBot is' padding.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with copy-paste CLI commands and a flag table, but has minor padding (the introductory 'what AMLBot is' paragraph, 'so you can focus on the integration logic rather than auth plumbing') and a redundant 'Popular actions' section that repeats the discovery command, fitting 'efficient; minor instances of over-explanation that could be trimmed' rather than the fully lean 5.	4 / 5
Actionability	It provides concrete, executable commands for install, auth, connect, search, run, and proxy with a full flag table, but examples use placeholders (<actionId>, CONNECTION_ID, /path/to/endpoint) and 'Popular actions' offers no concrete real actions, matching 'mostly executable guidance; concrete commands with minor gaps' rather than the fully copy-paste-with-concrete-values 5.	4 / 5
Workflow Clarity	A sequence exists (install -> auth -> connect -> search -> run -> proxy) with a genuine connection-state feedback loop (poll --wait, handle READY/CLIENT_ACTION_REQUIRED/CONFIGURATION_ERROR), but running actions and proxy requests (which support destructive POST/PUT/PATCH/DELETE) lack verification steps, and step numbering is loose (a '1b' and an unlabeled 'Step 2'), so the destructive-operations-without-validation cap holds it at 3.	3 / 5
Progressive Disclosure	It is a self-contained, well-sectioned single-file CLI guide with clear headers (Overview, Install, Authentication, Connecting, Searching, Running, Proxy, Best practices) and no need for external references; the main gap is the misleading/duplicate 'Popular actions' section, fitting 'good structure; minor organization gaps' rather than a perfectly organized 5.	4 / 5
	Total	15 / 20 Passed

Description

57%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 correctly includes both a 'what' and an explicit 'Use when' trigger in third person, but its actions are generic rather than concrete and its trigger phrasing is not what users would naturally say. It is distinct mainly because it names a specific app, not because of uniquely distinctive triggers.

Suggestions

Replace generic actions ('Manage data, records, and automate workflows') with concrete AMLBot capabilities such as checking wallet purity, analyzing transaction risk, and reviewing AML compliance alerts.

Rewrite the 'Use when' clause with natural trigger phrases users actually say, e.g. 'Use when the user wants to check a crypto wallet's purity, analyze a transaction's AML risk, or review compliance alerts via AMLBot.'

Add domain keywords and synonyms (crypto wallet, transaction, AML risk, compliance) so the description surfaces for the requests users naturally make.

Dimension	Reasoning	Score
Specificity	Names the AMLBot domain but the actions are generic ('Manage data, records, and automate workflows') with no concrete capabilities like wallet-purity checks or transaction analysis, fitting the 'names domain but actions are minimal or generic' anchor.	2 / 5
Completeness	Both a 'what' ('AMLBot integration. Manage data, records, and automate workflows') and a 'when' ('Use when the user wants to interact with AMLBot data') are present, but the 'when' is generic and could be more explicit, matching the score-4 anchor rather than the concrete-trigger-phrases of 5.	4 / 5
Trigger Term Quality	'AMLBot' is a relevant keyword and 'interact with AMLBot data' gives a trigger, but it misses the natural phrases users would say (crypto wallet, AML risk, transaction purity), so it matches 'some relevant keywords but missing common variations or synonyms' rather than the fuller coverage of 4.	3 / 5
Distinctiveness Conflict Risk	Naming the specific app 'AMLBot' makes it mostly distinct with minimal conflict risk, but the generic action verbs ('manage data, records, automate workflows') create minor overlap with other integration skills, so it is 4 rather than a fully distinct 5.	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: membranedev/application-skills
Path: skills/amlbot/SKILL.md
Commit: f484c82

Reviewed: 3 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.