Tessl • The management layer for AI agent skills

SkillPublic

aikido-security

Aikido Security integration. Manage data, records, and automate workflows. Use when the user wants to interact with Aikido Security 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/aikido-security/SKILL.md

Quality

Content

61%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 delivers copy-paste-ready Membrane commands with strong handling of connection states and authentication edge cases, making it genuinely usable. Its weaknesses are a padded marketing intro, a broken step-numbering scheme ("Step 2" and "1b" refer to headers that don't exist), and a vague entity overview that adds no actionable guidance.

Suggestions

Fix the dangling workflow references: either number the steps explicitly (Step 1: connect, Step 2: discover/run) or replace "skip to **Step 2**" and "#### 1b" with descriptive section links so the sequence is unambiguous.

Delete or compress the platform-background intro paragraph and the filler line "Use action names and parameters as needed" — Claude doesn't need Aikido's marketing positioning to execute the commands.

Make the "Aikido Security Overview" entity list actionable by mapping each entity (Finding, Finding Note, Repository, User) to a example action-list intent or endpoint, and add one worked end-to-end example (search → run) with realistic output.

Dimension	Reasoning	Score
Conciseness	The body is mostly command-focused, but the opening paragraph ("Aikido Security is a vulnerability management platform designed to help startups and SMBs... It's used by companies that want an easy-to-use, all-in-one security solution") is marketing-style background irrelevant to execution, and "Use action names and parameters as needed" is pure filler. Not level 4 because these padded sections could clearly be trimmed.	3 / 5
Actionability	Concrete, executable commands appear throughout ("membrane connection ensure \"https://www.aikido.dev/\" --json", "membrane action run <actionId> --connectionId=CONNECTION_ID --input '{\"key\": \"value\"}' --json") plus a complete proxy flag table. Not level 5: no worked example with a real action ID or output, and invocation is inconsistent ("membrane" vs "npx @membranehq/cli").	4 / 5
Workflow Clarity	A sequence exists (install → login → connection ensure → poll state → search actions → run), and the state machine (READY / CLIENT_ACTION_REQUIRED / CONFIGURATION_ERROR) with re-polling is well handled. However, "skip to Step 2" and the "#### 1b" header reference a numbering scheme that is never defined — no Step 1 or Step 2 headers exist — leaving the mid-workflow path ambiguous, which fits anchor 3 (sequence present, checkpoints/gaps in structure).	3 / 5
Progressive Disclosure	The single-file skill has no bundle files and no nested references; sections (Install, Authentication, Connecting, Searching, Running, Proxy, Best practices) are well organized and the content is appropriately inline for this size. Not level 5 because the bare entity list under "Aikido Security Overview" and the detailed clientAction block are minor organization gaps that could be better integrated or split out.	4 / 5
	Total	14 / 20 Passed

Description

50%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 names the target platform and includes an explicit "Use when" clause, but the capability list is boilerplate ("Manage data, records, and automate workflows") with no concrete Aikido-specific actions or natural trigger terms like "vulnerabilities" or "security findings". It is functional but reads like a template rather than a purpose-built description.

Suggestions

Replace "Manage data, records, and automate workflows" with concrete Aikido capabilities, e.g. "Query vulnerability findings, finding notes, and repositories, and manage users" — matching the entities the skill body itself lists.

Add natural trigger terms to the when-clause, e.g. "Use when the user mentions Aikido, wants to check or triage security findings, or asks about vulnerable repositories."

Tighten the description to third-person concrete verbs and drop the generic "automate workflows" tail to reduce overlap with other Membrane integration skills.

Dimension	Reasoning	Score
Specificity	"Manage data, records, and automate workflows" names the Aikido Security domain but the actions are generic filler — no concrete operations like "list findings", "scan repositories", or "manage users" are stated. It fits anchor 2 ("Names the domain but actions are minimal or generic") rather than 3, which requires 1-2 genuinely concrete actions.	2 / 5
Completeness	Both elements are explicit: the what ("Aikido Security integration. Manage data, records, and automate workflows") and the when ("Use when the user wants to interact with Aikido Security data"). Not 5 because the when-clause is generic ("interact with... data") rather than concrete trigger phrases; not 3 because the "Use when" trigger is explicitly present, not merely implied.	4 / 5
Trigger Term Quality	The only substantive keyword is "Aikido Security" (plus generic "data" and "records"); natural phrases a user would say — "vulnerabilities", "security findings", "issues", "repositories" — are absent. Not level 3 because there are no relevant synonyms or variations beyond the product name itself.	2 / 5
Distinctiveness Conflict Risk	"Aikido Security" is a specific platform with distinct triggers, so overlap risk is low. Not 5 because the tail "Manage data, records, and automate workflows" is boilerplate shared by virtually every integration skill, leaving the product name as the only real discriminator.	4 / 5
	Total	12 / 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/aikido-security/SKILL.md
Revision: f484c82

Reviewed: 16 days 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.

aikido-security

Table of Contents

Is this your skill?