CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

action-builder

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

Quality

72%

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/action-builder/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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.

A solidly actionable, command-first skill body that sequences the connection workflow well, including explicit state handling and re-poll feedback loops. Its weaknesses are minor: a dangling 'Step 2' reference, mis-leveled headings, an implicit actionId-vs-Key mapping, and a small amount of introductory padding.

Suggestions

Fix the dangling navigation: either label a 'Step 2' section (e.g., Searching for actions) or replace 'skip to Step 2' with the actual section name, and renumber/rename '1b' to match a real 'Step 1'.

Promote 'Searching for actions', 'Running actions', and 'Proxy requests' to consistent heading levels so they are not visually nested under 'Popular actions', or demote 'Popular actions' to h3.

Clarify how to obtain an actionId when running actions — state explicitly that the 'Key' column in the Popular actions table (or the id from 'action list' results) is what gets passed to 'membrane action run'.

DimensionReasoningScore

Conciseness

The body is mostly lean, executable commands and tables, but includes minor padding such as the intro about 'no-code/low-code platform... business users and citizen developers' and asides like 'so you can focus on the integration logic rather than auth plumbing' that could be trimmed.

4 / 5

Actionability

Nearly all guidance is copy-paste ready (npm install, membrane login, connection ensure, action list/run with --input examples, request flag table), but the 'Popular actions' table exposes a 'Key' column while 'action run' takes an <actionId>, leaving the id-to-key mapping implicit.

4 / 5

Workflow Clarity

The install → login → connection → search → run sequence is clear with explicit state-based branching (READY, CLIENT_ACTION_REQUIRED with a re-poll feedback loop, CONFIGURATION_ERROR/SETUP_FAILED with error-field guidance), but 'skip to Step 2' references a step label that does not exist, section '1b' has no '1a', and the heading level of 'Popular actions' breaks the 'Working with Action Builder' flow.

4 / 5

Progressive Disclosure

No bundle files exist (references/, scripts/, assets/ are absent) and none are referenced, yet the ~150-line body is organized into well-labeled sections with the bulk detail (proxy flags, client actions) reasonably placed inline; minor gaps are the inconsistent heading hierarchy and the 14-row actions table that could live in a reference file.

4 / 5

Total

16

/

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 has a clear niche via the product name and includes an explicit 'Use when' clause, but its capability statement is generic and its trigger guidance is circular ('use when they want to interact with Action Builder data'). It distinguishes itself mainly by the product name rather than by specific, concrete capabilities.

Suggestions

Replace generic verbs with concrete capabilities, e.g. 'Create, update, and list people, tags, and campaigns in Action Builder; run and automate workflow actions.'

Make the when-clause non-circular and richer with natural user terms, e.g. 'Use when the user mentions Action Builder, or wants to manage campaigns, people, tags, or person connections in Action Builder.'

Keep the description in third person and avoid padding like 'integration' as a standalone capability noun — let the concrete actions carry the specificity.

DimensionReasoningScore

Specificity

'Manage data, records, and automate workflows' names the domain (Action Builder) but the actions are generic — 'manage' and 'automate workflows' could describe almost any integration platform, with no concrete verbs like create, update, list, or tag records. Not 3 because no action is concretely specified.

2 / 5

Completeness

Both what ('Manage data, records, and automate workflows') and when ('Use when the user wants to interact with Action Builder data') are present, but the when-clause is circular and generic — it restates the product name rather than giving concrete trigger phrases. Fits anchor 4 ('when could be more explicit or specific'); not 5 because triggers lack concrete, varied phrases.

4 / 5

Trigger Term Quality

'Action Builder' is a strong product-name trigger and 'data', 'records', 'workflows' add some relevance, but common natural variations users would say (campaign, people, contacts, tags, no-code, automation) are missing. Matches 'some relevant keywords but missing common variations or synonyms'; not 4 because keyword coverage beyond the product name is thin.

3 / 5

Distinctiveness Conflict Risk

Naming the specific product 'Action Builder' creates a clear niche with minimal conflict risk when the app is mentioned, but the generic 'automate workflows' phrasing could overlap with other automation/integration skills when the app is not named. Fits 'mostly distinct; minor overlap risk with closely related skills'; not 5 because the broad automation wording is not fully distinctive.

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

membranedev/application-skills

Path

skills/action-builder/SKILL.md

Revision

f484c82

Reviewed

Table of Contents

DiscoveryImplementationValidation

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.

Claim skill