Tessl • The management layer for AI agent skills

Blog Docs Log inGet started

SkillPublic

braze

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

Quality

69%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/braze/SKILL.md

Quality

Content

65%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.

This is a strong operational skill: nearly everything is an exact, executable CLI command, and the connection lifecycle is handled with real state-machine guidance. Its weaknesses are a missing safety layer around destructive actions, a dangling Step 2 reference, and detail (the action catalog and flag docs) that belongs in a references/ file rather than the main body.

Suggestions

Add validation guidance for destructive and batch actions: before running delete-users or send-messages, list the affected records (e.g. via get-segment-details / export-user-by-id), show them to the user, and confirm before executing.

Fix the dangling "skip to Step 2" reference by labeling the actual steps (e.g. make "Searching for actions" Step 2), and remove the generic Braze intro paragraph, the bare entity list, and "Use action names and parameters as needed".

Move the 20-row popular-actions catalog and the proxy flag table into a references/ file (e.g. references/actions.md), keeping SKILL.md as an overview with a pointer.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient, command-driven content, but it opens with a paragraph explaining what Braze is ("a customer engagement platform used by marketing teams..."), includes a bare entity list with no descriptions, and filler like "Use action names and parameters as needed." These could be trimmed without losing anything Claude needs.	3 / 5
Actionability	Every section gives copy-paste-ready commands with flags and realistic placeholders: install ("npm install -g @membranehq/cli@latest"), headless auth ("membrane login complete <code>"), connection setup ("membrane connection ensure 'https://www.braze.com/' --json"), action search/run with JSON input, and proxy requests with a complete flag table. The popular-actions table covers the common cases with exact action keys.	5 / 5
Workflow Clarity	The connection workflow is well sequenced with state-based checkpoints (poll with --wait, CLIENT_ACTION_REQUIRED handling, CONFIGURATION_ERROR/SETUP_FAILED error guidance), but destructive and batch actions (delete-users, send-messages) ship with no validation or confirmation guidance, which caps this score at 3. The dangling "skip to Step 2" reference — no Step 2 is ever defined — further hurts coherence.	3 / 5
Progressive Disclosure	Sections are clearly headed and navigation within the file is easy, but the ~20-row action catalog and the CLI flag documentation are inlined in SKILL.md where a references/ file would be more appropriate, and the malformed entity list (inconsistent "Variants" nesting) adds noise. No bundle files exist to offload detail.	3 / 5
	Total	14 / 20 Passed

Description

61%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 functional and clearly scoped to Braze with an explicit use-when clause, but it undersells the skill's actual capabilities. Replacing generic verbs with the concrete operations (list/create campaigns, email templates, content blocks, segments; send messages; manage subscriptions) would raise both specificity and trigger coverage.

Suggestions

Replace "Manage data, records, and automate workflows" with the concrete operations the skill supports, e.g. "List and create campaigns, Canvases, email templates, content blocks, and segments; send messages; track and delete users; manage subscription groups in Braze."

Broaden the trigger clause to natural user phrasing: "Use when the user mentions Braze, campaigns, Canvases, segments, email templates, or customer engagement messaging."

Dimension	Reasoning	Score
Specificity	The description names the domain (Braze) but the actions are minimal and generic — "Manage data, records, and automate workflows" could apply to almost any data tool. It does not list concrete capabilities like campaigns, email templates, segments, or messaging.	2 / 5
Completeness	Both a "what" ("Braze integration. Manage data, records, and automate workflows") and an explicit "when" ("Use when the user wants to interact with Braze data") are present. Not 5 because the "when" is narrow and generic, and the "what" lacks concrete trigger phrases; not 3 because the "when" is explicit rather than weakly implied.	4 / 5
Trigger Term Quality	"Braze" and "interact with Braze data" are relevant natural keywords, but common terms users would actually say — campaigns, Canvases, segments, messaging, marketing automation — are missing. Matches "some relevant keywords but missing common variations or synonyms."	3 / 5
Distinctiveness Conflict Risk	Braze is a clearly named niche product with a distinct trigger ("Braze"), so the risk of firing for the wrong skill is minimal. The generic "Manage data, records" phrasing is the only slight overlap risk, keeping it firmly in the clear-niche anchor.	5 / 5
	Total	14 / 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/braze/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.

braze

Table of Contents

Is this your skill?