Name: branch
Rating: 52 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

branch

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

Quality

57%

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/branch/SKILL.md

Quality

Content

57%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 highly actionable with concrete CLI commands and a clear connection state machine, but it suffers from token-inefficient padding (an over-explaining intro and a redundant 60-line entity list), lacks validation checkpoints for destructive operations, and keeps everything in one file with no progressive disclosure. Trimming the list and adding a verify step would substantially improve it.

Suggestions

Remove or relocate the 60-line "Branch X" entity list since dynamic discovery via `membrane action list --intent` already exposes available actions, saving significant tokens.

Add an explicit validation/verification step after running actions or proxy requests (e.g. check the `output`/error fields and confirm the result before proceeding) to satisfy the destructive-operations checkpoint.

Split the proxy flag reference and entity catalog into separate reference files linked from SKILL.md to improve progressive disclosure and navigability.

Dimension	Reasoning	Score
Conciseness	The body is noticeably verbose: an introductory paragraph over-explains what Branch is and who uses it, and a ~60-line enumerated list of "Branch X" entities duplicates capability that the documented dynamic discovery (`membrane action list --intent`) already provides, padding the token budget.	2 / 5
Actionability	It provides copy-paste-ready commands for install, login, connection, action search/run, and proxy requests, complete with flag tables and JSON output examples that cover the common cases, matching the fully-executable anchor.	5 / 5
Workflow Clarity	The install→authenticate→connect→search→run sequence is clearly laid out with a connection state machine and polling, but because proxy requests and action runs can be destructive/batch operations with no validation or verification step, workflow clarity is capped at 3 per the rubric's destructive-operations rule.	3 / 5
Progressive Disclosure	The body has section headers but is a single monolithic file with no bundle references (references/scripts/assets are absent), and the large entity list and proxy flag table are inlined rather than split into separate files, fitting the some-structure-but-should-be-separate anchor.	3 / 5
	Total	13 / 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 successfully pairs a what-clause with an explicit when-clause and leverages a named platform for distinctiveness, but its action verbs are generic and its trigger terms omit platform-specific phrasing. Tightening the actions and adding concrete Branch-domain triggers would raise it.

Suggestions

Replace generic verbs ("Manage data, records, and automate workflows") with concrete Branch capabilities such as attribution tracking, deep linking, and workflow automation.

Expand the when-clause with natural user triggers, e.g. "Use when the user wants to track app attribution, set up deep links, or query Branch data."

Add common synonyms and file/term variants (deep linking, mobile attribution, Branch API) to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	The description names the Branch domain but its actions ("Manage data, records, and automate workflows") are minimal and generic rather than concrete, matching the anchor for domain-named-but-generic actions and sitting noticeably below the specificity midpoint.	2 / 5
Completeness	It states both what it does ("Manage data, records, and automate workflows") and when to use it ("Use when the user wants to interact with Branch data"), but the when-clause is generic and could be more explicit, fitting the both-present-but-could-be-sharper anchor.	4 / 5
Trigger Term Quality	It surfaces "Branch", "data", "records", and "workflows" as relevant keywords, but lacks common variations or platform-specific terms (attribution, deep linking) users would naturally say, matching the some-keywords-but-missing-synonyms anchor.	3 / 5
Distinctiveness Conflict Risk	The named "Branch" platform and trigger "interact with Branch data" carve a mostly distinct niche with only minor overlap risk against other data-management skills, fitting the mostly-distinct anchor rather than the fully-distinct one given the generic action verbs.	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/branch/SKILL.md
Commit: f484c82

Reviewed: 4 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.