Name: repsly
Rating: 53.6 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

repsly

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

Quality

60%

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/repsly/SKILL.md

Quality

Content

63%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 is highly actionable with executable Membrane CLI commands and a solid connect-and-poll workflow. Its main weaknesses are a verbose inlined entity catalog that burns tokens and the absence of any split-out reference files for that catalog.

Suggestions

Move the 80-item entity/"X Photo" catalog into a references/ file (e.g. ENTITIES.md) and link to it, cutting the inline token cost.

Label "Step 2" (the action search/run stage) so the "Skip to Step 2" jumps resolve, and add a short end-to-end checklist.

Drop the generic Repsly marketing intro sentence or condense it to one line to improve conciseness.

Dimension	Reasoning	Score
Conciseness	The ~80-item bullet catalog of entities and "X Photo" variants is a large padded block Claude does not need and that inflates the token budget, matching the "noticeably verbose; several unnecessary padded sections" anchor; it is not 3 because the padding is substantial rather than a minor trim, and not 1 because the CLI instructions themselves are lean.	2 / 5
Actionability	Concrete copy-paste commands are given for every stage ("npm install -g @membranehq/cli@latest", "membrane connection ensure ...", "membrane action run <actionId> ...", "membrane request CONNECTION_ID /path"), covering the common cases; this matches the "fully executable; copy-paste ready" anchor and is not below 5 because the examples are complete and runnable.	5 / 5
Workflow Clarity	There is a clear install → authenticate → connect → poll-until-ready → search → run sequence with an explicit state feedback loop (READY/BUILDING/CLIENT_ACTION_REQUIRED/CONFIGURATION_ERROR and re-polling), matching the "clear sequence with most checkpoints present" anchor; it is not 5 because "Skip to Step 2" references a step that is never labeled and there is no consolidated checklist.	4 / 5
Progressive Disclosure	The file has reasonable section headers but the 80-line entity catalog is inlined content that clearly belongs in a separate reference file and no bundle files exist, matching the "content that should be separate is inline" anchor; it is not 4 because the bulk catalog is not split out, and not 2 because section structure is present rather than monolithic.	3 / 5
	Total	14 / 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 pairs a clear trigger ("Use when the user wants to interact with Repsly data") with a distinct product name, giving it solid completeness and distinctiveness. Its weakness is generic, non-concrete capability language and thin trigger-term coverage beyond the product name.

Suggestions

Replace generic verbs with concrete Repsly actions, e.g. "Sync orders and visits, pull forms and retail audits, manage reps and territories."

Add natural trigger synonyms beyond the product name, such as "field sales", "mobile CRM", or "Repsly API".

Tighten the "what" to list 3-4 specific operations so completeness can reach a 5.

Dimension	Reasoning	Score
Specificity	"Manage data, records, and automate workflows" names the Repsly domain but the actions are generic abstractions rather than concrete operations, matching the "names the domain but actions are minimal or generic" anchor; it is not a 3 because no genuinely concrete actions (e.g. "sync orders", "pull visit forms") are listed.	2 / 5
Completeness	It states both a "what" ("Manage data, records, and automate workflows") and an explicit "Use when..." trigger, matching the "has both what and when; when could be more explicit" anchor; it is not 5 because the "what" is vague rather than concrete, and not 3 because a real trigger clause is present.	4 / 5
Trigger Term Quality	"Use when the user wants to interact with Repsly data" surfaces the natural product keyword "Repsly" but offers no synonyms or variations, fitting the "some relevant keywords but missing common variations" anchor; it is below 4 because coverage is limited to a single product name.	3 / 5
Distinctiveness Conflict Risk	"Repsly" is a unique named product so the skill is largely distinct with minimal conflict risk, matching the "mostly distinct; minor overlap risk" anchor; it is not 5 because the surrounding language ("Manage data, records") is generic and could overlap with other CRM/data skills.	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/repsly/SKILL.md
Commit: f484c82

Reviewed: 5 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.