Name: sender
Rating: 65.60000000000001 (1 reviews)
Author: membranedev

sender

Sender integration. Manage Persons, Organizations, Deals, Leads, Projects, Activities and more. Use when the user wants to interact with Sender data.

Quality

78%

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/sender/SKILL.md

Quality

Content

78%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 CLI commands and a solid validation/polling workflow for connection setup. It is held back by minor redundancy, a dangling 'Step 2' reference, and a monolithic structure with no progressive disclosure into reference files.

Suggestions

Fix the step numbering: the 'skip to Step 2' references point to no clearly labeled 'Step 2' and '1b' is orphaned from a missing '1' — relabel the connection flow as a coherent numbered sequence.

Move the proxy flag reference table and the clientAction spec into a separate references file (e.g. references/proxy.md) and link to it from the body to improve progressive disclosure.

De-duplicate the 'action list --intent=QUERY' command, which appears nearly verbatim in both 'Searching for actions' and 'Popular actions'.

Dimension	Reasoning	Score
Conciseness	The body is command-focused and mostly lean, but has minor redundancy (the 'action list --intent=QUERY' command is repeated across sections) and an unused 'Sender Overview' entity list that could be trimmed.	4 / 5
Actionability	It provides copy-paste-ready, fully executable commands for every common case (login, connection ensure, polling, action list/run, proxy) with a concrete flag table and explicit JSON-output conventions.	5 / 5
Workflow Clarity	The connection-readiness flow has a clear sequence with explicit state validation (READY/CLIENT_ACTION_REQUIRED/CONFIGURATION_ERROR) and a re-poll feedback loop, but inconsistent step numbering ('1b', a dangling 'Step 2' reference) introduces minor gaps.	4 / 5
Progressive Disclosure	It has decent section structure but no bundle files and no external references at all; reference-style content (the proxy flag table and the clientAction spec) is inlined in the single ~140-line file rather than split out.	3 / 5
	Total	16 / 20 Passed

Description

78%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 specific, distinct, and covers both what the skill does and when to use it, anchored by concrete Sender entity types. Its main weakness is a generic single trigger clause ('interact with Sender data') rather than richer natural-language triggers.

Suggestions

Replace the generic 'interact with Sender data' trigger with concrete scenarios, e.g. 'Use when the user wants to manage Sender contacts, deals, leads, campaigns, or activities.'

Add common synonyms users would actually say (e.g. 'contacts' alongside 'Persons', 'campaigns', 'newsletters') to broaden natural trigger coverage.

Vary the verbs beyond the single 'Manage' (e.g. 'Create and update Persons, Organizations, Deals...') to convey concrete actions rather than one generic one.

Dimension	Reasoning	Score
Specificity	It names the Sender domain and six concrete entity types ('Persons, Organizations, Deals, Leads, Projects, Activities'), but the single generic verb 'Manage' applied to the list keeps it just shy of the comprehensive multi-verb anchor 5.	4 / 5
Completeness	It explicitly answers both 'what' (Sender integration managing named entities) and 'when' ('Use when the user wants to interact with Sender data'), but the trigger clause is single and generic rather than enumerating concrete trigger scenarios like the anchor 5 example.	4 / 5
Trigger Term Quality	It surfaces the product name 'Sender', 'Sender data', and several natural entity keywords (Persons, Deals, Leads), giving good coverage, though 'interact with Sender data' is generic and common phrasings like 'contacts' or 'campaigns' are absent.	4 / 5
Distinctiveness Conflict Risk	It targets a named product ('Sender integration') with specific Sender entities, giving it a clear niche and minimal overlap risk with other skills.	5 / 5
	Total	17 / 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/sender/SKILL.md
Commit: f484c82

Reviewed: ~2 hours 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.