Name: missive
Rating: 60 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

missive

Missive integration. Manage Organizations. Use when the user wants to interact with Missive data.

Quality

70%

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/missive/SKILL.md

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.

The content is highly actionable with concrete, runnable Membrane CLI commands and a clear connect-then-act workflow that includes state validation and error handling. Weaknesses are marketing-style prose that pads the token budget and dangling step references ("Step 2", "1b") that break the otherwise clear sequence.

Suggestions

Trim explanatory/marketing prose (the Missive overview paragraph, "focus on integration logic rather than auth plumbing", "burn less tokens") to tighten token efficiency.

Fix the broken step numbering: either label a real "Step 2" / "1a" or reword the "skip to Step 2" and "1b" references to concrete section names.

Consider moving the proxy flags table and full action-discovery detail into a reference file so the overview stays lean and navigable.

Dimension	Reasoning	Score
Conciseness	The body is mostly commands but carries several padded prose passages ("collaborative email and messaging platform... more efficiently", "focus on the integration logic rather than auth plumbing", "This will burn less tokens"), fitting the mostly-efficient-with-some-unnecessary-explanation anchor; not a 4 because the over-explanation appears in multiple sections.	3 / 5
Actionability	It provides copy-paste ready commands for the common cases (install, login, connection ensure, action list/run, request) with parameter-passing examples, matching the fully-executable anchor; not lower because guidance is concrete and runnable rather than pseudocode.	5 / 5
Workflow Clarity	The install→auth→connect→poll-state→search→run sequence has explicit validation (state checks, polling, CLIENT_ACTION_REQUIRED/CONFIGURATION_ERROR handling), but references to a never-labeled "Step 2" and an unanchored "1b" are minor sequence gaps, so it sits below the fully-checkpointed 5.	4 / 5
Progressive Disclosure	As a single self-contained file with well-organized sections and no bundle files to navigate, structure is good and appropriately placed, but it exceeds the under-50-line simple-skill case and inlines reference-like material (proxy flags table, popular actions) that could be split, keeping it at 4 rather than 5.	4 / 5
	Total	16 / 20 Passed

Description

66%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 short and includes an explicit "Use when" trigger plus a named domain, but its action list is thin and its trigger keywords lack the natural terms (email, conversations, contacts) users would actually say. Distinctiveness is strong because Missive is a unique product.

Suggestions

Expand the action list beyond "Manage Organizations" to concrete capabilities (e.g., search conversations, manage contacts, apply labels) for higher specificity.

Add natural trigger terms users would say, such as "email", "shared inbox", "conversations", or "contacts", rather than only "Missive data".

Tighten the "when" clause to name concrete scenarios (e.g., "Use when the user wants to search or manage Missive conversations, contacts, or labels").

Dimension	Reasoning	Score
Specificity	Names the domain (Missive) and one concrete action target ("Manage Organizations"), matching the anchor for 1-2 concrete actions without being comprehensive; not a 2 because it specifies a named entity to act on, not a fully generic verb.	3 / 5
Completeness	Both "what" ("Missive integration. Manage Organizations.") and "when" ("Use when the user wants to interact with Missive data") are explicitly present, but the when-clause is generic and could be more specific, landing above the midpoint rather than at 5.	4 / 5
Trigger Term Quality	"interact with Missive data" supplies a relevant natural phrase, but common variations users would actually say (email, messaging, conversations, contacts) are missing, fitting the anchor for some keywords but lacking synonyms.	3 / 5
Distinctiveness Conflict Risk	"Missive" is a unique named product with a clear niche and distinct triggers, giving minimal conflict risk with other skills; it is not a 4 because the product name itself disambiguates strongly.	5 / 5
	Total	15 / 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/missive/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.