Name: todoist
Rating: 62.4 (1 reviews)
Author: membranedev

todoist

Todoist integration. Manage Projects, Users, Labels, Filters, Sections, Comments. Use when the user wants to interact with Todoist data.

Quality

73%

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/todoist/SKILL.md

Quality

Content

68%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 concrete, executable Membrane CLI commands and a clear connection workflow. It loses points on conciseness (padded intro and an uninformative action table) and on workflow clarity because destructive actions lack verification steps.

Suggestions

Drop the "Todoist is a popular to-do list..." intro paragraph and the proxy mechanics over-explanation; Claude already knows what Todoist is.

Add a validation/verification step before destructive actions (e.g., confirm the resolved task/project id and re-list after delete) so destructive workflows clear the workflow-clarity cap.

Trim or column-prune the "Popular actions" table — every row currently reads "No description", adding ~20 lines of tokens with no guidance; either give each a one-line purpose or link to a reference file.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete commands, but includes unneeded preamble Claude already knows ("Todoist is a popular to-do list..."), over-explains proxy mechanics, and spends ~20 table rows that all say "No description" for little value.	3 / 5
Actionability	It provides copy-paste-ready commands throughout (install, login, connection ensure, action list/run, request) with concrete flags and a full JSON-input example, covering the common cases the agent will hit.	5 / 5
Workflow Clarity	The connection sequence is well-staged with state polling checkpoints, but the skill exposes destructive actions (delete-task, delete-project, etc.) with no validation/verification step before running them, which caps workflow clarity at 3 per the destructive-operations rule.	3 / 5
Progressive Disclosure	Content is a single well-organized file with clear section headers and no nested references, and no bundle files are present; the bulky 20-row action table is the main item that could be trimmed or moved to keep navigation tighter.	4 / 5
	Total	15 / 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 and distinctive, clearly naming the Todoist domain and the entities it manages with an explicit "Use when..." trigger. Its main weakness is the repeated generic verb "Manage" and a somewhat broad trigger clause that could name concrete use cases.

Suggestions

Replace the repeated "Manage" with distinct concrete verbs (e.g., create, list, update, and delete Tasks, Projects, Labels, Sections, Comments) to lift specificity toward 5.

Broaden the "when" clause with concrete user phrasings, e.g. "Use when the user wants to create or list tasks, manage projects, or organize to-dos in Todoist."

Add natural synonym triggers such as "to-do list", "tasks", or "reminders" so the trigger matches how users actually phrase the request.

Dimension	Reasoning	Score
Specificity	"Manage Projects, Users, Labels, Filters, Sections, Comments" lists several specific entities the skill acts on, but the single generic verb "Manage" repeats rather than enumerating distinct concrete actions, leaving a minor coverage gap.	4 / 5
Completeness	It answers both "what" (Todoist integration managing the listed entities) and "when" (explicit "Use when..." clause), but the "when" is generic ("interact with Todoist data") and could name concrete trigger scenarios more specifically.	4 / 5
Trigger Term Quality	The natural term "Todoist" and the trigger phrase "Use when the user wants to interact with Todoist data" give good keyword coverage; it lacks synonyms or sub-feature triggers (tasks, projects) that users would also say.	4 / 5
Distinctiveness Conflict Risk	"Todoist integration" names a specific product niche with a distinct proper-noun trigger, making conflict with other skills minimal.	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/todoist/SKILL.md
Commit: f484c82

Reviewed: ~21 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.