Name: tookan
Rating: 49.6 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

tookan

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

Quality

53%

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/tookan/SKILL.md

Quality

Content

50%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 excels at actionability with complete, copy-paste CLI commands and a well-handled connection state machine, but it is severely hurt by a ~210-line padded entity enumeration that wrecks conciseness and misuses progressive disclosure. The action-execution workflow also lacks the validation checkpoints expected for destructive/batch Tookan operations.

Suggestions

Delete the ~210-line 'Task Question *' enumeration (or move it to a references/entities.md) so the body stays lean; Claude can discover real actions via `membrane action list`.

Add a validation/verification step to the 'Running actions' workflow: after `membrane action run`, check the `output`/error fields and confirm the Tookan-side effect before reporting success.

Move detailed proxy-flag reference or large action catalogs into a separate reference file and link to it from SKILL.md to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body inlines a ~210-item, auto-generated-looking enumeration of 'Task Question X' bullets (lines 23-231) that adds near-zero value, matching the 'severely verbose; heavily padded' anchor.	1 / 5
Actionability	It provides copy-paste-ready, executable commands across the full workflow (install, login, connection ensure/get, action list/run, request proxy) plus a flags table, covering the common cases as the top anchor requires.	5 / 5
Workflow Clarity	The connection flow has a clear sequence with an explicit state-feedback loop (READY / CLIENT_ACTION_REQUIRED with re-poll), but running actions on a delivery platform is destructive/batch-capable and the 'Running actions' section lacks any validation/verification step, so the cap applies.	3 / 5
Progressive Disclosure	Section structure is reasonable and no broken nested references exist, but the large 210-entity enumeration is inlined bulk content that belongs in a separate reference file (or should be removed), matching 'content that should be separate is inline.'	3 / 5
	Total	12 / 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 correctly pairs a what-clause with an explicit 'Use when' trigger and anchors distinctiveness on the Tookan brand name. Its main weakness is generic, abstract action verbs and missing Tookan-domain synonyms (delivery, dispatch, tasks) that would strengthen both specificity and trigger quality.

Suggestions

Replace generic verbs with concrete Tookan capabilities, e.g. 'Create and assign delivery tasks, manage field-service agents, track dispatches, and automate workflows.'

Add natural trigger terms users actually say: 'Use when the user wants to manage Tookan delivery tasks, dispatch agents, track field-service teams, or automate Tookan workflows.'

Keep the existing 'Use when...' clause (it satisfies the completeness trigger requirement) but make the trigger phrase reference concrete Tookan entities rather than 'interact with Tookan data'.

Dimension	Reasoning	Score
Specificity	The description names the Tookan domain and lists actions ('Manage data, records, and automate workflows'), but those actions are generic abstractions rather than concrete capabilities, matching the 'names the domain but actions are minimal or generic' anchor.	2 / 5
Completeness	Both a 'what' ('Manage data, records, and automate workflows') and an explicit 'when' ('Use when the user wants to interact with Tookan data') are present, but the trigger is generic rather than concrete phrases, fitting 'has both what and when; when could be more specific.'	4 / 5
Trigger Term Quality	It includes the strong proper-noun trigger 'Tookan' plus an explicit trigger clause, but omits common domain synonyms users would say (delivery, dispatch, field service, tasks), matching the 'some relevant keywords but missing common variations' anchor.	3 / 5
Distinctiveness Conflict Risk	The named platform 'Tookan' gives a clear niche with low conflict risk, but the surrounding verbs ('manage data, records, automate workflows') are generic enough to create minor overlap with other data-management 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/tookan/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.