Name: kanbanize
Rating: 58.4 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

kanbanize

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

Quality

67%

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/kanbanize/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 well-structured and highly actionable, with concrete membrane commands, a thorough action table, and a clear connection-state feedback loop. Its main weakness is the absence of validation/verification steps around destructive actions, which caps workflow clarity.

Suggestions

Add a confirmation/verification step to the 'Running actions' workflow for destructive and batch operations — e.g. verify the target card ID and confirm with the user before delete-card, and re-fetch the card after update-card to confirm the change.

Trim the introductory paragraph explaining what the Kanban method is and fix the 'Agent Types' sentence, since these explain concepts Claude already knows or read as padded.

Consider moving the full popular-actions table or the proxy flags into a one-level-deep reference file (e.g. ACTIONS.md) to keep SKILL.md as a tighter overview, signalling the reference clearly with a link.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean — copy-paste membrane commands, a flags table, and an action table — with only minor over-explanation such as the intro paragraph on what the Kanban method is and the awkward 'Agent Types' sentence, fitting 'efficient; minor instances that could be trimmed' rather than the padded 3 or the fully-lean 5.	4 / 5
Actionability	Concrete executable commands with --json flags, a 17-row popular-actions table, and proxy flag reference give mostly copy-paste-ready guidance; the minor gap is placeholder-filled commands (CONNECTION_ID, <actionId>) and a generic input example, fitting 'mostly executable with minor gaps' rather than the fully-specified 5.	4 / 5
Workflow Clarity	The install→authenticate→connect→poll-for-READY→search→run sequence is clearly laid out with a state-polling feedback loop, but destructive actions (Delete Card, Update Card) are listed without any confirm-before-delete or post-run verification step, so the destructive-operation cap holds this at 3 per the rubric guideline.	3 / 5
Progressive Disclosure	A single well-organized file with clear section headers (Overview, Connecting, Searching, Popular actions, Proxy, Best practices) and no bundle files; the ~160 lines are navigable, fitting 'good structure; most content appropriately placed; minor organization gaps' rather than the multi-file-reference 5.	4 / 5
	Total	15 / 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 third-person, has an explicit 'Use when' trigger, and names a clearly distinct branded niche, so activation guidance is solid. It is held back by thin action coverage (only 'Manage Organizations') and sparse task-level trigger keywords.

Suggestions

Expand the 'what' beyond 'Manage Organizations' to the core entities users act on — e.g. 'Manage boards, columns, cards, comments, and users in Kanbanize' — to lift specificity.

Add concrete task-level trigger terms so users' natural phrasing matches, e.g. 'Use when the user wants to manage Kanbanize boards, cards, comments, logged time, or tags.'

Make the when-clause more concrete than 'interact with Kanbanize data' by listing the specific operations that should activate this skill.

Dimension	Reasoning	Score
Specificity	"Manage Organizations" names one concrete-ish action over the "Kanbanize integration" domain, but it is the only action and is generic; this matches the '1-2 concrete actions, not comprehensive' anchor rather than the multi-action 4 or the minimal-action 2.	3 / 5
Completeness	Both "what" (Kanbanize integration, Manage Organizations) and an explicit "Use when the user wants to interact with Kanbanize data" trigger are present, but the when-clause is generic and the what is narrow, fitting 'has both but when could be more explicit' rather than the concrete-trigger-phrases 5.	4 / 5
Trigger Term Quality	The natural trigger users say ("Kanbanize") is present, but coverage is thin — only the brand name repeated with "interact with Kanbanize data", missing task-level synonyms like boards, cards, tasks, or projects, so it fits the 'some relevant keywords but missing variations' anchor.	3 / 5
Distinctiveness Conflict Risk	"Kanbanize" is a specific branded application, giving a clear niche with a distinct trigger and minimal overlap risk with other skills, matching the 'clear niche with distinct triggers' anchor.	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/kanbanize/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.