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

Blog Docs Log in Get started

helpwise

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

Quality

74%

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/helpwise/SKILL.md

Quality

Content

82%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 commands throughout and a clear connect-to-run workflow. Its weaknesses are mild verbosity in a few prose patches, a lack of validation guidance around destructive conversation operations, and the absence of reference files for the inlined action/flag catalogs.

Suggestions

Add a validation/verification step for destructive operations, e.g. confirm a conversation is the intended target and verify the deletion succeeded via the command output before reporting success.

Move the Popular actions table and proxy flag table into a references/ file (e.g. ACTIONS.md) and link to it from the body to keep SKILL.md a lean overview.

Trim explanatory prose like "This is the fastest way to get a connection… The URL is normalized…" down to the essential behavior, and fix the Step 1b / Step 2 numbering so the sequence reads cleanly.

Dimension	Reasoning	Score
Conciseness	Most sections are lean command blocks with brief, useful commentary (state transitions, --wait, --json), but a few prose passages ("This is the fastest way to get a connection…") and the inlined 15-row action table and proxy-flag table add tokens that could be trimmed.	4 / 5
Actionability	Every workflow gives concrete, copy-paste-ready membrane commands with flags and example inputs (connection ensure, action list --intent, action run --input, request), covering the common search/run/proxy cases.	5 / 5
Workflow Clarity	The connect -> poll -> search -> run flow is clearly sequenced with state-transition branches and a re-poll feedback loop, but destructive actions ("Permanently delete a conversation") ship with no validation/verification guidance, and the Step 1b/Step 2 numbering is slightly inconsistent.	4 / 5
Progressive Disclosure	The single self-contained document is well-organized with clear headers, but there are no bundle/reference files, so the bulk Popular-actions catalog and proxy-flag table are inlined rather than split into a one-level-deep reference.	4 / 5
	Total	17 / 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 names the app and gives an explicit use-trigger, but it understates the skill's real capabilities and lacks the natural user phrases (shared inbox, conversations, replies, tags) that would help it surface. Specificity and trigger-term coverage are the main weaknesses.

Suggestions

Replace "Manage Organizations" with the actual concrete actions the skill supports, e.g. "Manage conversations, reply to messages, tag and assign conversations, and search/create contacts in Helpwise."

Add natural trigger phrases users would say, such as "shared inbox," "reply to a conversation," "list mailboxes," or "search Helpwise contacts."

Tighten the Use-when clause to name the concrete objects (mailboxes, conversations, contacts) rather than the generic "interact with Helpwise data."

Dimension	Reasoning	Score
Specificity	"Manage Organizations" names the domain plus one concrete action, but the description omits the conversation/message/contact/mailbox operations the skill actually covers, so coverage is not comprehensive.	3 / 5
Completeness	It states a "what" ("Helpwise integration. Manage Organizations.") and an explicit "when" ("Use when the user wants to interact with Helpwise data."), but the trigger is generic rather than concrete.	4 / 5
Trigger Term Quality	"Helpwise" and "interact with Helpwise data" provide a relevant keyword, but the natural user phrases surfaced by the body (shared inbox, reply to conversation, list mailboxes, search contacts) are absent, missing common variations.	3 / 5
Distinctiveness Conflict Risk	Naming the specific app Helpwise alongside a scoped "Use when… interact with Helpwise data" trigger carves a clear niche with minimal overlap risk against other skills.	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/helpwise/SKILL.md
Commit: f484c82

Reviewed: ~17 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.