Name: teamgate
Rating: 57.599999999999994 (1 reviews)
Author: membranedev

teamgate

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

Quality

66%

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/teamgate/SKILL.md

Quality

Content

67%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 Membrane CLI commands and a solid connect-to-ready workflow including error-recovery polling, but it is held back by redundant sections, inferable product prose, and the lack of concrete Teamgate-specific action examples.

Suggestions

Trim inferable context — the "Teamgate is a CRM software..." paragraph and the "so you can focus on the integration logic rather than auth plumbing" prose — and de-duplicate the `action list` command shared between "Searching for actions" and "Popular actions".

Replace the placeholder "Popular actions" discovery command with concrete Teamgate examples (e.g. create a lead, list deals, update a contact) so the common cases are covered end-to-end.

Label the post-connection step that "skip to Step 2" refers to, and add a brief validation note for action/proxy results (check the `output` field / HTTP status) to complete the workflow checkpoints.

Dimension	Reasoning	Score
Conciseness	It includes unnecessary explanation Claude can infer (the "Teamgate is a CRM software... used by small to medium-sized businesses" paragraph, the "auth plumbing" prose) and duplicates the `action list` command across "Searching for actions" and "Popular actions", fitting anchor 3 (mostly efficient but with unnecessary explanation that could be tightened) rather than anchor 4 (only minor instances).	3 / 5
Actionability	It provides many copy-paste-ready commands (`membrane connection ensure`, `npx @membranehq/cli connection get <id> --wait --json`, `membrane action run ... --input '...'`, `membrane request ...`) plus a full proxy-flag table, but `--intent "QUERY"` and the "Popular actions" section only show generic discovery rather than concrete Teamgate examples, fitting anchor 4 (mostly executable, minor gaps) and not anchor 5 (specific examples don't cover the common Teamgate cases).	4 / 5
Workflow Clarity	The connect-to-ready flow is well sequenced with a real feedback loop (poll `BUILDING` -> handle `CLIENT_ACTION_REQUIRED` -> user acts -> "poll again... to check if the state moved to READY" -> handle `CONFIGURATION_ERROR`), but "skip to Step 2" references an unlabeled step (the section is "1b") and running/proxy actions lack validation checkpoints, fitting anchor 4 (clear sequence, most checkpoints, minor gaps) rather than anchor 5.	4 / 5
Progressive Disclosure	No bundle files exist; the single ~140-line file is organized into clear sections (Overview, Install, Authentication, Connecting, Searching, Popular actions, Proxy requests, Best practices) with no nested references, fitting anchor 4 (good structure, content appropriately placed) — not 5 because the simple-skill exception only applies under 50 lines and there are no one-level-deep external references.	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 answers both what and when with an explicit trigger and is highly distinct thanks to the named brand, but its capability verbs are generic and it underuses the natural Teamgate vocabulary (CRM, leads, contacts, deals) that the body itself mentions.

Suggestions

Replace the generic verbs ("Manage data, records, and automate workflows") with concrete Teamgate actions such as create/update leads, manage contacts, move deals through the pipeline, and search records.

Add the natural trigger terms users actually say — e.g. "CRM", "leads", "contacts", "deals", "pipeline" — rather than relying on the single phrase "interact with Teamgate data".

Dimension	Reasoning	Score
Specificity	It names the domain ("Teamgate integration") and lists a few actions ("Manage data, records, and automate workflows"), but the actions are generic rather than concrete (e.g. no create/update/search verbs), fitting anchor 3 over anchor 2 (multiple actions listed, not minimal) and below anchor 4 (actions are vague, not specific).	3 / 5
Completeness	Both are present: "Manage data, records, and automate workflows" (what) and "Use when the user wants to interact with Teamgate data" (when, an explicit trigger clause), fitting anchor 4; not 5 because the "what" is generic rather than concrete trigger phrases.	4 / 5
Trigger Term Quality	The natural trigger is the brand name "Teamgate" plus "interact with Teamgate data", but the description omits common variations users say (CRM, leads, contacts, deals, pipeline) that the body actually references, matching anchor 3 (some relevant keywords, missing synonyms) rather than anchor 4 (good coverage).	3 / 5
Distinctiveness Conflict Risk	"Teamgate" is a specific named product, giving a clear niche with a distinct trigger and minimal overlap risk with other skills, matching anchor 5.	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/teamgate/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.