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

Blog Docs Log in Get started

teamwork

Teamwork integration. Manage Organizations, Users. Use when the user wants to interact with Teamwork 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/teamwork/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 content is a well-structured, highly actionable CLI integration guide with clear connection-state workflows and feedback loops. Its main weaknesses are an unnecessary marketing intro and entity-list padding, plus absent validation guidance for destructive actions.

Suggestions

Remove the opening marketing paragraph and trim the 33-item entity bullet list, or move it to a reference file, to reduce tokens that do not aid execution.

Add a validation checkpoint before destructive actions (e.g. confirm task IDs via list-tasks before running delete-task or complete-task) to lift workflow clarity.

Include one fully concrete worked example that ties a real action key from the popular-actions table (e.g. create-task) through membrane action run with a sample --input payload.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete commands, but it opens with a marketing paragraph ("Teamwork is a project management platform... used by businesses of all sizes to improve productivity") and a 33-item entity list plus filler like "Use action names and parameters as needed" that Claude does not need.	3 / 5
Actionability	It provides copy-paste-ready commands for install, login, connection ensure, action list, action run with --input JSON, and proxy requests, plus a concrete popular-actions table; the minor gap is that run examples use abstract placeholders (<actionId>, CONNECTION_ID) with no fully concrete worked example.	4 / 5
Workflow Clarity	The connect-then-search-then-run sequence is clear with explicit state branches (READY, BUILDING, CLIENT_ACTION_REQUIRED, CONFIGURATION_ERROR) and polling feedback loops, but there is no validation/checkpoint guidance before destructive actions like delete-task or complete-task.	4 / 5
Progressive Disclosure	No bundle files exist and the body is organized into clear, well-labeled sections with inline quick-reference tables; the large entity list and tables are reasonably placed inline, with only minor organization gaps since the skill is longer than the simple-skill threshold.	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 includes an explicit trigger clause and a distinct brand niche, but its capability statement is generic ("Manage Organizations, Users") and omits the task/project actions that dominate the skill body. Trigger keywords cover the brand but not the natural task vocabulary users would say.

Suggestions

Replace the generic "Manage Organizations, Users" with the skill's actual primary actions, e.g. "Create and manage tasks, tasklists, projects, and time entries in Teamwork."

Broaden the trigger phrase beyond "interact with Teamwork data" to include natural terms users say, such as tasks, projects, tasklists, and time tracking.

Align the description's entities with the body: "Organizations" is not among the listed capabilities, which makes the what-statement slightly misleading.

Dimension	Reasoning	Score
Specificity	Names the domain ("Teamwork integration") and two entities ("Manage Organizations, Users") but the action verb "Manage" is generic and the entities listed are not even the skill's primary capabilities (tasks/projects), so it sits just above the minimal/generic anchor.	3 / 5
Completeness	Both a "what" ("Manage Organizations, Users") and an explicit "when" clause ("Use when the user wants to interact with Teamwork data") are present; the trigger is generic rather than concrete, fitting the "both present, when could be more specific" anchor.	4 / 5
Trigger Term Quality	It surfaces the natural brand keyword "Teamwork" and a trigger ("Use when the user wants to interact with Teamwork data"), but misses the common task phrases users actually say (tasks, projects, time entries), matching the "some relevant keywords but missing variations" anchor.	3 / 5
Distinctiveness Conflict Risk	"Teamwork" is a distinct named brand and the trigger is scoped to interacting with Teamwork data, giving it a clear niche with minimal conflict 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/teamwork/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.