Name: appveyor
Rating: 56.8 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

appveyor

AppVeyor integration. Manage Projects, Accounts, Users. Use when the user wants to interact with AppVeyor data.

Quality

65%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/appveyor/SKILL.md

Quality

Content

65%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 highly actionable with concrete, copy-paste-ready CLI commands, but it is held back by an unnecessary concept-explaining intro, missing verification around destructive actions, and a large inlined reference table that should be split into a separate file.

Suggestions

Add an explicit verification/confirmation checkpoint before destructive actions (delete-project, delete-build, delete-user), e.g. confirm the target ID and state before running, and re-fetch to verify deletion.

Move the "Popular actions" table into a separate references file (e.g. references/actions.md) and keep SKILL.md as a concise overview that links to it.

Cut the opening paragraph explaining what CI/CD is and the "auth plumbing" sentence, and fix the duplicated "Update Project → get-project-settings" row in the actions table.

Dimension	Reasoning	Score
Conciseness	The opening paragraph ("AppVeyor is a continuous integration and continuous delivery (CI/CD) service...") and phrases like "so you can focus on the integration logic rather than auth plumbing" explain concepts Claude already knows and could be trimmed, plus the actions table contains a duplicated/erroneous row ("Update Project → get-project-settings") (anchor 3). It is not a 2 because the bulk of the body is concrete commands rather than padded explanation.	3 / 5
Actionability	The body provides copy-paste-ready executable commands for every common case — install, login, connection ensure, action list/run, and proxy requests — with exact flags and JSON examples (anchor 5). It is not lower because the commands are complete and directly runnable rather than pseudocode.	5 / 5
Workflow Clarity	The connection flow has a clear poll-and-check-state feedback loop, but destructive operations (delete-project, delete-build, delete-user) are run via a bare "membrane action run" with no verification checkpoint, and "skip to Step 2" references a step that does not exist (anchor 3, capped by the destructive-operations guideline). It is not a 4 because the validation gap for destructive actions is material, not minor.	3 / 5
Progressive Disclosure	No bundle files exist and the ~177-line skill inlines a large "Popular actions" reference table and detailed connection-state handling that belong in separate files, though section headers give some structure (anchor 3). It is not a 4 because there are no one-level-deep references at all and reference material is fully inlined, not appropriately split.	3 / 5
	Total	14 / 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 cleanly states what the skill does and when to use it, anchored by a distinctive product name that minimizes conflict risk. Its main weaknesses are a generic action verb and thin trigger-term coverage that misses the build/deployment language AppVeyor users actually say.

Suggestions

Replace the generic "Manage" with differentiated concrete actions, e.g. "List and start builds, deploy to environments, manage projects and collaborators".

Add the natural trigger terms users say for AppVeyor, such as "builds", "deployments", and "CI/CD", to the "Use when" clause.

Tighten the "when" clause to concrete triggers, e.g. "Use when the user wants to trigger or check AppVeyor builds, deployments, or projects."

Dimension	Reasoning	Score
Specificity	"Manage Projects, Accounts, Users" names the domain and several concrete entity targets, but the single generic verb "Manage" is applied uniformly rather than listing differentiated actions, so it is not comprehensive (anchor 3). It does not reach 4 because the actions are not distinct specific operations like "extract", "fill", or "convert".	3 / 5
Completeness	It has a clear "what" ("Manage Projects, Accounts, Users") and an explicit "Use when the user wants to interact with AppVeyor data" trigger, satisfying both halves (anchor 4). It stays at 4 rather than 5 because the "when" clause is generic ("interact with AppVeyor data") rather than concrete trigger phrases.	4 / 5
Trigger Term Quality	The keyword "AppVeyor" plus "Projects, Accounts, Users" gives some relevant terms, but it omits the natural phrases AppVeyor users actually say ("build", "deployment", "CI/CD", "trigger a build"), missing common variations (anchor 3). It is not a 4 because keyword coverage is thin and lacks the synonyms a user would naturally invoke.	3 / 5
Distinctiveness Conflict Risk	"AppVeyor integration" tied to a uniquely named product gives a clear niche with a distinct trigger and minimal conflict risk with other skills (anchor 5). No neighboring anchor fits better since the product name itself is the discriminator.	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/appveyor/SKILL.md
Commit: f484c82

Reviewed: 3 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.