Tessl • The management layer for AI agent skills

SkillPublic

appcircle

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

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

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

Quality

Content

57%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 a workable CLI-driven guide with genuinely executable commands and a solid connection lifecycle section covering polling, client actions, and error states. Its main weaknesses are a redundant/empty "Popular actions" section, a dangling "Step 2" reference and absent run-result validation, and an all-in-one layout with no reference files for catalog detail.

Suggestions

Merge the duplicate action-discovery instructions in "Searching for actions" and "Popular actions", and either populate that section with concrete example Appcircle actions (with real action IDs and inputs) or remove it.

Replace the dangling "skip to Step 2" references with a clearly numbered workflow (1. Install and authenticate, 2. Connect, 3. Discover actions, 4. Run or proxy) and add guidance for validating action run output and handling failed runs.

Move the module overview list and the proxy flag table into a reference file (e.g. references/actions.md) to keep SKILL.md a lean overview with one-level-deep references.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and command-driven, but "Searching for actions" and "Popular actions" duplicate the same discovery command, the 20-item module bullet list capped by "Use action names and parameters as needed." adds little value, and invocations are inconsistent between `membrane` and `npx @membranehq/cli@latest`. More than minor trimming is needed, so it sits below anchor 4.	3 / 5
Actionability	Commands are concrete and executable — `membrane connection ensure "https://appcircle.io/" --json`, `membrane action run <actionId> --connectionId=CONNECTION_ID --input '{"key": "value"}' --json`, and a proxy flag table. It falls short of anchor 5 because no real action ID or filled end-to-end example is shown, and the "Popular actions" section contains no actual popular actions.	4 / 5
Workflow Clarity	The sequence (install → login → connect → poll state → discover → run → proxy) is conveyed by section order, and connection-state handling is a genuine checkpoint, but "skip to Step 2" references a step that is never defined, and there is no validation or error handling for action run results. This matches anchor 3 (sequence present, checkpoints missing or implicit) rather than 4.	3 / 5
Progressive Disclosure	No bundle files exist; everything is inlined in a single ~155-line SKILL.md. Sections are clearly headed and navigable (above anchor 2), but catalog-style content like the module overview list and the proxy flag table would fit better in reference files, and the empty "Popular actions" section suggests content that should be split out. This matches anchor 3 rather than 4.	3 / 5
	Total	13 / 20 Passed

Description

57%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 has an explicit and functional "Use when..." trigger anchored to a distinct product name, which gives it acceptable completeness and distinctiveness. However, the capability statement is generic boilerplate that fails to convey what Appcircle actually offers (mobile CI/CD: building, testing, distributing apps) and omits most natural trigger terms a user would say.

Suggestions

Replace the generic "Manage data, records, and automate workflows" with Appcircle's concrete capabilities, e.g. "Build, test, and distribute iOS and Android apps, manage signing identities and environment variable groups, and submit builds to app stores."

Expand the trigger clause with natural user phrasing such as "Use when the user mentions Appcircle, mobile CI/CD, building or distributing iOS/Android apps, or app store submission."

Align the "when" clause with the stated capabilities — it currently covers only "interact with Appcircle data", excluding the workflow-automation use cases the "what" claims.

Dimension	Reasoning	Score
Specificity	The description names the domain ("Appcircle integration") but the stated actions — "Manage data, records, and automate workflows" — are generic and could apply to nearly any integration; no concrete capabilities (build, distribute, store submission) are named. It is above anchor 1 because the domain is named and actions are listed, but below anchor 3 because none of the actions are concrete.	2 / 5
Completeness	Both parts are present: the "what" ("Appcircle integration. Manage data, records, and automate workflows") and an explicit "when" ("Use when the user wants to interact with Appcircle data"). It falls short of anchor 5 because the "what" is vague and the "when" clause covers only "data" interaction, narrower than the stated capabilities.	4 / 5
Trigger Term Quality	"Appcircle" is a strong natural trigger a user would actually say, but the description misses common variations and synonyms users would use ("build apps", "distribute", "iOS/Android", "mobile CI/CD", "TestFlight"). Matches anchor 3 (some relevant keywords, missing variations) rather than 4, since coverage beyond the product name is thin.	3 / 5
Distinctiveness Conflict Risk	"Appcircle" is a distinct product name creating a clear niche with a direct trigger, so wrong-skill triggering is unlikely. It is not anchor 5 because the templated generic action phrasing ("manage data, records, and automate workflows") is identical to sibling app-integration skills and carries minor overlap risk within that family.	4 / 5
	Total	13 / 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/appcircle/SKILL.md
Revision: f484c82

Reviewed: 16 days ago

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.

appcircle

Table of Contents

Is this your skill?