Tessl • The management layer for AI agent skills

Blog Docs Log inGet started

SkillPublic

beeple

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

Quality

72%

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/beeple/SKILL.md

Quality

Content

75%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 delivers a highly actionable, mostly lean guide to driving Beeple through the Membrane CLI, with a coherent connect-then-act workflow and real state-based error checkpoints. Its main flaws are small: a dangling "Step 2" reference with broken step numbering, a "Popular actions" section that lists no actions, and a few padded passages.

Suggestions

Fix the broken step navigation: replace "skip to **Step 2**" and the orphan "#### 1b." heading with explicit, consistently numbered step headings (e.g. "Step 1: Connect", "Step 2: Discover actions", "Step 3: Run actions").

Either populate "Popular actions" with 2-3 concrete examples for the listed entities (e.g. listing meetings, fetching participants) or drop the section, since it currently just repeats the `action list` command from "Searching for actions".

Trim the content-free "Beeple Overview" bullet list and the marketing phrasing around Membrane credentials to tighten token usage.

Dimension	Reasoning	Score
Conciseness	The bulk of the body is lean, executable CLI commands and state-handling guidance, but there is minor waste: the near-empty "Beeple Overview" section (five lines naming Meeting/Participant/Document with no content), marketing fluff ("so you can focus on the integration logic rather than auth plumbing", "This will burn less tokens"), and a background intro sentence. Not 5 because these padded passages could be trimmed without losing information.	4 / 5
Actionability	Concrete copy-paste-ready commands throughout: install command, login flow including headless completion, `membrane connection ensure` with a real URL, `--wait` polling, action run with a JSON `--input` example, and a full proxy flag table. Not 5 because the "Popular actions" section promises examples but delivers only the discovery command, and the listed entities (Meeting, Participant, Document) never get worked examples.	4 / 5
Workflow Clarity	There is a clear end-to-end sequence (install → authenticate → connect → poll connection state → search actions → run → proxy fallback) with state-based checkpoints (`READY` / `CLIENT_ACTION_REQUIRED` / `CONFIGURATION_ERROR`, `--wait` long-polling, `error` field inspection) and an explicit re-poll loop after user actions. Not 5 because "If the returned connection has state: READY, skip to Step 2" references a numbered step that does not exist — headings are unlabeled except a dangling "1b" — leaving the sequence's checkpoints partially incoherent.	4 / 5
Progressive Disclosure	A single ~140-line SKILL.md with clear section headers and no bundle files; the content is operationally relevant so nothing is forced inline that belongs elsewhere, and navigation is easy. Not 5 because of minor organization gaps: the orphaned "1b" numbering, the near-empty Overview section, and a duplicated `action list` command under both "Searching for actions" and "Popular actions".	4 / 5
	Total	16 / 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 "Use when" trigger and a distinctive app name, but its capability statements are generic boilerplate that could describe any integration. It would reliably trigger on the word "Beeple" but gives the model little concrete information about what the skill can actually do (meetings, participants, documents per the body).

Suggestions

Replace the generic "Manage data, records, and automate workflows" with concrete capabilities drawn from the body, e.g. "List and manage Beeple meetings, participants, and documents, and run Beeple API actions".

Expand the trigger clause to include the natural terms users would say: "Use when the user mentions Beeple, or wants to work with Beeple meetings, participants, documents, or records".

Remove the circular "interact with Beeple data" phrasing in favor of specific trigger situations (syncing records, automating Beeple workflows, querying meeting data).

Dimension	Reasoning	Score
Specificity	"Manage data, records, and automate workflows" names the domain (Beeple) but the actions are entirely generic abstract language, with no concrete operations listed. The skill body itself reveals the real capabilities (meetings, participants, documents), none of which appear in the description.	2 / 5
Completeness	Both "what" ("Manage data, records, and automate workflows") and an explicit "when" clause ("Use when the user wants to interact with Beeple data") are present. Not 5 because the "what" is vague and the "when" is circular ("interact with Beeple data") rather than giving concrete trigger phrases.	4 / 5
Trigger Term Quality	Relevant keywords ("Beeple", "data", "records") are present but coverage is thin, missing the natural phrases and synonyms users would actually say such as meetings, participants, documents, or scheduling. Not 4 because the natural-term coverage is limited to essentially the app name.	3 / 5
Distinctiveness Conflict Risk	"Beeple" is a distinctive named app giving a clear niche trigger, but the middle sentence ("Manage data, records, and automate workflows") mirrors generic integration-skill phrasing, creating minor overlap risk with other app-integration skills. Not 5 because the generic action phrasing weakens the distinct trigger surface.	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/beeple/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.

beeple

Table of Contents

Is this your skill?