Tessl • The management layer for AI agent skills

SkillPublic

beekeeper

Beekeeper integration. Manage data, records, and automate workflows. Use when the user wants to interact with Beekeeper 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/beekeeper/SKILL.md

Quality

Content

76%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.

A strongly actionable, token-efficient integration guide with copy-paste-ready CLI commands and thorough error-state handling for connection setup. The main defects are the dangling 'skip to Step 2' reference (no numbered steps exist) and the absence of validation checkpoints around destructive operations like delete-post and delete-user.

Suggestions

Number the workflow steps explicitly (1. Install CLI, 2. Authenticate, 3. Ensure connection, 4. Search actions, 5. Run action) so the existing 'skip to Step 2' references resolve to a real step.

Add a validation checkpoint before destructive actions from the catalog (delete-post, delete-user), e.g. 'Before deleting, run get-post/get-user to confirm the target ID, and confirm with the user for batch deletions'.

Drop the duplicated credential-refresh explanation from 'Proxy requests' (already stated in 'Working with Beekeeper') and tighten the 'Agent Types' line into a short flag note.

Dimension	Reasoning	Score
Conciseness	The body is command-first and largely free of padding — no generic concept explanations, and the intro sentence about frontline workers is genuinely unfamiliar context. Minor trimmable instances: Membrane's credential handling is explained in both 'Working with Beekeeper' and 'Proxy requests', and the rambling 'Agent Types : claude, openclaw, codex...' line. Not score 5 due to these small redundancies.	4 / 5
Actionability	Fully executable throughout: exact install command, login commands including headless completion ('membrane login complete <code>'), connection ensure/poll commands with flags, action run with JSON input syntax, proxy request flags table, and a 20-row catalog of concrete action names and keys. Copy-paste ready and covering the common cases.	5 / 5
Workflow Clarity	A real sequence exists (install → login → connect → poll states → search actions → run) with good error-state handling (CLIENT_ACTION_REQUIRED, CONFIGURATION_ERROR, clientAction fields), but the instruction 'If the returned connection has state: READY, skip to Step 2' references a step that does not exist — there is a '1b' heading but no numbered step list. Destructive actions (delete-post, delete-user) also lack validation checkpoints. The broken step reference plus missing validation fits the score-3 anchor better than score 4's 'minor validation gaps'.	3 / 5
Progressive Disclosure	No bundle files exist, and the single-file layout is well-sectioned (Overview, Install, Auth, Connecting, Searching, Popular actions, Proxy, Best practices) with no dangling references at any depth. Not score 5: at ~160 lines the popular-actions table and proxy flag table are borderline content that a references/ file could absorb, keeping SKILL.md as a tighter overview.	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 correctly names the Beekeeper domain and includes an explicit 'Use when' clause, but wastes its action slots on generic phrases ('manage data, records, automate workflows') instead of the concrete capabilities the skill actually provides. Trigger coverage relies almost entirely on the product name, missing the natural vocabulary (posts, streams, messages, users) that would help invocation.

Suggestions

Replace 'Manage data, records, and automate workflows' with the skill's concrete actions, e.g. 'Create and schedule posts, manage users and groups, send messages, and retrieve reports in Beekeeper'.

Expand the 'Use when' clause with natural trigger phrases users would actually say: 'Use when the user mentions Beekeeper, posts, streams, frontline/deskless employees, or wants to send messages or manage users'.

Add 1-2 synonyms or context words (e.g. 'frontline worker platform', 'employee communications app') so the skill triggers even when the product name is not spoken.

Dimension	Reasoning	Score
Specificity	"Manage data, records, and automate workflows" are generic actions any integration skill could claim; the body shows concrete capabilities (create/schedule posts, manage users/groups, send messages, list streams) that the description never names. It names the domain ("Beekeeper integration") but the actions are minimal and generic, matching the score-2 anchor rather than score 3, which requires 1-2 concrete named actions.	2 / 5
Completeness	Both parts are explicitly present: what ("Beekeeper integration. Manage data, records, and automate workflows") and when ("Use when the user wants to interact with Beekeeper data"). Not score 5 because the 'what' is vague and the 'when' largely restates the product name rather than giving concrete trigger phrases.	4 / 5
Trigger Term Quality	"Beekeeper" is a strong natural keyword users would say, but coverage stops there — common phrases from the skill's own body (posts, streams, messages, comments, users, frontline/deskless workers) are absent. Some relevant keywords exist but common variations and synonyms are missing, fitting the score-3 anchor.	3 / 5
Distinctiveness Conflict Risk	The distinct product name "Beekeeper" carves out a clear niche with minimal conflict risk. Not score 5 because the generic tail ("manage data, records, and automate workflows") could pull matches for unrelated data-management or workflow-automation skills.	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/beekeeper/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.

beekeeper

Table of Contents

Is this your skill?