Name: directus
Rating: 61.6 (1 reviews)
Author: membranedev

directus

Directus integration. Manage Collections, Users, Presets, Dashboards, Flows. Use when the user wants to interact with Directus data.

Quality

73%

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/directus/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.

A well-structured, largely executable integration guide with a clear connect-and-run workflow and explicit state checkpoints. Its weaknesses are mild verbosity in the overview, inconsistent step numbering, and a large inlined action table that has no progressive-disclosure offload.

Suggestions

Trim the opening Directus explainer and the Overview concept bullets; assume Claude knows what a headless CMS is and keep only Membrane/Directus-specific details.

Fix step numbering: label the connect step "Step 1"/"Step 2" consistently so the "skip to Step 2" reference resolves.

Move the Popular actions table into a references/actions.md file and link to it, reducing inline token weight.

Dimension	Reasoning	Score
Conciseness	The body opens by explaining what Directus is and who uses it ("Directus is a headless CMS that provides a GraphQL and REST API...") and includes filler like "Use action names and parameters as needed", which Claude already knows. Mostly efficient with executable commands, but several sections could be tightened.	3 / 5
Actionability	Concrete copy-paste commands throughout ("npm install -g @membranehq/cli@latest", "membrane connection ensure", "membrane action run", "membrane request") plus a popular-actions table with keys. Not a 5 because some placeholders (<actionId>, CONNECTION_ID) and the proxy flags lack end-to-end runnable examples for the common cases.	4 / 5
Workflow Clarity	Clear sequence (install → login → connect → poll for READY → search actions → run) with explicit state-based checkpoints (READY/BUILDING/CLIENT_ACTION_REQUIRED/CONFIGURATION_ERROR) and a re-poll feedback loop. Not a 5 because step numbering is inconsistent ("skip to Step 2" references an unlabeled step; "#### 1b" appears without a 1a/Step 1 header).	4 / 5
Progressive Disclosure	No bundle files exist (references/scripts/assets are empty), and the body is organized into clear sections (Overview, Working with Directus, Install, Auth, Connecting, Popular actions, Proxy, Best practices). Not a 5 because the large inlined Popular actions table is content that could live in a separate reference file for a skill of this length.	4 / 5
	Total	15 / 20 Passed

Description

78%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.

A focused, third-person description that names the domain and several concrete entities and includes an explicit "Use when" trigger. Its main weakness is that actions are uniform "manage" verbs and the trigger clause is broad rather than scenario-specific.

Suggestions

Replace the generic "manage" verb with distinct concrete verbs (e.g., create, update, list, query) so capabilities read as specific actions.

Broaden the trigger clause beyond "interact with Directus data" to concrete scenarios (e.g., querying collections, managing users/roles, running flows).

Dimension	Reasoning	Score
Specificity	"Manage Collections, Users, Presets, Dashboards, Flows" lists several concrete actions within a named domain, with minor coverage gaps (no read/write/create distinction). Not a 5 because the actions are uniformly generic "manage" verbs rather than the fuller set of concrete operations.	4 / 5
Completeness	Both "what" (manage Collections/Users/Presets/Dashboards/Flows) and "when" ("Use when the user wants to interact with Directus data") are explicitly present. Not a 5 because the trigger phrase is somewhat generic ("interact with Directus data") rather than enumerating concrete trigger situations.	4 / 5
Trigger Term Quality	Includes natural product-specific terms ("Collections, Users, Presets, Dashboards, Flows", "Directus data") a user would say, but misses common synonyms and has no file-extension-style triggers. Not a 5 because coverage is product-named rather than comprehensively varied.	4 / 5
Distinctiveness Conflict Risk	"Directus integration" plus Directus-specific entity names carves a clear niche with distinct triggers and minimal overlap with other skills. Voice is third person ("Manage...", "the user wants"), so no voice penalty applies.	5 / 5
	Total	17 / 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/directus/SKILL.md
Commit: f484c82

Reviewed: ~18 hours 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.