BC directus_io
Use this skill for anything involving Directus — the open-source headless CMS and backend-as-a-service. Triggers include setting up Directus (Docker, Cloud, self-hosted), using the Directus JavaScript/TypeScript SDK, integrating Directus with frontend frameworks (especially Astro, but also Next.js, Nuxt, SvelteKit), building Directus Flows and automations, generating content with AI via Directus Automate, building custom extensions (hooks, endpoints, interfaces, layouts, modules, operations), data modeling and collections, access control and permissions, file management, real-time subscriptions, REST and GraphQL API usage, troubleshooting Directus errors, and any mention of 'Directus', 'directus.io', '@directus/sdk', 'Directus Cloud', 'Directus Flows', 'Directus Automate', or 'Data Studio'. Also trigger when users mention headless CMS integration with Astro/TypeScript and Directus is a likely fit, or when they ask about CMS-powered content pipelines, dynamic page generation from a CMS, or automating content workflows with a headless backend.
As a process C 52/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
How to improve
- Shorten the description to 1024 characters.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 1
✓ No critical or high findings
Medium and low: 1
-
medium Dangerous commands
cmd-privilegereferences/troubleshooting.md:186Privilege escalation / world-writable permissionssudo chown -R 1000:1000 ./uploads ./database ./extensions
Files scanned: 9. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1057 chars, limit 1024 - warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens)
Process rating: all ten parameters 52/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 1 mutating operations with no state check
- 40Consistency. Frontmatter name (directus_io) differs from the folder (directus-io)
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Steps. 6 steps
- 100Execution cost. Instruction body is 1192 tokens
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 1057: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Structure: 9 headings
- +3Step-by-step instructions: 6 items
- +4Has examples (5 code blocks)
- +4Reference files are cited in the instructions (7 of 7)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 55.