AC orshot
Generate images, PDFs, and videos from templates with Orshot — via the REST API, SDKs (Node/Python/PHP/Ruby), the remote MCP server, or no-code tools (Zapier, Make, n8n, Airtable), and wire those renders into a recurring automation. Use whenever the user mentions Orshot, connects Orshot to an AI agent or MCP client, wants a render to run unattended on a schedule or trigger, or needs to programmatically produce marketing visuals, OG images, social carousels, certificates/invoices/tickets as PDF, or video from templates — including when migrating from Bannerbear, Placid, Creatomate, RenderForm, Abyssale, or similar. Always load this skill for Orshot tasks, even simple ones, because it carries gotchas (modifications key by parameterId, multi-page needs a page1@ prefix, video output needs video elements in the template) that otherwise cause failed renders. Not for generating standalone AI images with no template or Orshot involved.
Generate images, PDFs, and videos from templates with Orshot — via the REST API, SDKs (Node/Python/PHP/Ruby), the remote MCP server, or no-code tools (Zapier…
As a process C 63/100 · Has gaps — weak spots: inputs and preconditions, execution cost, running it twice
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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 · 0
✓ No critical or high findings
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 15372 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 63/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 60 mutating operations with no state check
- 40Execution cost. Instruction body is 15372 tokens: crowds the task out of the window
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash, web, python, node) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 85Steps. 202 steps, 3 vague phrases
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 14 top-level sections: this looks like several domains in one skill
- high The skill tells the model to perform an irreversible action with no human approval
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
- +3Description length 941: 120–800 characters recommended
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +4Structure: 104 headings
- +3Step-by-step instructions: 202 items
- +3Output format is stated explicitly
- +4Has examples (52 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 78.