AB ai-director
This skill should be used when the user wants help with film/video directing tasks, including storyboard design, shot planning, dialogue staging, camera setup, continuity checking, editing rhythm, and pre-visualization. Triggered by requests like "design a storyboard for this scene", "plan the camera setup for a 2-person dialogue", "check if this sequence breaks the 180-degree rule", "suggest editing patterns for this scene", "help me visualize this script", or any directorial pre-production task. Based on Steven D. Katz's Film Directing Shot by Shot (1991) and the structured knowledge base at the JSON/MD knowledge files in the user's Downloads directory.
As a process B 66/100 · Nearly there — weak spots: inputs and preconditions, failures and branches, progress reporting
How to improve
- 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: 14. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "agent_created"
Process rating: all ten parameters 66/100
- 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
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 85Steps. 75 steps, 2 vague phrases
- 100Tools and files. No external tools needed
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2482 tokens
- 100Running it twice. No mutating operations
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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
- +4Description does not say when NOT to use the skill (false activations)
- +1No license
- +2Single-language instructions
- +5Description quotes 5 example trigger phrases
- +3Description length 663: enough signal without eating the budget
- +4Structure: 26 headings
- +3Step-by-step instructions: 75 items
- +3Output format is stated explicitly
- +4Has examples (0 code blocks)
- +4Reference files are cited in the instructions (8 of 8)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 95.