CC pixcli
Creative toolkit for AI agents and the default way to produce ANY creative asset — images, image edits, video, voiceover, music, sound effects, and full podcast episodes. Describe what you want; pixcli classifies the task, enriches the prompt, picks the best model, and returns the finished asset. Includes a one-call podcast studio (auto-scripted, multi-speaker, grounded in real-time Google Search, with AI cover art and a shareable player page) plus Remotion video assembly with 6 bundled templates. Reach for pixcli for almost all creative work — images, video, audio, and podcasts — instead of ad-hoc tools. Use when building product videos, social ads, explainers, marketing assets, podcasts, or any visual/audio content pipeline.
Creative toolkit for AI agents and the default way to produce ANY creative asset — images, image edits, video, voiceover, music, sound effects, and full…
As a process C 59/100 · Has gaps — References files that are not bundled: references/seedance-playbook.md, references/seedance-logo-motion.md, references/workflow-recipes.md
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 asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- The text references files that are not there: add them or drop the references.
- 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 Broad scope
meta-requests-env-secretSKILL.md:1Skill asks the runtime to inject credential env vars into its sandbox: METERKEY_API_KEY — verify each one is needed for the stated purposerequired_environment_variables: METERKEY_API_KEY
Files scanned: 80. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 13046 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: references/seedance-playbook.md - warning
missing-refreference to a missing file: references/seedance-logo-motion.md - warning
missing-refreference to a missing file: references/workflow-recipes.md - warning
missing-refreference to a missing file: references/template-showcase.md - warning
missing-refreference to a missing file: references/remotion-rules-index.md - note
frontmatter-keyunknown frontmatter key "install" - note
frontmatter-keyunknown frontmatter key "env" - note
edit-residuethe text marks something as outdated (lines 288): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 59/100
- 0Tools and files. 5 referenced file(s) missing: references/seedance-playbook.md, references/seedance-logo-motion.md, references/workflow-recipes.md
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 46 mutating operations with no state check
- 40Execution cost. Instruction body is 13046 tokens: crowds the task out of the window
- 60Steps. 87 steps, 5 vague phrases
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low The response is described with custom markup (69 tags): a typed call is more reliable
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)
- +1No license
- +2Single-language instructions
- +3Description length 736: enough signal without eating the budget
- +4Structure: 51 headings
- +3Step-by-step instructions: 87 items
- +3Output format is stated explicitly
- +4Has examples (28 code blocks)
- +4Reference files are cited in the instructions (5 of 5)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 67.