AB content-pipeline-provisioner
Self-serve AI content pipeline skill for OpenClaw. Sets up and runs a fully automated social media content engine on your own OpenClaw instance using your own API keys and accounts. Automates TikTok daily posts (AI-generated slides), Twitter/X 5 posts per day in your voice, newsletter 3x per week via MailerLite, daily blog post published to your site, and morning/evening Telegram briefings. Use when setting up a content pipeline for any product or brand, or when asked to 'provision pipeline for [product]', 'set up content pipeline', 'run my content engine', 'start posting for [product]', 'go live [slug]', 'pause pipeline', or 'resume pipeline'.
As a process B 70/100 · Nearly there — weak spots: result and completion, when it triggers, running it twice
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 instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".
If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.
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 · 1
✓ No critical or high findings
Medium and low: 1
-
medium Exfiltration
exfil-webhook-urlreferences/setup-checklist.md:46Webhook / callback URL commonly used for exfiltration (verify the destination) (the skill's own vendor host)3. Get your chat ID: message your bot, then fetch https://api.telegram.org/bot{TOKEN}/getUpdatesvendor-host
Files scanned: 7. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 70/100
- 0Result and completion. Does not say what the result is
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 8 mutating operations with no state check
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Tools and files. No external tools needed
- 100Steps. 34 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1826 tokens
- 100Progress reporting. Reports progress
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)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 652: enough signal without eating the budget
- +4Structure: 18 headings
- +3Step-by-step instructions: 34 items
- +4Has examples (3 code blocks)
- +4Reference files are cited in the instructions (4 of 5)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.