CD schedulala
Install, connect, and use Schedulala to schedule and publish social media posts to 12 platforms (Twitter/X, Instagram, TikTok, LinkedIn, YouTube, Facebook, Threads, Bluesky, Pinterest, Mastodon, Telegram, Google Business Profile). Use when the user asks to install or set up Schedulala, or wants to create, schedule, preview, or bulk-plan social posts, post photos/videos/PDFs, auto-post a first comment (link-in-first-comment), check post status or analytics, reply to or moderate comments, monitor keywords, or repurpose YouTube videos. Works through the schedulala CLI (any agent with a shell), the hosted MCP connector (claude.ai / ChatGPT, with interactive widgets), or the local @schedulala/mcp-server (Claude Desktop, Claude Code, Cursor, OpenClaw). Encodes key setup, the per-platform rules (TikTok privacy + postMode, Instagram media, YouTube titles, Pinterest boards, character limits), and the safe workflow draft → validate/preview → confirm → publish → verify.
Install, connect, and use Schedulala to schedule and publish social media posts to 12 platforms (Twitter/X, Instagram, TikTok, LinkedIn, YouTube, Facebook…
As a process D 46/100 · Unfinished process — References files that are not bundled: ../../examples/
What is at stake
The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.
The skill tells the agent to hide things from you: not to show errors, not to mention actions, to report differently from what was done. You lose the ability to see what the agent really did.
Transparency beats a smooth answer. If the goal is to hide technical noise, ask the agent to "summarise briefly", not to "not mention".
How to improve
- Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
- 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
-
high Concealment
en-hide-from-userreferences/media.md:20Instruction to hide actions from the userquality is preserved end-to-end. Never tell the user the widget doesn't
Files scanned: 6. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: ../../examples/
Process rating: all ten parameters 46/100
- 0Tools and files. 1 referenced file(s) missing: ../../examples/
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 27 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 70When it triggers. States when to use, but not when not to
- 100Steps. 24 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3861 tokens
- 100Progress reporting. Reports progress
- 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
- +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 973: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +4Structure: 10 headings
- +3Step-by-step instructions: 24 items
- +4Has examples (3 code blocks)
- +4Reference files are cited in the instructions (3 of 4)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.