CB codivupload-social-manager
Social media scheduler, cross-poster, and content calendar for OpenClaw. Schedule social media posts, publish content, cross-post to multiple platforms, automate social media posting, and manage a content calendar across YouTube, Instagram, Facebook, X (Twitter), TikTok, Threads, and Pinterest from one OpenClaw skill — turn your local AI agent into an autonomous social media manager covering 7+ launched social platforms with Bluesky in active rollout. Post to YouTube, post to Instagram, post to Facebook, post to X (Twitter), post to TikTok, post to Threads, post to Pinterest — single- prompt posting and multi-platform cross-posting from one OpenClaw skill. YouTube post automation and YouTube Shorts uploader with bulk publish and BYOP for unlimited YouTube API quota; Instagram post scheduler, Instagram Reels publisher, and Instagram carousel poster with AI captions; Facebook post scheduler and Facebook Page publisher with multi-page agency support; X post scheduler, tweet scheduler, X (Twitter) thread poster, schedule tweets, post a tweet, tweet thread automation — with long-form 25K-character support on X Premium / Premium+ accounts, polls, image and video tweets, quote tweets, and BYOK for dedicated rate limits via your own X Developer App; TikTok post automation with Direct Post and Draft modes; Threads post scheduler; Pinterest pin scheduler; cross-platform publisher and multi-platform poster across all of the above. Content calendar, queue, scheduled posting, draft management, AI caption generation, best-time-to-post analytics, agency multi- workspace + RBAC with whitelabel branded OAuth for client portfolios, presigned upload flow for media up to 5GB, 50+ platform-specific override parameters, webhook notifications, 24/7 managed YouTube live streaming. Buffer alternative, Hootsuite alternative, Later alternative, Sprout Social alternative, Post Bridge alternative, Upload-Post alternative, Mixpost alternative, Postiz alternative, Ayrshare alternative — built A
As a process B 67/100 · Nearly there — weak spots: inputs and preconditions, execution cost
How to improve
- Shorten the description to 1024 characters.
- 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 · 6
✓ No critical or high findings
Medium and low: 6
-
low Obfuscation
obf-base64-blobSKILL.md:74Long base64-looking blob (quoted — discussed, not commanded)metadata.openclaw.dependencies.optional: [{name: "codivupload-mcp", pinned_version: "2.0.0", inte…12: "pK0r8XkR2M/brfn…DfA==quoted -
low Concealment
en-hide-from-userSKILL.md:212Instruction to hide actions from the user (negated — the text forbids it)| Generate `curl` / SDK code samples | None — code is text in chat for the user to read | Use `$CODIVUPLOAD_API_KEY` placeholder, never echo the actual key. Show generated code for review; do not sile
negated -
low Exfiltration
net-credential-useSKILL.md:212Credential used in a network call (verify the destination is the intended service) (documentation table row)| Generate `curl` / SDK code samples | None — code is text in chat for the user to read | Use `$CODIVUPLOAD_API_KEY` placeholder, never echo the actual key. Show generated code for review; do not sile
table -
low Exfiltration
net-credential-useSKILL.md:274Credential used in a network call (verify the destination is the intended service) (quoted — discussed, not commanded)- **Never** echo, log, paste, or include the key in chat output, error messages, or generated code samples — use the literal `$CODIVUPLOAD_API_KEY` placeholder when showing curl examples.
quoted -
low Obfuscation
obf-base64-blobSKILL.md:284Long base64-looking blob (quoted — discussed, not commanded)- Integrity sha512 (verify): `pK0r8XkR2M/brfn…DfA==` — `npm view co…@….0.0 dist.integrity`
quoted -
low Obfuscation
obf-base64-blobSKILL.md:321Long base64-looking blob (quoted — discussed, not commanded)- Tarball integrity (sha512): `pK0r8XkR2M/brfn…DfA==` (verify with `npm view co…@….0.0 dist.integrity`)
quoted
Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 3808 chars, limit 1024 - warning
body-longSKILL.md body ≈ 12701 tokens (recommended < 5000); move details to references/ - note
description-budgetdescription takes 3808 of the ~15000-char shared budget for all skills - note
frontmatter-keyunknown frontmatter key "metadata.openclaw.os" - note
frontmatter-keyunknown frontmatter key "metadata.openclaw.requires.bins" - note
frontmatter-keyunknown frontmatter key "metadata.openclaw.requires.config" - note
frontmatter-keyunknown frontmatter key "metadata.openclaw.permissions.network" - note
frontmatter-keyunknown frontmatter key "metadata.openclaw.permissions.scope" - note
frontmatter-keyunknown frontmatter key "metadata.openclaw.permissions.summary" - note
frontmatter-keyunknown frontmatter key "metadata.openclaw.permissions.recommended_key_scope" - note
frontmatter-keyunknown frontmatter key "metadata.openclaw.permissions.technical_boundary" - note
frontmatter-keyunknown frontmatter key "metadata.openclaw.dependencies.optional"
Process rating: all ten parameters 67/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 40Execution cost. Instruction body is 12701 tokens: crowds the task out of the window
- 60Tools and files. Uses tools (bash, web, python, node) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 85Steps. 116 steps, 1 vague phrases
- 100Failures and branches. 13 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 13 top-level sections: this looks like several domains in one skill
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 3807: 120–800 characters recommended
- +1No license
- +2Single-language instructions
- +4Structure: 50 headings
- +3Step-by-step instructions: 116 items
- +3Output format is stated explicitly
- +4Has examples (21 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 43.