agentleFS
Sign inStart free
seranking-planableseranking-planable/smm-skills/skills/pending-approvals-roundup/SKILL.md

pending-approvals-roundup

Skill3 starsChanged 5 months agoMITView on GitHub

Fetch and summarize all posts pending approval across one or more Planable workspaces. Use this skill whenever the user asks about approvals, wants to know what's waiting for review, says things like "what needs my approval", "show me pending posts", "what's waiting for sign-off", "approval queue", "morning check-in", or "what posts are stuck". Also activate when the user asks for a daily or weekly content status across clients. Always use this skill for approval-related queries that touch Planable.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 4 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Ask (or infer from context):

    line 27
  2. Very specific:

    If the user wants a broader view, query NOT_APPROVED and PARTIAL_APPROVED together.

    line 55
  3. Distinctive:

    After showing results, offer:

    line 89
  4. Distinctive:

    Do NOT offer to approve posts — approval actions are not available via the connector.

    line 93
  5. Very specific:

    Many workspaces: If list_workspaces returns more than 10, ask the user to confirm scope before fetching each one.

    line 99
  6. Distinctive:

    No workspace specified: Default to checking the 5 most recently active workspaces unless the user says "all clients."

    line 100
  7. Very specific:

    Scheduled posts with errors: If WITH_ERRORS posts appear in results, call them out separately — these are likely blocking issues.

    line 101

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Pending approvals roundup

Surface all posts waiting for approval across one or more Planable workspaces, so nothing gets missed.

How this skill works

  1. Identify which workspaces to check
  2. Fetch posts filtered by approval status
  3. Summarize clearly — grouped by workspace/client, with post previews and context

Step 1: Scope the check

Ask (or infer from context):

  • Which workspaces? — a specific client, a list, or all workspaces
  • Whose approvals? — posts pending the user's own approval (PENDING_MY_APPROVAL) or all pending posts (NOT_APPROVED, PARTIAL_APPROVED)

Default behavior if not specified: fetch PENDING_MY_APPROVAL across all workspaces (or the most recently active ones if there are many).

Step 2: Fetch pending posts

For each workspace in scope:

list_posts(
  workspaceId,
  approvalStatus: ["PENDING_MY_APPROVAL"]   // or NOT_APPROVED, PARTIAL_APPROVED
)

Approval status reference:

StatusMeaning
PENDING_MY_APPROVALPosts where this user is a required approver
NOT_APPROVEDPosts with no approvals yet
PARTIAL_APPROVEDPosts with some but not all required approvals
REQUESTED_BY_MEPosts where this user requested approval from others

If the user wants a broader view, query NOT_APPROVED and PARTIAL_APPROVED together.

Step 3: Organize and present results

If results exist, group by workspace (client). For each post show:

  • Platform/page name
  • Post preview (first 100–150 chars of textPreview)
  • Scheduled date (if set) — flag posts that are scheduled soon (within 24–48 hours)
  • Current approval status
  • Number of approvals received vs. required (if available)

Sort order within each workspace: most urgently scheduled first, then by creation date.

Format:

📋 [Workspace name]
  • [Platform] — "[Post preview...]"
    Scheduled: [date] ⚠️ (if within 48h)
    Status: [approval status]

  • [Platform] — "[Post preview...]"
    No date set
    Status: Partially approved (1/2)

If no pending posts, say so clearly. Don't pad the response.

Step 4: Optional follow-up actions

After showing results, offer:

  • "Want me to show you the full text of any of these?"
  • "Should I check a specific workspace in more detail?"

Do NOT offer to approve posts — approval actions are not available via the connector.

Edge cases

  • Many workspaces: If list_workspaces returns more than 10, ask the user to confirm scope before fetching each one. Fetching 20+ workspaces sequentially is slow and may not be what they want.
  • No workspace specified: Default to checking the 5 most recently active workspaces unless the user says "all clients."
  • Scheduled posts with errors: If WITH_ERRORS posts appear in results, call them out separately — these are likely blocking issues.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free