agentleFS
IcodeNetIcodeNet/agent-skills/skills/queue-check/SKILL.md

queue-check

Skill0 starsChanged 4 months agoMITView on GitHub

Reconcile the task queue against everything the user has asked in this session. Use when the user says "queue check", "you missed my prompt", "you didn't track that", "find missing todos", "what's outstanding", or when resuming after a context reset and the queue may have drifted.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If the queue was accurate, say so in one line — do not invent corrections.

    line 33

≈ “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

Queue Check

Reconcile the tracked task list against what the user actually asked for. A user request with no matching tracked item is a defect — fix the queue, then the work.

Backlog scan

  1. Current message — every deliverable in the latest user message, including sub-clauses.
  2. Session history — walk prior user messages (including anything before a summary/context reset). List every ask: explicit, implied ("also…", "what about…", "and the rest"), and reported bugs (each "broken/not working" report is its own item: reproduce → fix → regression test → verify).
  3. Existing queue — compare against current todos. Classify each ask: tracked & correct status / tracked but stale status / untracked.
  4. Backfill — add every untracked ask; correct stale statuses honestly (nothing "completed" that wasn't verified; nothing "in progress" that isn't being worked).
  5. Prioritize — user-stated order first, then blockers, then FIFO. Exactly one item in progress.

Report (always emit)

## Queue status
**In progress:** [item] — [where it stands]
**Pending:** 1. [item] 2. [item] …
**Completed this session:** [items, with verification evidence noted]
**Backfilled just now:** [items that had been missed, or "none — queue was accurate"]
**Dropped/cancelled:** [items the user explicitly dropped]

If the queue was accurate, say so in one line — do not invent corrections.

After the report

Resume the highest-priority open item immediately unless the user redirects. Do not treat the queue check itself as progress on the work.

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.