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.
In this repository40 other files it gives its agents.
- address-pr-feedbackSkill
- architectureSkill
- code-reviewSkill
- code-structureSkill
- competitive-briefSkill
- contract-guardSkill
- debugSkill
- deep-workSkill
- dependency-upgradeSkill
- deploy-checklistSkill
- diagnoseSkill
- documentationSkill
- explain-pr-step-by-stepSkill
- feedback-checkpointSkill
- grill-meSkill
- grill-with-docsSkill
- handoffSkill
- improve-codebase-architectureSkill
- incident-responseSkill
- memory-managementSkill
- observabilitySkill
- plan-criticSkill
- plan-from-rfcSkill
- pr-babysitterSkill
- prototypeSkill
- rebase-onto-mainSkill
- releaseSkill
- security-reviewSkill
- setup-engineering-skillsSkill
- squash-and-pushSkill
- synthesize-researchSkill
- system-designSkill
- tddSkill
- tech-debtSkill
- testing-strategySkill
- to-issuesSkill
- to-prdSkill
- triageSkill
- verification-before-completionSkill
- zoom-outSkill
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
- Distinctive: line 33
If the queue was accurate, say so in one line — do not invent corrections.
≈ “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.
Files
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
- Current message — every deliverable in the latest user message, including sub-clauses.
- 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).
- Existing queue — compare against current todos. Classify each ask: tracked & correct status / tracked but stale status / untracked.
- Backfill — add every untracked ask; correct stale statuses honestly (nothing "completed" that wasn't verified; nothing "in progress" that isn't being worked).
- 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.
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
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.

