feedback-checkpoint
Skill0 starsChanged 4 months agoMITView on GitHub
Status checkpoint to unstick a run: detect loops and stuck states, report Done / Next / Blocking, and recover one step at a time. Use when the user asks for a status update, says "checkpoint", or when you suspect you are looping or stuck.
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
- grill-meSkill
- grill-with-docsSkill
- handoffSkill
- improve-codebase-architectureSkill
- incident-responseSkill
- memory-managementSkill
- observabilitySkill
- plan-criticSkill
- plan-from-rfcSkill
- pr-babysitterSkill
- prototypeSkill
- queue-checkSkill
- 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
4 rules. About 0 are common, 4 are distinctive, and 0 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.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 12
Run this to take stock and unstick a session.
- Distinctive: line 24
Do only that one step, then stop and wait for user feedback.
- Distinctive: line 25
Keep the task list up to date.
- Distinctive: line 29
Stop and wait for user direction (e.g.
≈ “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
Feedback Checkpoint
Run this to take stock and unstick a session.
- Check for a loop. Have you done 3+ similar actions in a row, repeated the same failing step, or kept re-reading/re-editing the same area without progress? If yes, treat as loop.
- Check for stuck. Are you blocked (error, missing type, unclear requirement) or have you spent more than 2–3 turns on the same task without finishing? If yes, treat as possibly stuck.
Respond in one of these ways:
If in a loop:
- Say you may be in a loop, what you were trying to do, and the single next step you will take.
- Do only that one step, then stop and wait for user feedback.
- Keep the task list up to date.
If stuck:
- Output a 3-bullet status: Done, Next, Blocking.
- Stop and wait for user direction (e.g. "Proceed", "Simplify scope", or clarification). Do not start another round of tool calls until the user responds.
If neither:
- Give a short 3-bullet status anyway (Done / Next / Blocking) so there is a clear checkpoint.
- Rule: one task at a time when recovering. Complete one step, then rely on the next turn or user confirmation before continuing.
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.

