check-wave
Skill0 starsChanged 39 days agoMITView on GitHub
Checks that the current wave really works before it's called done, then saves a checkpoint. Use at the end of every wave, or when the person asks "is it done?", "check this wave", "does it work?".
In this repository19 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- feedback-reviewSkill
- go-liveSkill
- log-lessonSkill
- make-fullSkill
- new-ideaSkill
- results-checkSkill
- start-appSkill
- write-handoffSkill
- check-waveSkill
- feedback-reviewSkill
- go-liveSkill
- log-lessonSkill
- make-fullSkill
- new-ideaSkill
- results-checkSkill
- start-appSkill
- write-handoffSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 3 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 8
Read the wave's "Covers:" line in docs/5-BUILD-PLAN.md.
- Very specific: line 9
Run the wave-checker role (harness/roles/wave-checker.md) as a sub-agent with a fresh context, naming the wave.
- Distinctive: line 14
update doc 4's "Developer handover".
- Distinctive: line 16
run the write-handoff skill.
- Distinctive: line 17
Use the start-app skill so the person can do "Your check", and reply in the answer-first shape (AGENTS.md), with the person's check in the …
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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
Check a wave
- Read the wave's "Covers:" line in docs/5-BUILD-PLAN.md.
- Run the wave-checker role (harness/roles/wave-checker.md) as a sub-agent with a fresh context, naming the wave.
- Run
sh tools/check-plan.sh. - For every failure: add a row to docs/lessons.md first, then fix it, then repeat steps 2–3. Stop after 2 failed fix attempts on the same problem and ask the person (or move that fix to the deep tier; see harness/models.md).
- When everything passes:
- tick the wave's tasks in doc 5;
- update doc 4's "Developer handover";
- save one checkpoint (git commit) for this wave;
- run the write-handoff skill.
- Use the start-app skill so the person can do "Your check", and reply in the answer-first shape (AGENTS.md), with the person's check in the step-by-step shape.
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.

