avc-build-slice
Skill0 starsChanged 3 months agoMITView on GitHub
Implement one authorized AVC/XP vertical node as the single Builder using focused red-green-refactor feedback. Use only after doctor, frame, and frozen-oracle gates pass.
In this repository15 other files it gives its agents.
- AGENTS.mdAGENTS.md
- ai-memory-durable-pagesSkill
- ai-memory-handoffSkill
- ai-memory-learning-maintenanceSkill
- ai-memory-retrievalSkill
- ai-memory-routing-installSkill
- avc-amendSkill
- avc-freeze-oracleSkill
- avc-live-qaSkill
- avc-retroSkill
- avc-reviewSkill
- avc-scoutSkill
- avc-spikeSkill
- avc-startSkill
- avc-verifySkill
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
Follow .avc/roles/builder.md.
- Very specific: line 10
If any differs from the dispatch capsule, return BLOCKED.
- Distinctive: line 16
run the most focused useful check.
- Distinctive: line 19
run the node checkpoint gate.
- Distinctive: line 21
Never edit state, protected files, policy, adapters, or frozen acceptance.
≈ “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
Build one vertical slice
Follow .avc/roles/builder.md. Verify run id, revision, tree/HEAD, active node,
authorized paths, oracle status, command, and stop condition before editing.
If any differs from the dispatch capsule, return BLOCKED.
Work one hypothesis at a time:
- reproduce or create the smallest relevant red signal;
- make the smallest coherent change inside the node allowlist;
- run the most focused useful check;
- inspect output and changed paths;
- refactor only while green;
- run the node checkpoint gate.
Never edit state, protected files, policy, adapters, or frozen acceptance. New scope, dependency, migration, risk, or changed acceptance is an amendment, not an implementation detail. Stop after two repair attempts without new evidence. Return exact paths/commands in the canonical result; never self-approve.
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.