avc-spike
Skill0 starsChanged 3 months agoMITView on GitHub
Run a timeboxed AVC/XP discovery experiment for an ambiguous technical question, ending in evidence, a decision, a testable hypothesis, or explicit abandonment rather than production code by inertia.
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-build-sliceSkill
- avc-freeze-oracleSkill
- avc-live-qaSkill
- avc-retroSkill
- avc-reviewSkill
- avc-scoutSkill
- avc-startSkill
- avc-verifySkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
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 8
Follow the Scout authority unless a separate disposable write surface is explicitly authorized.
- Distinctive: line 13
Prefer a benchmark, reproduction, throwaway prototype, or targeted read.
≈ “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
Run a bounded spike
Follow the Scout authority unless a separate disposable write surface is explicitly authorized. Define one question, prediction, time budget, permitted paths, command/environment, and stop condition. Search ai-memory for prior attempts and gotchas, then verify current applicability.
Prefer a benchmark, reproduction, throwaway prototype, or targeted read. Mark all spike code disposable; it does not become production without a new authorized implementation node and oracle. Stop at the configured timebox or when the decision is supported.
Return the canonical result with evidence, limitations, and one recommended next decision. More speculative planning is not a successful spike.
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.