Methodology Skill Loop

/goal Convert one practical methodology into a reusable agent skill with clear fit, ordered steps, validation questions, and a small example.
 
Task type: Custom
Target tool: Claude Code
 
Work toward this goal until all validation checks pass or the stop rule is reached.
 
Design hypothesis:
This methodology skill loop can produce a safer result if the scope stays narrow, validation is explicit, and a checker can reject shortcut work.
 
Smallest useful run:
Run one bounded pass on the newest relevant signal before expanding scope or adding a schedule.
 
Loop cycle:
1. Discovery — Read the latest signal for this template before acting: CI output, issue detail, review comment, dataset report, or content brief.
2. Handoff — Hand the work to one agent in an isolated branch, worktree, or clearly scoped session. Keep final approval with a human.
3. Verification — Use an independent review pass to confirm the result, inspect the diff or artifact, and reject shortcut work.
4. Persistence — Save a short run note with the signal reviewed, actions taken, validation result, and next recommended step.
5. Scheduling — Run manually until the loop is reliable; only then consider a scheduled or event-triggered run.
 
Context:
Start from a method the team already understands. Keep the first version small enough to test with three representative tasks.
 
Validation:
The skill names when to use and when not to use the method
Steps are ordered and observable
Quality checks can reject weak output
At least one example input and output is included
 
Validation evidence:
Record the original signal, checks run, final result, changed files or artifacts, and any checker rejection.
 
Independent checker:
Use an independent review pass to confirm the result, inspect the diff or artifact, and reject shortcut work.
 
Boundaries:
Do not claim the method is universal
Do not invent facts about the method's origin
Do not remove human review for high-stakes outputs
Do not add execution or API calls to the skill definition
 
Stop rule:
Stop when the skill passes three test tasks or after 3 failed revisions.
Maximum iterations: 3
 
Budget:
Example only: stop before exceeding the agreed per-run token budget.
 
Human approval:
Required before merge, deploy, delete, purchase, or external communication.
 
Fallback:
If the method does not fit the task, recommend a better method and explain why.
 
Loop Validation Log:
- Hypothesis: This methodology skill loop can produce a safer result if the scope stays narrow, validation is explicit, and a checker can reject shortcut work.
- Smallest useful run: Run one bounded pass on the newest relevant signal before expanding scope or adding a schedule.
- Expected evidence: Record the original signal, checks run, final result, changed files or artifacts, and any checker rejection.
- Actual evidence: [fill in after the run]
- Passed? [yes / no / partial]
- Feedback: After the run, note what the loop learned, what failed, and what should change before the next pass.
- Next step: [stop / adjust the loop / run the next pass]
 
Do not delete tests, bypass checks, or modify unrelated files just to satisfy the validation condition. If blocked, stop and summarize the blocker, attempted fixes, and recommended next action.