plugins/attune/skills/dorodango/SKILL.md
Polishes working code through successive quality passes in fresh subagents. Use after tests pass when code needs multi-dimension refinement before release.
npx skillsauth add athola/claude-night-market dorodangoInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Named after the Japanese art of polishing a ball of dirt into a high-gloss sphere. Applied to code: take the initial implementation (the "mud ball") and refine it through successive quality passes until it shines.
Four quality dimensions, each a self-contained pass:
See modules/pass-definitions.md for detailed scope
of each pass type.
issues_found: 0 marks that
dimension as convergedState tracked in .attune/dorodango-state.json:
{
"target": "plugins/foo",
"started_at": "2026-03-18T12:00:00Z",
"pass_count": 3,
"passes": [
{
"type": "correctness",
"issues_found": 2,
"issues_fixed": 2
},
{
"type": "clarity",
"issues_found": 5,
"issues_fixed": 5
},
{
"type": "consistency",
"issues_found": 0
}
],
"converged_dimensions": ["consistency"],
"converged": false
}
This file enables resume across sessions. On resume, skip converged dimensions and continue from the next unconverged dimension.
Each pass dispatches a self-contained subagent to prevent context accumulation. The subagent receives:
Subagent dispatch is optional for targets under 100 lines of code; in-session review is sufficient for small files.
pensive:code-refinement - used in clarity passconserve:code-quality-principles - KISS/YAGNI/SOLIDimbue:latent-space-engineering - frame pass prompts
with emotional framing for better resultstools
Detect friction signals; graduate patterns into rules. Use for session retrospectives.
testing
Use when you need a diff-derived test plan for an MR — reads the diff, groups changes by area, runs targeted verifications, and proves revert-tests are genuine guards, not dead assertions.
development
Curate the web-capture index. Use when the capture backlog grows, captures sit unprocessed at seedling/pending, or to surface stored research during work.
testing
Probe memory/summary clarity via dual anchor questions: task progress, info gaps. Use when verifying session state or summary before handoff or compression.