rdd
Skill1 starsChanged 6 months agoApache-2.0View on GitHub
Run review-driven development. Use when the user asks for RDD, review-driven development, or wants each issue handled by an executor-reviewer-debugger loop until reviewer approval before moving to the next issue.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- markleetw/reverse-due-diligence-skilltheir own version, first seen Oct 25, 2026
- ericluo04/claude-academic-workflowtheir own version, first seen Oct 9, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- ericluo04/claude-academic-workflow★ 25same name
- markleetw/reverse-due-diligence-skill★ 6same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository8 other files it gives its agents.
- AGENTS.mdAGENTS.md
- docs/AGENTS.mdAGENTS.md
- hooks/AGENTS.mdAGENTS.md
- plugin/AGENTS.mdAGENTS.md
- plugin-e2e-module/AGENTS.mdAGENTS.md
- src/AGENTS.mdAGENTS.md
- tests/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
The file
We split this skill into the rules it gives an agent
9 rules. About 0 are common, 9 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈9
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 10
Use this workflow to process issues one at a time with separated implementation, review, and fix roles.
- Distinctive: line 17
If the reviewer requests fixes, summon a debugger to address all in-scope fixes.
- Distinctive: line 19
If reviewer-requested fixes are too far out of scope, defer them and report them after all issues finish.
- Distinctive: line 25
Keep each executor, reviewer, and debugger scoped to the current issue.
- Distinctive: line 26
Only the main agent may summon RDD subagents, and each summon must happen from the main agent's context stream so every handoff is visible …
- Distinctive: line 29
If oh-my-codex subagents are unavailable, try Codex native subagents.
- Distinctive: line 30
If neither oh-my-codex nor Codex native subagents are available, halt the RDD workflow and alert the user instead of emulating the roles in …
- Distinctive: line 31
Do not let a reviewer implement fixes.
- Distinctive: line 32
Do not move to the next issue until the current reviewer approves or the remaining requests are explicitly deferred as out of scope.
≈ “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
Review-Driven Development
Overview
Use this workflow to process issues one at a time with separated implementation, review, and fix roles. Keep each issue bounded, verify the result, and carry deferred out-of-scope findings to the final report.
Workflow
- Pick the next issue and define the expected done state.
- Summon a dedicated executor for only that issue.
- Summon a dedicated reviewer to inspect the executor's work.
- If the reviewer requests fixes, summon a debugger to address all in-scope fixes.
- Repeat review and debug until the reviewer approves.
- If reviewer-requested fixes are too far out of scope, defer them and report them after all issues finish.
- Discard the issue-specific agents and restart from step 1 with the next issue.
- Finish with changed files, verification evidence, deferred items, and remaining risks.
Role Rules
- Keep each executor, reviewer, and debugger scoped to the current issue.
- Only the main agent may summon RDD subagents, and each summon must happen from the main agent's context stream so every handoff is visible and auditable.
- Executors, reviewers, debuggers, and other child agents must not summon additional subagents or delegate to sub-subagents.
- Spawn issue-specific agents through oh-my-codex first when that surface is available.
- If oh-my-codex subagents are unavailable, try Codex native subagents.
- If neither oh-my-codex nor Codex native subagents are available, halt the RDD workflow and alert the user instead of emulating the roles in the main thread.
- Do not let a reviewer implement fixes; route fixes through the debugger role.
- Do not move to the next issue until the current reviewer approves or the remaining requests are explicitly deferred as out of scope.
Completion Report
Report:
- Issues completed.
- Files changed.
- Tests or verification run.
- Reviewer approval status.
- Deferred out-of-scope requests.
- Remaining risks.
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.