implement-backlog
Skill0 starsChanged 2 months agoNo licenceView on GitHub
Fan out across a project's whole open issues/ backlog (or a named feature/issue subset) instead of implementing one issue at a time. Computes a dependency + file-conflict plan (waves of issues that can run in parallel, sequenced where they'd collide), shows it to the user for a go-ahead, then launches capped batches of subagents — one per issue, isolated in a git worktree when the project is a git repo — each following implement-issue's implementation rules and TDD-with-the-project's-own-test-framework convention, but never touching shared files (issues/INDEX.md, issues/FEATURES.md, SPEC.md) or running per-issue code-review/security-review themselves. The orchestrator merges each wave's branches locally, updates bookkeeping centrally, and once the whole run finishes, runs one consolidated adversarial code-review pass (via the code-review skill, focused using a generic baseline plus bug patterns mined from this project's own CLAUDE.md/KNOWN-ISSUES.md history) across the cumulative diff, plus security-review if any security:true issue was touched — reopening whatever it implicates. Never commits automatically. Use when the user wants to work through many backlog issues at once instead of one-by-one, or invokes /implement-backlog. Requires an issues/ folder (from doc-to-issues) — if none, use doc-to-issues first.
In this repository9 other files it gives its agents.
- doc-to-issuesSkill
- documentationSkill
- implement-issueSkill
- interviewSkill
- polishSkill
- qcSkill
- reportSkill
- review-issueSkill
- staging-qa-docSkill
The file
We split this skill into the rules it gives an agent
9 rules. About 0 are common, 4 are distinctive, and 5 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
No licence file, so all rights are reserved — read it at the source. We count its rules but don't quote them. Read them on GitHub.
≈ “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.
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.