refactor-heavy
Skill1 starsChanged 5 months agoLicence not identifiedView on GitHub
Prescriptive 11-step refactor workflow for COMPLEXA / cross-module restructures (behavior-preserving across module boundaries). Restructure code WITHOUT changing observable behavior, made auditable by REFACTOR_SCOPE_LOCK + a before/after characterization snapshot, PLUS a final 3-parallel adversarial review, a post-refactor UX user-journey E2E, and an after-all sanity sweep. Steps 1-2 inline (understand scope + terrain/impact), step 3 subagent (characterization tests via pre-tester in characterization mode — MUST PASS), step 4 inline gate (refactor plan + REFACTOR_SCOPE_LOCK — fires before first file touch), step 5 inline (execute minimal diff), step 6 subagent (characterization rerun — IDENTICAL verdict), step 7 inline (complexity/risk confirmation), step 8 parallel subagents gate (adversarial security+architecture+quality), step 9 subagent (post-refactor UX E2E), step 10 inline gate (Pa de Cal GO/NO-GO), step 11 subagent (final after-all sanity sweep). Reuses explore + plan-architect + pre-tester + executor-implementer-task + diff-discipline-reviewer + review-orchestrator/adversarial reviewers — ZERO genuinely-new agents. Manual-only invocation via /pipeline-orchestrator:refactor-heavy or via /pipeline-orchestrator:refactor --heavy, or via auto-escalation from refactor-light step 7.
In this repository35 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- audit-heavySkill
- audit-lightSkill
- auditSkill
- bugfix-heavySkill
- bugfix-lightSkill
- bugfixSkill
- feature-heavySkill
- feature-lightSkill
- featureSkill
- measure-paperclip-fidelitySkill
- pipelineSkill
- refactor-lightSkill
- refactorSkill
- reviewSkill
- spec-audit-onlySkill
- spec-designSkill
- spec-heavySkill
- spec-initSkill
- spec-lightSkill
- spec-requirementsSkill
- spec-reviewSkill
- specSkill
- spec-tasksSkill
- unblockSkill
- user-story-heavySkill
- user-story-lightSkill
- user-storySkill
- ux-sim-heavySkill
- ux-sim-lightSkill
- ux-simSkill
- validate-designSkill
- validate-gapSkill
- verify-completionSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 2 are distinctive, and 3 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.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
The licence could not be identified — 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.