Adversarial Debugging with Agent Teams - Multiple agents investigate competing hypotheses in parallel, challenge each other's findings through structured debate, and converge on the true root cause.
★not rated 2 29d agoA
tokens not measured
originalMIT
Generate a bespoke DESIGN.md for any product brief by reverse-engineering a corpus of existing DESIGN.md design systems into a computable design grammar (rules + rationale + relationships), then forward-generating with three-part rationale (inheritance + adaptation + justification). Outputs the v1.13.0 distinctiveness.
★not rated 2 29d agoA
tokens not measured
originalMIT
Agent Teams Product Development Pipeline - 7-phase adversarial collaborative development with multi-agent debate, competition, and cross-validation at every critical decision point, including red team attacks, adversarial debugging, independent bug fix loop, and requirement verification.
★not rated 2 29d agoA
tokens not measured
originalMIT
Product Development Forge - AI-driven 7-phase product development workflow. Provides complete methodology from requirements analysis to deployment, including brainstorming, TDD, three-stage review, and auto-fix loops.
★not rated 2 29d agoA
tokens not measured
originalMIT
Humanize — make AI-written technical prose read like a competent human professional wrote it, at the level where readers actually get lost: discourse, not vocabulary. Three skills. /humanize rewrites a draft (zh/en) without changing a single fact: it targets the mechanisms behind 'every word is clear but I can't foll.
★not rated 2
changed 1mo agoA
tokens not measured
originalMIT
Persona Distillation Ecosystem — a parameterized schema library + generation/evaluation/scheduling/debate toolkit for distilling personas (people or rule systems) into self-contained Claude Code skills. 5 skills, 9 persona schemas, 19 reusable components (incl. execution-profile via Klein-RPD/CDM 4-sweep), 9-phase…
★not rated 2 29d agoA
tokens not measured
originalMIT
A Claude Code plugin containing a full software-development workflow from product definition through implementation, testing, review, release, and learning. Its steps produce files that scripts can check or require a human approval.
★not rated 2
changed 29d agoA
tokens not measured
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: