Skills/Agent Hub
unlazy
Anti-laziness skill for AI agents. Core: the Depth Tree method, which splits a task N layers deep and gives every leaf the full time budget of the whole task, so effort multiplies with depth. Grounded in 2025-2026 research on model laziness, underthinking and premature completion.
License: MIT
Repository files
- .github/workflows/test.yml
- .gitignore
- CHANGELOG.md
- CONTRIBUTING.md
- LICENSE
- README.md
- SECURITY.md
- SKILL.md
- agents/openai.yaml
- package.json
- references/dispatch.md
- references/gates.md
- references/method.md
- references/orchestration.md
- references/parallel.md
- references/token-economy.md
- research/validation-protocol.md
- scripts/dispatch-check.mjs
- scripts/gate-check.mjs
- scripts/gate-lint.mjs
- scripts/install-hooks.mjs
- scripts/lib/check-supervisor.mjs
- scripts/lib/dispatch.mjs
- scripts/lib/gates.mjs
- scripts/lib/process-tree.mjs
- scripts/lib/regex-worker.mjs
- scripts/stop-hook.mjs
- templates/PLAN.md
- templates/gates-leaf.md
- templates/gates-node.md
- tests/contract-tests.mjs
- tests/dispatch-tests.mjs
- tests/hardening-tests.mjs
- tests/lint-tests.mjs
- tests/run-tests.mjs
- tests/self-check.mjs
- tests/stress-tests.mjs