// Remove telltale AI-writing patterns from README, docs, and user-facing text. Must be done line-by-line, manually. No regex. Use after agents write any user-visible prose.
Deep review — random exploration + cross-agent review, alternating. Finds integration bugs that self-review misses. Run every 30–60 min during active implementation.
Overview of Forge's Agentic Coding Flywheel methodology. Use to route between plan, bead, and code space. See FLYWHEEL.md at the repo root.
End-of-session ritual. Close finished beads, file new ones for remaining work, run verify, commit in logical groupings, push. Work is not complete until git push succeeds.
Start a new Flywheel planning round. Produce initial markdown plan, route to competing frontier models, synthesize hybrid, refine 4–5×. Use before any coding begins on a new feature.
Translate a polished markdown plan into self-contained beads in .beads/beads.jsonl. Every bead must be executable without reopening the plan. Use after the plan has converged.
Polishing pass over all open beads. Run 4–6 times. "Check your beads N times, implement once." Use after plan-to-beads and between refinement rounds.
| name | de-slopify |
| description | Remove telltale AI-writing patterns from README, docs, and user-facing text. Must be done line-by-line, manually. No regex. Use after agents write any user-visible prose. |
AI writing has tells. Emdashes. "It's not just X, it's Y." "Here's why." Forced enthusiasm. Pseudo-profound openers. These patterns signal "LLM wrote this" to readers and erode trust in the project.
Use the verbatim prompt at .flywheel/prompts/de-slopify.md.
No regex. No script. Read each line. Revise each line deliberately. Attempts to automate this pass fail, because the fixes are context-dependent.
README.md.CHANGELOG.md entries.Technical specifics, command names, exact flag names, actual counts (tests, providers, tools). Strip tone tics, not information.