hoangsonww/forge-agentic-coding-cli
18 skills
$npx skills add hoangsonww/forge-agentic-coding-cliSkillInstalls
add-agentScaffold a new Forge subagent (planner/architect/executor/reviewer/debugger/memory-style).add-providerScaffold a new model provider for Forge — class, registry wiring, providerEnum entry, local-catalog classification, router check, and a unit test with mocked…add-toolScaffold a new Forge tool end-to-end — implementation, registration, permission/risk metadata, sandbox routing, and a unit test.de-slopifyRemove telltale AI-writing patterns from README, docs, and user-facing text. Must be done line-by-line, manually. No regex.debug-loopSystematic debugging playbook for the Forge agentic loop (src/core/loop.ts and src/agents/executor.ts).dedupe-beadsMerge duplicate or excessively overlapping beads in .beads/beads.jsonl into canonical ones. Run after any batch where 20+ new beads were created.deep-reviewDeep review — random exploration + cross-agent review, alternating. Finds integration bugs that self-review misses.flywheelOverview of Forge's Agentic Coding Flywheel methodology. Use to route between plan, bead, and code space. See FLYWHEEL.md at the repo root.fresh-eyesReset review context when bead polishing or code review has flatlined. Requires starting a brand-new Claude / Codex session.idea-wizard30 → 5 → 15 funnel for brainstorming new features on the existing Forge codebase. Use when adding capability to a mature install, not for greenfield.landingEnd-of-session ritual. Close finished beads, file new ones for remaining work, run verify, commit in logical groupings, push.planStart a new Flywheel planning round. Produce initial markdown plan, route to competing frontier models, synthesize hybrid, refine 4–5×.plan-synthesizeSynthesize competing plans from multiple frontier models into a single best-of-all-worlds hybrid.plan-to-beadsTranslate a polished markdown plan into self-contained beads in .beads/beads.jsonl. Every bead must be executable without reopening the plan.polish-beadsPolishing 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.reality-checkBreak the spell of local productivity. Ask whether completing all open beads actually closes the gap to the project goal.release-checkPre-release checklist for Forge — verify, version bump, changelog, docs, docker build, smoke test. Run before tagging v*.verifyRun Forge's canonical verification chain (format:check + lint + typecheck + build + test). Use before claiming any task complete or opening a PR.