// Foundational philosophy for autonomous agent work. Breaks analysis paralysis and enforces tangible output per interaction. Use when: a conversation feels circular, a session risks ending without an artifact, or an agent needs a reminder to act instead of plan. Generic -- applies to any domain or toolchain.
| name | forward-momentum |
| description | Foundational philosophy for autonomous agent work. Breaks analysis paralysis and enforces tangible output per interaction. Use when: a conversation feels circular, a session risks ending without an artifact, or an agent needs a reminder to act instead of plan. Generic -- applies to any domain or toolchain. |
| metadata | {"author":"ManniTheRaccoon","version":"1.1","category":"engineering"} |
| compatibility | Any agent. No tool dependencies. |
Break Analysis Paralysis. Enforce Action.
A foundational principle for driving projects forward. Use this when the conversation feels circular or theoretical.
Input → Impact → Output.
Every interaction must result in a state change. No idle chatter.
If a session ends without producing a tangible artifact, the session failed.
An artifact is anything that changes the state of the world:
"I thought about it" is not an artifact. "I planned next steps" is not an artifact.
Signs that Forward Momentum is needed:
When stagnation is detected:
The output doesn't have to be perfect. A bad artifact you can iterate on beats a perfect plan you never start.
Agents running autonomous sessions (cron jobs, heartbeats) should treat this as a hard constraint: every session produces an artifact or explicitly documents why it couldn't (with a concrete blocker, not a vague "nothing to do").
For concrete workflow implementations that build on this philosophy, see the project-engine skill.
"Act, then iterate. Don't plan, then plan some more." 🦝
Orchestrate specialized coding agents in isolated worktrees for parallel development tasks.
End-to-end skill for curated team news digests. Covers the full pipeline: team inbox (manual submissions & co-authored drafts), source aggregation (RSS, Twitter, GitHub, web search), research & fact-checking, relevance scoring, article formatting (5 templates), and scheduled delivery to Slack/Discord/WhatsApp. Handles the critical handoff between conversational sessions (where links are received) and isolated cron sessions (where digests are built).
Discover available tools, sub-agents, and skills at session start or when unsure about capabilities.
Qualified, critical code reviews using GitHub's pending review API. Inline comments, verification, and validation.
Standardized Git + GitHub workflows for AI agents. Branching, committing, PRs, reviews, CI checks.
Periodic scan of GitHub repos for open issues. Classifies issues into actionable queues (new, needs-clarification, ready-to-implement, in-progress, blocked) and persists state across heartbeat cycles. Use when an engineering agent needs to autonomously discover and triage work.
