frontier-spawn-beams
暂无简介
- License 许可
- MIT
- 最近更新
- 2026-06-13
- Stars
- ★ 3
- Forks
- 1
01 前言 Front Matter
- id
- frontier-spawn-beams
- title
- Beam Spawning
03 SKILL.md 正文
Beam Spawning
Design N parallel research beams targeting promising frontier edges.
Process
- Read ranked frontier edges from frontier analysis
- Design N beams, distributing across top-ranked edges
- For each beam, define:
- Direction: Which frontier edge to explore
- Approach: A unique research methodology (not shared across beams)
- Hypothesis: A specific, testable prediction
- Exploration strategy: Step-by-step plan for the exploration
- Ensure diversity in both direction AND methodology:
- Multiple beams may target the same edge if using different approaches
- At least one beam should target a lower-ranked but novel edge
- Assess dead-end risk for each beam
Key Principle
Beams have NO fixed methodology. Each beam defines its own approach. Possible approaches include:
- Literature synthesis and meta-analysis
- First-principles reasoning from axioms
- Analogical reasoning from related domains
- Adversarial analysis (trying to disprove claims)
- Computational/formal modeling
- Historical case study analysis
- Thought experiments and counterfactuals
Outputs
beams.json— N beam definitions with direction, approach, hypothesis, and strategy
Quality Criteria
- Exactly N beams produced (matching beamWidth input)
- Each beam has a unique approach (no two beams use the same methodology)
- Hypotheses are specific and testable
- Exploration strategies are concrete enough to execute
- Mix of high-confidence and speculative beams
04 同仓库更多 Skills
hello-checker
Use this skill when asked to "verify", "check", or "validate" a file's existence and content. It provides a reliable workflow for confirming files meet their spec.
ask-skill
暂无简介
html-review-artifact
Framework-wide guidance for crafting polished human-review artifacts as markdown or HTML
converge-planning
Design a Converge playbook end-to-end. Use when the user says "plan a project", "design a playbook", "decompose into tasks", "scaffold a Converge workflow", "onboard to Converge", or asks how to write TASK.md / playbook.yml. Two entry points: plan a new playbook or update an existing one. Hand off to `/converge-control` after producing the playbook structure.
converge-control
Operate a Converge playbook end-to-end — start runs, monitor progress, narrow failures with `--select`, inspect runtime state, validate definitions, surgically reset subtrees, and stop stuck or orphaned runs. Use this skill whenever the user says "run my playbook", "execute this", "monitor the run", "converge failed", "the run is stuck", "retry failures", "babysit this playbook", "what's the status?", "show me the gantt", or asks how to use `converge run` / `--select` / `inspect` / `doctor` / `clean` / `stop`. Also use it for `HTTP 401` / `Invalid API key` failures on the first task — those are environment-not-playbook problems — and for any post-run cleanup work. Hand off to `converge-planning` if the user wants to design or restructure the playbook itself.
repair-taskts
Fix task.ts definition issues — Seed syntax, missing .build(), empty checks, import errors, TypeScript errors