frontier-explore-beam
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-explore-beam
- title
- Beam Exploration
03 SKILL.md 正文
Beam Exploration
Execute a single research beam following its defined methodology.
Process
- Read the beam definition (direction, approach, hypothesis, strategy)
- Execute the exploration strategy step by step
- For each insight discovered:
- State the claim clearly
- Document supporting evidence
- Assess confidence (0-1) based on evidence quality
- Assess novelty (0-1) relative to known territory
- Note connections to other potential insights
- Test the beam's hypothesis against gathered evidence
- Record dead ends — approaches that were tried but failed
- Note unexpected findings that don't fit the original hypothesis
- Suggest follow-up directions for future beams
Key Principle
Each beam uses its OWN methodology. Do not impose a standard research framework. If the beam says "use adversarial analysis," reason adversarially. If it says "use analogical reasoning," find analogies. Follow the beam's defined approach.
Outputs
beam-{id}.json— exploration results with insights, dead ends, and follow-ups
Quality Criteria
- At least 2 insights per beam (even dead-end beams should yield negative results)
- Each insight has evidence and confidence assessment
- Hypothesis outcome is explicitly stated (supported/refuted/modified/inconclusive)
- Dead ends explain WHY the approach failed (not just that it failed)
- Unexpected findings are captured (not filtered to fit the hypothesis)
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