research-convergence
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
- research-convergence
- title
- Research Quality Convergence
03 SKILL.md 正文
Research Quality Convergence
Evaluate overall research quality and decide whether to continue iterating or stop.
Quality Score Rubric
Compute a weighted score (0-100):
| Criterion | Weight | Scoring Method |
|---|---|---|
| Evidence Coverage | 25% | % of active hypotheses with evidence grade B or above |
| GRADE Quality | 30% | Weighted average: A=100, B=75, C=50, D=25 |
| Contradiction Resolution | 15% | % of contradictions resolved |
| Statistical Rigor | 15% | % of claims with computed effect sizes and CIs |
| Paper Completeness | 15% | % of 8 paper sections meeting minimum word counts |
qualityScore = 0.25*evidenceCoverage + 0.30*gradeQuality + 0.15*contradictionResolution + 0.15*statisticalRigor + 0.15*paperCompleteness
Convergence Decision
CONVERGED when ALL of:
- qualityScore >= targetScore
- Improvement from prior epoch < 3 points (plateau)
- No unresolved contradictions where both sides have grade B+ evidence
CONTINUE otherwise.
Gap Analysis
When continuing, identify:
- Which subscore is weakest
- Specific actions for the next epoch to improve it
- Unresolved questions to investigate
Ledger Entry
Append one JSON line to research-ledger.jsonl per epoch with:
- Epoch number, timestamp
- Quality score and all subscores
- Decision (CONVERGED/CONTINUE)
- Counts: hypotheses, claims, grade distribution
Quality Criteria
- Score computation is traceable (show the math)
- Gap analysis is specific and actionable
- Ledger entry is appended (not overwritten)
- Decision follows the convergence rules strictly
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