assess
Assess a decision against stated criteria: sourced ratings per criterion and a verdict, kept in a dated topic folder
- License 许可
- MIT
- 所属仓库
- tony/skills
- 最近更新
- 2026-11-08
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- assess
- description
- Assess a decision against stated criteria: sourced ratings per criterion and a verdict, kept in a dated topic folder
- allowed-tools
- [ "Bash", "Read", "Write", "Edit", "Grep", "Glob", "AskUserQuestion" ]
- argument-hint
- [decision or question] [--root=<dir>] [--resume] [--audience=private|internal|public]
- disable-model-invocation
- true
02 资源文件 1
- 参考文档agents/openai.yaml300 B
03 SKILL.md 正文
/research:assess
Read ../foray/SKILL.md and follow it, treating assess as the first word of the arguments.
User arguments: $ARGUMENTS
04 同仓库更多 Skills
serene-bliss
Use when asked to make a CLI --help, docs page, error message, or tooling UX more serene or calmer for developer experience; returns text, no edits.
review
Weave code review: run independent adversarial reviews in parallel, then synthesize findings
refine
Use when asked to refine a draft, iterate on code until cleaner, or polish a README through repeated critique and improvement.
prompt
Weave prompt: compare independent adversarial implementations, then adopt the single best one
plan
Weave planning: compare independent adversarial plans, then synthesize the best one
fix-review
Fix weave review findings: validate, add test coverage, fix, and commit each as atomic changes