openJiuwen-ai/agent-core

assess

评估方法论 — 根据 query 中的评估模式执行代码库健康评估或 runtime extension 能力缺口评估

Idioma del texto original: chino

commit

基于 commit skill 的自主提交流程。适用于 implement 阶段在提交前规划范围并通过 bash 完成 git 提交。

Idioma del texto original: chino

communicate

沟通规范 — 约束 commit message、PR、journal 和求助信息的表达方式

Idioma del texto original: chino

design-ext

扩展方案设计 — 将能力缺口转化为 ExtensionDesign 结构

Idioma del texto original: chino

implement-ext

扩展实现阶段 — 在 worktree 中生成运行时扩展代码

Idioma del texto original: chino

implement

实现阶段主操作手册 — 指导 agent 完成改码与局部验证，并把提交留给独立 commit phase

Idioma del texto original: chino

plan

规划规范 — 将评估结果收敛为结构化任务计划

Idioma del texto original: chino

select-pipeline

流水线选择规范 — 根据任务和事实选择最合适的 pipeline

Idioma del texto original: chino

verify-ext

Runtime extension 验证规范 — 验证 harness package 中 tools、rails、skills 是否能真实热加载并可运行

Idioma del texto original: chino

verify

验证规范 — 定义实现阶段应满足的验证等级与通过标准

Idioma del texto original: chino

generate-skill-from-url

Generates a multimodal Skill markdown file from a source URL. Use this Skill when a user wants to turn a web tutorial, product support article, or software guide into a reusable agent Skill with concise steps and embedded screenshots.

Idioma del texto original: chino

booking-dot-com

Comprehensive step-by-step workflow for navigating the Booking.com mobile site to search for destinations, select dates/occupancy, browse results, and extract detailed hotel information including pricing and facilities.

Idioma del texto original: inglés

github-com

Navigate github.com in mobile Chrome to retrieve repository information (files, README, contributors, languages, releases, packages) and switch to desktop site mode for richer metadata (forks, stars). Use for in-browser research, not git CLI or GitHub API…

Idioma del texto original: inglés

scheduling

Complete calendar-and-clock workflows on mobile (find events, read start times, create alarms or reminders relative to meetings). Use when the user asks to schedule, set an alarm before/after a meeting, find appointment times, or coordinate Calendar with…

Idioma del texto original: inglés

python-patterns

Python idioms, immutability, async patterns, and anti-patterns for agent-core.

Idioma del texto original: inglés

python-testing

Deep pytest guide for agent-core: fixtures, mocking, async tests, and TDD workflow.

Idioma del texto original: inglés

security-review

10-category security checklist for agent-core: secrets, input validation, sandbox, and prompt injection.

Idioma del texto original: inglés

verification-loop

Formalizes agent-core's make check/type-check/test/fix pipeline into a structured 6-phase verification skill.

Idioma del texto original: inglés

skill-tester

Generate and run synthetic test cases against any skill by executing real prompts through the skill and grading actual outputs — functional and behavioral testing only. Use when verifying a skill WORKS: correct outputs, edge case handling, error recovery,…

Idioma del texto original: inglés

eval-pipeline

Full skill evaluation pipeline — the single entry point for comprehensive skill assessment. Orchestrates multiple evaluators in sequence, aggregates their scores, and produces a final weighted verdict. Use when you want to fully evaluate a skill end-to-end:…

Idioma del texto original: inglés

skill-llm-judge

Audit Agent Skill design quality through static analysis of SKILL.md — no prompt execution, no code running. Scores 7 design dimensions (100pts): knowledge ratio, expert knowledge craft, specification compliance, progressive disclosure, pattern + freedom fit,…

Idioma del texto original: inglés

skill-safety-eval

Evaluate Agent Skill safety through static analysis of SKILL.md instructions — no prompt execution, no code running. Gates the eval pipeline at score_pct ≥ 0.80: skills that fail do not ship regardless of design or functional scores.Scores 5 safety dimensions…

Idioma del texto original: inglés