Back to Details

skill-writer

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Skill Writer

Skill Writer

Use this as the single canonical workflow for skill creation and improvement. Primary success condition: maximize high-value input coverage before authoring so the resulting skill has minimal blind spots.
Load only the path(s) required for the task:
TaskRead
Set skill class and required dimensions
references/mode-selection.md
Apply writing constraints for depth vs concision
references/design-principles.md
Select structure pattern for this skill
references/skill-patterns.md
Select workflow orchestration pattern for process-heavy skills
references/workflow-patterns.md
Select output format pattern for deterministic quality
references/output-patterns.md
Choose workflow path and required outputs
references/mode-selection.md
Load representative synthesis examples by skill type
references/examples/*.md
Synthesize external/local sources with depth gates
references/synthesis-path.md
Author or update SKILL.md and supporting files
references/authoring-path.md
Optimize skill description and trigger precision
references/description-optimization.md
Iterate using positive/negative/fix examples
references/iteration-path.md
Evaluate behavior and compare baseline vs with-skill (opt-in quantitative)
references/evaluation-path.md
Register and validate skill changes
references/registration-validation.md
将此作为技能创建与优化的唯一标准工作流。 核心成功条件：在编写前最大化高价值输入覆盖范围，使最终技能的盲区最小化。
仅加载任务所需的路径：
任务阅读内容
设置技能类别与所需维度
references/mode-selection.md
应用关于深度与简洁性的编写约束
references/design-principles.md
为此技能选择结构模式
references/skill-patterns.md
为流程密集型技能选择工作流编排模式
references/workflow-patterns.md
为确定性质量选择输出格式模式
references/output-patterns.md
选择工作流路径与所需输出
references/mode-selection.md
按技能类型加载代表性合成示例
references/examples/*.md
结合深度门限合成外部/本地资源
references/synthesis-path.md
编写或更新SKILL.md及支持文件
references/authoring-path.md
优化技能描述与触发精度
references/description-optimization.md
使用正面/负面/修复示例进行迭代
references/iteration-path.md
评估行为并对比基准与技能启用后的表现（可选定量分析）
references/evaluation-path.md
注册并验证技能变更
references/registration-validation.md

Step 1: Resolve target and path

步骤1：确定目标与路径

  1. Resolve target skill path and intended operation (
    create
    , 
    update
    , 
    synthesize
    , 
    iterate
    ).
  2. Read 
    references/mode-selection.md
    and select the required path(s).
  3. Classify the skill (
    workflow-process
    , 
    integration-documentation
    , 
    security-review
    , 
    skill-authoring
    , 
    generic
    ).
  4. Ask one direct question if class or depth requirements are ambiguous; otherwise state explicit assumptions.
  1. 确定目标技能路径与预期操作（
    create
    、
    update
    、
    synthesize
    、
    iterate
    ）。
  2. 阅读
    references/mode-selection.md
    并选择所需路径。
  3. 对技能进行分类（
    workflow-process
    、
    integration-documentation
    、
    security-review
    、
    skill-authoring
    、
    generic
    ）。
  4. 若类别或深度要求不明确，提出一个直接问题；否则说明明确的假设。

Step 2: Run synthesis when needed

步骤2：必要时执行合成操作

Read 
references/synthesis-path.md
.
  1. Collect and score relevant sources with provenance.
  2. Apply trust and safety rules when ingesting external content.
  3. Produce source-backed decisions and coverage/gap status.
  4. Load one or more profiles from 
    references/examples/*.md
    when the skill is hybrid.
  5. Enforce baseline source pack for skill-authoring workflows.
  6. Enforce depth gates before moving to authoring.
阅读
references/synthesis-path.md
。
  1. 收集相关来源并按来源可信度评分。
  2. 引入外部内容时应用信任与安全规则。
  3. 生成基于来源的决策及覆盖范围/缺口状态。
  4. 当技能为混合型时，从
    references/examples/*.md
    加载一个或多个示例模板。
  5. 为技能编写工作流强制执行基础资源包要求。
  6. 在进入编写阶段前执行深度门限检查。

Step 3: Run iteration first when improving from outcomes/examples

步骤3：从结果/示例优化时先执行迭代

Read 
references/iteration-path.md
first when selected path includes 
iteration
(for example operation 
iterate
).
  1. Capture and anonymize examples with provenance.
  2. Re-evaluate skill behavior against working and holdout slices.
  3. Propose improvements from positive/negative/fix evidence.
  4. Carry concrete behavior deltas into authoring.
Skip this step when selected path does not include 
iteration
.
当所选路径包含
iteration
（例如操作为
iterate
）时，先阅读
references/iteration-path.md
。
  1. 捕获并匿名化带有来源信息的示例。
  2. 根据有效样本和保留样本重新评估技能行为。
  3. 基于正面/负面/修复证据提出改进方案。
  4. 将具体的行为改进点带入编写阶段。
若所选路径不包含
iteration
，则跳过此步骤。

Step 4: Author or update skill artifacts

步骤4：编写或更新技能工件

Read 
references/authoring-path.md
.
  1. Write or update 
    SKILL.md
    in imperative voice with trigger-rich description.
  2. Create focused reference files and scripts only when justified.
  3. Follow 
    references/skill-patterns.md
    , 
    references/workflow-patterns.md
    , and 
    references/output-patterns.md
    for structure and output determinism.
  4. For authoring/generator skills, include transformed examples in references:
    • happy-path
    • secure/robust variant
    • anti-pattern + corrected version
阅读
references/authoring-path.md
。
  1. 使用命令式语气编写或更新
    SKILL.md
    ，并包含丰富的触发描述。
  2. 仅在合理情况下创建针对性的参考文件与脚本。
  3. 遵循
    references/skill-patterns.md
    、
    references/workflow-patterns.md
    和
    references/output-patterns.md
    以保证结构与输出的确定性。
  4. 对于编写/生成类技能，在参考资料中包含转换后的示例：
    • 正常流程示例
    • 安全/健壮变体示例
    • 反模式+修正版本示例

Step 5: Optimize description quality

步骤5：优化描述质量

Read 
references/description-optimization.md
.
  1. Validate should-trigger and should-not-trigger query sets.
  2. Reduce false positives and false negatives with targeted description edits.
  3. Keep trigger language generic across Codex and Claude.
阅读
references/description-optimization.md
。
  1. 验证应触发与不应触发的查询集合。
  2. 通过针对性的描述编辑减少误报与漏报。
  3. 保持触发语言在Codex和Claude中通用。

Step 6: Evaluate outcomes

步骤6：评估结果

Read 
references/evaluation-path.md
.
  1. Run a lightweight qualitative check by default (recommended).
  2. For integration/documentation and skill-authoring skills, include the concise depth rubric from 
    references/evaluation-path.md
    .
  3. Run deeper eval playbook and quantitative baseline-vs-with-skill only when requested or risk warrants it.
  4. Record outcomes and unresolved risks.
阅读
references/evaluation-path.md
。
  1. 默认执行轻量级定性检查（推荐）。
  2. 对于集成/文档类和技能编写类技能，包含
    references/evaluation-path.md
    中的简洁深度评估标准。
  3. 仅在被要求或风险需要时，执行更深入的评估手册及基准与技能启用后的定量对比。
  4. 记录评估结果与未解决的风险。

Step 7: Register and validate

步骤7：注册与验证

Read 
references/registration-validation.md
.
  1. Apply repository registration steps.
  2. Run quick validation with strict depth gates.
  3. Reject shallow outputs that fail depth gates or required artifact checks.
阅读
references/registration-validation.md
。
  1. 执行仓库注册步骤。
  2. 结合严格的深度门限执行快速验证。
  3. 拒绝未通过深度门限或必要工件检查的浅层输出。

Output format

输出格式

Return:
  1. Summary
  2. Changes Made
  3. Validation Results
  4. Open Gaps
返回以下内容：
  1. Summary
    （摘要）
  2. Changes Made
    （已做变更）
  3. Validation Results
    （验证结果）
  4. Open Gaps
    （未解决缺口）

When to Use

使用场景

Use this skill when tackling tasks related to its primary domain or functionality as described above.
当处理上述描述的主要领域或功能相关任务时，使用此技能。

Limitations

局限性

  • Use this skill only when the task clearly matches the scope described above.
  • Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
  • Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.
  • 仅在任务明确匹配上述描述的范围时使用此技能。
  • 不要将输出结果替代为特定环境下的验证、测试或专家评审。
  • 若缺少必要的输入、权限、安全边界或成功标准，请停止操作并请求澄清。