Agent写作
- 作者仓库星标 739
- 作者更新于 实时读取
- 作者仓库 skills
- 领域
- 文档
- 兼容 Agent
-
- Claude Code
- Cursor
- Cline
- Codex
- Windsurf
- Gemini CLI
- +20
- 信任分
- 88 / 100 · 社区维护
- 作者 / 版本 / 许可
- @getsentry · 未声明 license
- Token 消耗评级
- 中等消耗
- 接入复杂程度
- 需简单配置
- 是否需要外部 API Key
- 不需要
- 兼容的系统
- 未声明(默认跨平台)
- 底层运行要求
- 无特殊要求
- 文件与系统权限
-
- 只读
- 允许写入 / 修改
- Shell 执行
- 网络行为
- 仅限本地
- 安装命令数
- 26 条
档案由构建时根据 SKILL.md 与安装命令自动衍生,可能与作者实际意图存在差异。
需要注意: 未限定 allowed-tools,默认拥有全部工具权限。
---
name: skill-writer
description: Create, synthesize, and iteratively improve agent skills following the Agent Skills specificatio…
category: 文档
runtime: 无特殊运行时
---
# skill-writer 输出预览
## PART A: 任务判断
- 适用问题:PRD、RFC、README、项目说明或知识库整理。
- 输入要求:目标材料、限制条件、期望输出和验收方式。
- 证据边界:围绕“Core Workflow References / Artifact Layout References / Workflow Mechanic References”读取原文规则,不把推断写成作者承诺。
## PART B: 执行结果
- **01** 任务判断:确认你的需求是否属于PRD、RFC、README、项目说明或知识库整理,并标出输入、限制和预期结果。
- **02** 执行计划:优先按“Core Workflow References / Artifact Layout References / Workflow Mechanic References”拆成步骤,说明每一步会读取什么、修改什么、产出什么。
- **03** 交付结果:给出可复制的命令、文件改动、检查清单或内容草稿,并说明如何继续迭代。
- **04** 风险边界:结合 读取文件、写入/修改文件、执行终端命令、主要在本地完成、通常不需要额外 API Key 给出执行前确认项。
## Running Rules
- 读取文件、写入/修改文件、执行终端命令;主要在本地完成;通常不需要额外 API Key。
- 先小样例验证,再放大到真实任务。
- 交付时同时给结果、检查口径和下一步迭代建议。 原文没有稳定的斜杠命令要求。安装验证后通常全局生效,直接在对话里点名这个 Skill 并描述任务即可。
告诉 Agent 目标文件或材料、期望结果、不可改范围、是否允许联网或执行命令。本 Skill 的权限画像是:读取文件、写入/修改文件、执行终端命令。
先用一个小任务确认它会围绕“Core Workflow References / Artifact Layout References / Workflow Mechanic References”工作;涉及文件或命令时,先看 diff、日志、预览或测试结果。
检查最终产物是否包含明确结果、必要证据和下一步动作;如果输出泛泛而谈,就补充输入、边界和验收标准后重跑。
---
name: skill-writer
description: Create, synthesize, and iteratively improve agent skills following the Agent Skills specificatio…
category: 文档
source: getsentry/skills
---
# skill-writer
## 什么时候使用
- 把项目文档方向的常用动作沉淀成 Agent 可调用的技能 适合处理README、PRD、RFC、教程和知识库文档,核心价值是把输入、判断、执行、验证和交付边界固定下来,避免 Agent 泛泛回答。 把任务拆成可执行、可检查、可继续迭代的…
- 面向PRD、RFC、README、项目说明或知识库整理,优先处理能明确输入、步骤和验收标准的工作。
## 需要提供什么
- 目标材料、目录范围、期望结果和不可改动内容。
- 是否允许联网、执行命令、读写文件或调用外部服务。
## 执行规则
- 围绕「Core Workflow References / Artifact Layout References / Workflow Mechanic References」组织步骤,不把推断写成作者事实。
- 读取文件、写入/修改文件、执行终端命令;主要在本地完成;通常不需要额外 API Key。
- 先跑小样例,确认结果可检查后再扩大任务范围。
## 输出要求
- 给出最终产物、关键证据、验证方式和下一步动作。
- 信息不足时标记 unknown,不编造命令、平台或依赖。 作者原文负责流程事实;仓库文件负责来源和命令;流狐只补充适用场景、限制和质量判断。
skill "skill-writer" {
输入层 -> 用户目标 + 目标文件 + 禁止范围 + 验收标准
上下文层 -> Core Workflow References / Artifact Layout References / Workflow Mechanic References
规则层 -> SKILL.md 触发条件 / 执行顺序 / 输出格式
运行层 -> 无特殊运行时 | 读取文件、写入/修改文件、执行终端命令 | 主要在本地完成
安全层 -> 通常不需要额外 API Key + 小任务验证 + diff / 日志复核
输出层 -> 可复制结果 + 检查清单 + 下一步迭代
} Skill Writer
Use this as the single canonical workflow for skill creation and improvement. Primary success condition: maximize high-value input coverage before authoring while minimizing wasted runtime tokens.
Follow the workflow steps in order. Load only the reference files required for the step you are on.
SKILL.md is the primary router: every bundled reference file should be flat under references/ and listed here with a direct "open when..." reason.
Core Workflow References
| Open when you need to... | Read |
|---|---|
| choose the minimum workflow path for create, update, iterate, or research-first work | references/mode-selection.md |
| choose the simplest adequate execution shape before deciding files | references/execution-shapes.md |
| apply writing constraints for depth, concision, and portability | references/design-principles.md |
decide what belongs in SKILL.md, references/, SPEC.md, or supporting files |
references/reference-architecture.md |
| create or update the maintenance contract for a skill | references/spec-template.md |
| find missing high-signal sources, including history and regressions | references/source-discovery.md |
| adapt an upstream prompt, workflow, rubric, benchmark, or docs into a skill | references/source-adaptation.md |
| run the full synthesis pass with coverage checks and source capture | references/synthesis-path.md |
author or update SKILL.md, SPEC.md, and supporting files |
references/authoring-path.md |
| improve trigger language and false-positive/false-negative behavior | references/description-optimization.md |
| iterate from positive, negative, or fix examples | references/iteration-path.md |
| store persistent working and holdout examples for future revisions | references/iteration-evidence.md |
| choose a response template, schema, or output contract | references/output-contracts.md |
| troubleshoot overloaded layouts, hidden refs, or other structure failures | references/structure-troubleshooting.md |
| register the skill and run final validation checks | references/registration-validation.md |
Artifact Layout References
| Open when you need to... | Read |
|---|---|
keep the whole skill inline in one coherent SKILL.md |
references/layout-inline-skill.md |
| split optional deep knowledge into focused routed references | references/layout-reference-backed-skill.md |
| add scripts for deterministic automation or validation | references/layout-script-backed-workflow.md |
| define a skill that is usually invoked with explicit arguments | references/layout-argument-driven-skill.md |
| ship reusable templates, schemas, or other static assets | references/layout-asset-template-skill.md |
Workflow Mechanic References
| Open when you need to... | Read |
|---|---|
| break a task into fixed ordered steps | references/workflow-prompt-chaining.md |
| classify requests and route them to different downstream paths | references/workflow-routing.md |
| split independent work into parallel units or votes | references/workflow-parallel.md |
| discover work units dynamically and coordinate worker outputs | references/workflow-orchestrator-workers.md |
| run validate-fix-repeat checks during authoring or execution | references/workflow-validation-loops.md |
| validate a plan before executing a risky action | references/workflow-plan-validate-execute.md |
Claude Code References
| Open when you need to... | Read |
|---|---|
| use Claude-specific frontmatter or invocation controls | references/claude-frontmatter-invocation.md |
| use Claude argument fields or substitution variables | references/claude-argument-substitutions.md |
build a skill that runs in isolated context: fork |
references/claude-subagent-fork.md |
| build a skill that uses Claude hooks for deterministic enforcement | references/claude-hook-backed.md |
| use Claude shell preprocessing for dynamic context injection | references/claude-dynamic-context.md |
Example Profiles
| Open when you need to... | Read |
|---|---|
| see the expected depth for a documentation-heavy skill | references/example-documentation-skill.md |
| see the expected depth for a workflow-process skill | references/example-workflow-process-skill.md |
| see what a good routed skill looks like | references/example-router-skill.md |
| see what a good subagent-fork skill looks like | references/example-subagent-fork-skill.md |
| see what a good hook-backed skill looks like | references/example-hook-backed-skill.md |
Step 1: Resolve target, path, and shape
- Resolve the intended operation (
create,update,synthesize,iterate) and inspect workspace prior art before choosing where files belong. - Choose the target skill root from observed conventions. If the canonical location is still unclear after inspection, ask one direct question before editing files.
- Read
references/mode-selection.mdto choose the minimum required workflow paths. - Read
references/execution-shapes.mdto choose the primary execution shape. - Default to the simplest adequate shape. If selecting a more complex shape, record why simpler shapes were rejected.
- Load only the exact artifact-layout, workflow-mechanic, and provider-specific leaf files required by that shape.
- Before adding guidance, identify what existing rule, section, or file should be narrowed, replaced, or removed.
- Record portability implications before using provider-specific mechanics.
Step 2: Run synthesis when needed
Read references/synthesis-path.md.
- Use this path for new skills, material changes, and research-first planning.
- Collect and score relevant sources with provenance.
- Read
references/source-discovery.mdwhen source material is thin, stale, or ambiguous. - Read
references/source-adaptation.mdwhen adapting an upstream prompt, workflow, rubric, benchmark, or docs. - Produce source-backed decisions and coverage/gap status, including the class and execution-shape choice.
- Load example profiles only when they add concrete depth for the selected class or shape.
- If the skill uses provider-specific mechanics, include current official provider docs and capture usage constraints.
- Do not move to authoring until required coverage is understood or gaps are explicit.
Step 3: Run iteration first when improving from outcomes/examples
Read references/iteration-path.md first when selected path includes iteration (for example operation iterate).
- Capture and anonymize examples with provenance.
- Read
references/iteration-evidence.mdwhen examples should persist beyond the current turn. - Review skill behavior against working and holdout slices.
- Propose improvements from positive/negative/fix evidence.
- Carry concrete behavior deltas into authoring.
Skip this step when selected path does not include iteration.
Step 4: Author or update skill artifacts
Read references/authoring-path.md.
- Write or update
SKILL.mdin imperative voice with trigger-rich description. - Keep
SKILL.mdas the runtime router, not an encyclopedia. - Run the pre-edit precision check in
references/authoring-path.mdbefore creating new sections or files. - Read
references/reference-architecture.mdbefore adding bulk instructions or new reference files. - Create or update
SPEC.mdusingreferences/spec-template.mdwhen creating a new skill or materially changing its contract. - Create focused reference files, scripts, and assets only when each one has a clear "open when..." reason and cannot be handled by tightening an existing file.
- If you add a bundled reference file, add a direct routing entry for it in this
SKILL.md. - Prefer checklists, tables, templates, and input/output examples over explanatory prose.
- Follow only the specific artifact-layout, workflow-mechanic, Claude-specific, and output-contract references selected for this skill.
- For advanced execution shapes, add the required routing, delegation, or safety contracts before considering the skill complete.
- For authoring/generator skills, include transformed examples in references:
- happy-path
- secure/robust variant
- anti-pattern + corrected version
- After any skill artifact changes, run the post-change precision pass in
references/authoring-path.mdbefore description optimization or validation.
Step 5: Optimize description quality
Read references/description-optimization.md.
- Validate should-trigger and should-not-trigger query sets.
- Reduce false positives and false negatives with targeted description edits.
- Keep trigger language generic across providers unless the skill is intentionally provider-specific.
Step 6: Register and validate
Read references/registration-validation.md.
- Apply repository registration steps for the active layout you verified in the workspace.
- Run quick validation for structural checks.
- Review validator warnings, precision-pass results, and coverage gaps with judgment before completion.
Output format
Return:
SummaryChanges MadeValidation ResultsOpen Gaps
先判断是否适合
作者设计意图
作者的方法与取舍
边界和复核