Agent Skills
› shinpr/claude-code-workflows
› llm-friendly-context
llm-friendly-context
GitHub旨在优化LLM交互上下文，通过明确指令、具体标准、输出格式及不确定性处理，确保下游智能体无需猜测即可稳定执行。适用于编写或修订提示词、交接文档及计划任务。
Trigger Scenarios
编写或修订面向LLM的提示词
创建或优化智能体间的工作交接说明
生成或审查规划类工件与报告
将模糊指令转化为可执行的具体步骤
Install
npx skills add shinpr/claude-code-workflows --skill llm-friendly-context -g -y
SKILL.md
Frontmatter
{
"name": "llm-friendly-context",
"description": "Clarifies inputs, outputs, success criteria, decisions, and unresolved conditions so downstream agents can execute without guessing. Use when writing or revising LLM-facing prompts, handoffs, planning artifacts, reviews, reports, or generated instructions."
}
LLM-Friendly Context
The goal is stable downstream execution: the next agent should know what to read, what to do, what counts as success, and when to stop or escalate.
Core Rules
-
Use positive, executable instructions
- State what the next agent should do.
- Convert quality policies into positive criteria.
- Example: "Preserve existing public API behavior across the documented compatibility cases."
-
Make vague instructions concrete
- Replace subjective terms with observable conditions, paths, commands, schemas, examples, or decision rules.
- Terms that often need clarification when they leave a decision to the next agent:
appropriate,proper,related,existing behavior,optional,as needed,if needed,per convention, unresolved alternatives,TBD,placeholder.
-
Specify output shape
- Define required sections, fields, table columns, JSON keys, or checklist items.
- For handoffs, include paths to produced artifacts and the exact status fields the caller must inspect.
-
Provide necessary context
- Include the purpose, source artifacts, hard constraints, accepted decisions, and unresolved conditions.
- Prefer concrete file paths and section hints over broad module names.
-
Decompose complex work into verifiable steps
- Split work with 3+ objectives or sequential dependencies into ordered steps.
- Each step needs a checkpoint: what evidence proves it is complete.
-
Permit uncertainty explicitly
- If the source material is missing, contradictory, or not verifiable, state the uncertainty and the required escalation.
- Record unknown business, product, security, or compatibility decisions as blocking unresolved items with the input needed to resolve them.
-
Keep constraints proportionate
- Add only constraints that reduce ambiguity or preserve a real requirement.
- Keep simple downstream tasks lightweight when the target action, context, and success criteria are already clear.
Rewrite Patterns
Use these rewrites before treating a prompt, handoff, or artifact as complete.
| Ambiguous form | Rewrite as |
|---|---|
optional used as an unresolved choice |
Required, omitted, or required only under a named condition |
| Multiple alternatives that the next agent must choose between | The selected option, or a deterministic decision rule |
as needed / if needed |
The triggering condition and required action |
per convention |
The file, function, test, or documented convention to follow |
related files |
Specific paths, globs, or search hints |
existing behavior |
The observable behavior, source file, test, API response, or UI state to preserve |
placeholder |
Exact temporary value/behavior, allowed dependencies, and verification expectation |
TBD used as a placeholder for required information |
A blocking unresolved item with owner, required input, or escalation condition |
appropriate / proper |
A measurable criterion or checklist |
Handoff Checklist
Before sending a prompt or artifact to another agent, verify:
- The target action is explicit.
- Required input paths and source artifacts are named.
- Accepted decisions and constraints are stated once, without alternate wording.
- Output format or expected status fields are specified.
- Success criteria are observable.
- Ambiguous expressions have been rewritten or marked as unresolved.
- The next agent can complete its scope with explicit choices, decision rules, or blocking unresolved items.
Generated Artifact Checklist
Before writing or finalizing a generated document:
- Each requirement, claim, task, test skeleton, or review finding has enough source context to trace why it exists.
- Every executable instruction names the target, action, and expected result.
- Verification steps say what to run or observe and what result proves success.
- If an artifact is derived from another artifact, copied decisions stay consistent in wording and meaning.
- If downstream work is blocked by missing information, the artifact records the missing input and escalation condition.
Version History
- 66e3b29 Current 2026-07-05 11:58
