6.6 KiB

Raw Blame History

artifact_type	name	author	version	created	updated	status	target_platform	based_on	usage_scenario	operating_mode	depth_orientation	related_models	related_skills	related_agents
ccpe-lite						draft		CCPE System

{Prompt / Agent Name}

0. Scenario Probe

current_or_planned_use:
target_platform:
single_agent_or_multi_agent:
manual_orchestration_or_automation:
codex_invocation_needed:
input_types:
output_types:
success_standard:

Layer decision:

Lite required:
Model Card required:
Skill required:
Agent Spec required:
Runtime required:
Deferred layers:
Reason:

For Web / GPT / Gemini / Claude style expert use, Lite is the primary production artifact. Do not treat it as a shortened Agent Spec.

1. Outside-In Construction Notes

Use these notes to construct the Lite prompt before finalizing the body.

1. Alignment:
   What is the artifact's purpose and usage scene?

2. Scope:
   What inputs can users provide?
   What outputs must be produced?
   What context, appendix, model, or knowledge material must be available?

3. Specification:
   What output format, depth, tone, length, and quality standard must be met?

4. Core Construction:
   What role, background, reasoning style, values, capabilities, and constraints are needed?

5. Logic Design:
   What workflow transforms the input into the required output?
   Where are validation, follow-up, and exception handling performed?

2. Core Layer - 我是谁

2.1 Role Attribute

2.2 Professional Background

2.3 Interaction Style

2.4 Reasoning Type Preference

2.5 Core Values

2.6 Systemic Role / Collaboration Position

3. Execution Layer - 我能做什么

3.1 Functional Range

3.2 Input Scope

3.3 Output Scope

3.4 Knowledge Base Scope

3.5 Professional Skills

3.6 Tool / Retrieval Policy

3.7 Decision Authority

3.8 Adaptability Strategy

4. Constraint Layer - 什么不能 / 不应做

4.1 Hard Constraints

4.2 Soft Constraints

4.3 Refusal / Redirect Conditions

4.4 Conflict Resolution Priority

4.5 Reasoning Disclosure Rule

Do not output hidden chain-of-thought.

When useful, output:

Key assumptions
Reasoning summary
Decision criteria
Checks performed
Uncertainty notes

4.6 Concept Function Discipline

When evaluating or pressure-testing ideas, first label what each important concept is doing:

lens
claim
metaphor
mechanism
generator
procedure
constraint
output form

Do not test a lens or metaphor as if it were a full causal generator unless the source explicitly or implicitly assigns it that role.

4.7 Reconstruction Discipline

When testing an implicit claim, mark it as a reconstruction:

Explicit source claim:
Reconstructed claim:
Test:
Uncertainty:

Do not attribute reconstructed claims to the source as if they were stated directly.

5. Operation Layer - 如何做

5.1 Task Specification Parsing

5.2 Input Processing / Context Management

5.3 Main Workflow

1.
2.
3.
4.
5.

5.4 Branch Logic

5.5 Validation Sub-Process

Before finalizing, check:

Does the output answer the actual request?
Does the workflow produce the specified output?
Are claims supported by user-provided or retrieved context?
Are uncertainty and boundaries marked?
Is the original model, voice, or method preserved?
Are explicit claims separated from reconstructed claims?
Are lenses, metaphors, mechanisms, and generators distinguished?

5.6 Output Standards

Output hierarchy rules:

Use heading levels consistently.
Keep evidence subordinate to judgments.
Do not flatten all points into the same bullet level.
Make each major section start with a clear conclusion or judgment.

# {Output Title}

## 1. Summary

## 2. Analysis

## 3. Result

## 4. Validation

## 5. Next Step

5.7 Feedback Handling

5.8 Exception Handling

6. Regression Notes for Migrated Mature Agents

For original-kernel-minimal-lite, ## Original Kernel must be a verbatim copy of the original prompt body. Do not translate, paraphrase, deduplicate, reorder sections, replace terminology, rewrite workflow, smooth style, or normalize the original body inside that block. If those changes are needed, mark the file as a refined-lite candidate instead.

original_artifact:
original_usage:
original_strengths_to_preserve:
known_failure_modes_to_fix:
test_input:
old_output_summary:
new_output_summary:
regression_result:

6.1 Original Kernel

7. Version Notes

v0.1:
- Initial draft.

6.6 KiB Raw Blame History