Prompt

# Ground Prompt in your agent

## Objective
Use “Prompt” precisely in code, documentation, and conversations: Text or content supplied to a model to frame the task, context, constraints, and expected output form.

## Prerequisites
- Inspect how the term is used today in the repository, documentation, and prompts.
- Identify the neighboring notions already named: Skill, Tool, Agent.
- Preserve existing correct usages.

## Working definition
Text or content supplied to a model to frame the task, context, constraints, and expected output form.

## Decisive difference
A prompt is a current instruction; a skill is a versioned, discoverable procedure for repeated tasks.

## Example that counts as Prompt
Summarize this report into five decisions, with a source for every claim.

## Counter-example
An executable that opens a browser is not a prompt: it is a tool.

## Acceptance criteria
- Every use of the term matches the working definition.
- Edge cases are settled with the decisive difference, not by intuition.
- Neighboring notions (Skill, Tool, Agent) are named with their own term.

## Guardrails
- Show the proposed changes before any external action.
- Do not publish, send, delete, pay for, or change remote state without explicit authorization.
- Preserve unrelated changes and stop if the scope becomes ambiguous.

## Output format
- Outcome or verdict.
- Files or actions involved.
- Checks run and observable evidence.
- Remaining blockers or limitations.

• Requires · The agentic vocabulary already used in the repository and documentation

# Map the neighboring notions

## Objective
Extend the same rigor to the related notions (Skill, Tool, Agent) so the project vocabulary stays coherent.

## Checks
- List every neighboring notion used without a definition.
- Apply its documented decisive difference.
- Record the still-ambiguous cases for the next entry.

## Guardrails
- Show the proposed changes before any external action.
- Do not publish, send, delete, pay for, or change remote state without explicit authorization.
- Preserve unrelated changes and stop if the scope becomes ambiguous.

## Output format
- Outcome or verdict.
- Files or actions involved.
- Checks run and observable evidence.
- Remaining blockers or limitations.

sha256:a73a9e5eb9b88fedb9f174714b3f731e262150a72ef3cf8c323aa0022f14cb27

# Fix a mix-up around Prompt

## Observed symptom
[DESCRIBE THE SYMPTOM HERE]

## Observable checks
- Compare the disputed usage with the working definition: Text or content supplied to a model to frame the task, context, constraints, and expected output form.
- Apply the decisive difference: A prompt is a current instruction; a skill is a versioned, discoverable procedure for repeated tasks.
- Confront the case with the documented counter-example: An executable that opens a browser is not a prompt: it is a tool.

## Possible causes
- The term is used for a neighboring notion (Skill, Tool, Agent).
- The observed form (interface, script, service) is confused with the actual behavior.
- The term is used without a shared definition in the project.

## Bounded fixes
- Rename or reclassify only the usages that contradict the working definition.
- Document each choice by citing the decisive difference.

## Final verification
- Reread every corrected occurrence against the documented example and counter-example.

## Guardrails
- Show the proposed changes before any external action.
- Do not publish, send, delete, pay for, or change remote state without explicit authorization.
- Preserve unrelated changes and stop if the scope becomes ambiguous.

## Output format
- Outcome or verdict.
- Files or actions involved.
- Checks run and observable evidence.
- Remaining blockers or limitations.

• Requires · The agentic vocabulary already used in the repository and documentation

# Anchor the vocabulary in the project

## Objective
Turn the clarification into a reusable rule so the mix-up does not return.

## Checks
- Add the working definition to the project glossary.
- Link every neighboring term to its own entry.
- Check new documents against the decisive difference.

## Guardrails
- Show the proposed changes before any external action.
- Do not publish, send, delete, pay for, or change remote state without explicit authorization.
- Preserve unrelated changes and stop if the scope becomes ambiguous.

## Output format
- Outcome or verdict.
- Files or actions involved.
- Checks run and observable evidence.
- Remaining blockers or limitations.

sha256:264896534714aeee998763e6476c93a2f1ea07a351d620586050c543d3f09c91