Skill

# Ground Skill in your agent

## Objective
Use “Skill” precisely in code, documentation, and conversations: A versionable directory of instructions and resources that an agent can discover and load to apply a reusable procedure.

## Prerequisites
- Inspect how the term is used today in the repository, documentation, and prompts.
- Identify the neighboring notions already named: Prompt, Tool, Model Context Protocol (MCP).
- Preserve existing correct usages.

## Working definition
A versionable directory of instructions and resources that an agent can discover and load to apply a reusable procedure.

## Decisive difference
A skill organizes know-how; it is neither the tool that acts, the agent that chooses, nor a one-off prompt.

## Example that counts as Skill
A UI audit skill describes its triggers, steps, evidence, and references to load.

## Counter-example
A single API request without a decision procedure is not a complete skill.

## Acceptance criteria
- Every use of the term matches the working definition.
- Edge cases are settled with the decisive difference, not by intuition.
- Neighboring notions (Prompt, Tool, Model Context Protocol (MCP)) 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- Do not publish, send, delete, pay for, or change remote state without explicit authorization.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 (Prompt, Tool, Model Context Protocol (MCP)) 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- Do not publish, send, delete, pay for, or change remote state without explicit authorization.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:e5a42123cc1f73ad61130b4f110f0ae8759d3b96483aeadcff7e813436cfc7d2

# Fix a mix-up around Skill

## Observed symptom
[DESCRIBE THE SYMPTOM HERE]

## Observable checks
- Compare the disputed usage with the working definition: A versionable directory of instructions and resources that an agent can discover and load to apply a reusable procedure.
- Apply the decisive difference: A skill organizes know-how; it is neither the tool that acts, the agent that chooses, nor a one-off prompt.
- Confront the case with the documented counter-example: A single API request without a decision procedure is not a complete skill.

## Possible causes
- The term is used for a neighboring notion (Prompt, Tool, Model Context Protocol (MCP)).
- The observed form (interface, script, service) is confused with the actual behavior.
- An alias (Agent Skill, SKILL.md) carries a different meaning 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.

sha256:9b527351b153e0f749a8108a28323158bc6957d86cf0379d0389e5160e3aaedb