david.delagneau/fidelity-ai-workspace
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: Update prompting rules to emphasize English usage, first-person phrasing, and conciseness for AI prompts

Browse Source
This commit is contained in:
David Delagneau
2026-04-20 16:00:05 -06:00
parent 6409539c0b
commit a921d5f7ce
2 changed files with 6 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
.opencode/skills/copilot-prompt-engineering/SKILL.md
View File

@@ -28,6 +28,9 @@ Use this skill when the user wants a prompt for another AI assistant, GitHub Cop
## Fidelity Prompting Rules ## Fidelity Prompting Rules
- Write the final prompt in English unless the user explicitly requests another language.
- Default to first-person wording so the user can paste the prompt directly into Copilot.
- Keep the prompt short unless the user asks for more detail.
- Include Jira ID and approved title when available. - Include Jira ID and approved title when available.
- For REST work, say REST is behind a feature flag and GraphQL is fallback unless confirmed otherwise. - For REST work, say REST is behind a feature flag and GraphQL is fallback unless confirmed otherwise.
- For XFlow work, say behavior may depend on entry point, auth state, backend config, and consumer integration. - For XFlow work, say behavior may depend on entry point, auth state, backend config, and consumer integration.

3
agent-memory/workflows/ai-to-ai-prompting.md
View File

@@ -45,6 +45,9 @@ Use this structure by default:
## Prompt Quality Rules ## Prompt Quality Rules
- Write prompts in English by default for GitHub Copilot and other development-machine AI tools unless the user explicitly asks for another language.
- Prefer first-person phrasing when drafting a prompt the user will paste directly into another AI tool, unless the user asks for a different voice.
- Keep prompts concise by default; include only the context needed for correct execution.
- Prefer precise task framing over long background dumps. - Prefer precise task framing over long background dumps.
- Include Jira ID and title when the work maps to a ticket. - Include Jira ID and title when the work maps to a ticket.
- Include current constraints such as REST feature flag, GraphQL fallback, auth state, backend-driven behavior, and consumer validation when relevant. - Include current constraints such as REST feature flag, GraphQL fallback, auth state, backend-driven behavior, and consumer validation when relevant.