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

feat: add comprehensive agent rules and workflows for memory curation, communication synchronization, and project documentation management

Browse Source
This commit is contained in:
David Delagneau
2026-04-27 10:41:03 -06:00
parent de7f2b02f6
commit 0e6957d0b3
57 changed files with 1359 additions and 1316 deletions
Download Patch File Download Diff File Expand all files Collapse all files

26
.opencode/skills/ai-prompt-engineering/SKILL.md
View File

@@ -1,26 +0,0 @@
---
name: ai-prompt-engineering
description: Create self-contained prompts for another AI assistant that lacks access to this workspace memory.
compatibility: opencode
---
## When To Use
Use this skill when the user wants a prompt for another AI assistant, coding agent, review tool, or implementation environment.
## Workflow
1. Identify target task type: investigation, implementation, review, testing, debugging, or documentation.
2. Pull only relevant workspace context.
3. Make the prompt self-contained.
4. Tell the target AI what to inspect before acting.
5. State constraints, non-goals, expected output, and validation expectations.
6. Avoid invented file paths when the implementation repository is not available.
## Output Rules
- Return only the prompt unless the user asks for commentary.
- Prefer clear sections over long prose.
- Include work-item ID and title when relevant.
- Make assumptions explicit.

1
.opencode/skills/ai-prompt-engineering/SKILL.md Symbolic link
View File

@@ -0,0 +1 @@
../../../.agents/rules/ai-prompt-engineering.md

47
.opencode/skills/copilot-prompt-engineering/SKILL.md
View File

@@ -1,47 +0,0 @@
---
name: copilot-prompt-engineering
description: Create high-quality prompts for GitHub Copilot or another AI running on the Fidelity development machine, using this workspace's context without assuming the target AI has access to it.
compatibility: opencode
---
## When To Use
Use this skill when the user wants a prompt for another AI assistant, GitHub Copilot, or the Fidelity development machine.
## Workflow
1. Identify the target task type:
- investigation
- implementation plan
- code change
- review
- test strategy
- story/PR drafting
2. Pull only the relevant context:
- `project-knowledge/02-work-items/` for ticket-specific context
- `project-knowledge/03-context/systems/` for component context
- `project-knowledge/03-context/workstreams/` for recurring constraints
- `project-knowledge/03-context/ios/` for Swift/iOS guidance
3. Make the prompt self-contained.
4. Tell the target AI what to inspect before acting.
5. State constraints, non-goals, and validation expectations.
## 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.
- For follow-up prompts in the same AI session, assume recent shared context and avoid repeating which side made the previous changes unless it matters for the task.
- 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 XFlow work, say behavior may depend on entry point, auth state, backend config, and consumer integration.
- For AO/Discourse issues, say external report vs regression must be separated.
- For SwiftUI/XFlow work, mention lifecycle, modal presentation, UIKit bridge, feature flag, and Fid4 validation if relevant.
## Output Rules
- Return only the prompt unless the user asks for explanation.
- Keep the prompt concise but complete.
- Prefer sections over paragraphs.
- Do not invent file paths unless the workspace context explicitly names them.
- If exact files are unknown, ask Copilot to locate them first.

1
.opencode/skills/copilot-prompt-engineering/SKILL.md Symbolic link
View File

@@ -0,0 +1 @@
../../../.agents/rules/copilot-prompt-engineering.md

28
.opencode/skills/ios-swift-answering/SKILL.md
View File

@@ -1,28 +0,0 @@
---
name: ios-swift-answering
description: Answer Swift, SwiftUI, and iOS programming questions using current Apple guidance while adapting recommendations to Fidelity/XFlow project constraints.
compatibility: opencode
---
## When To Use
Use this skill for Swift, SwiftUI, iOS architecture, concurrency, testing, or debugging questions.
## Workflow
1. Identify whether the question is general Swift/iOS or Fidelity-specific.
2. Read `project-knowledge/03-context/ios/current-practices.md` for currentness rules.
3. Read `project-knowledge/03-context/ios/project-swift-guidance.md` when the answer may affect XFlow, Fid4, XFlowViewMaker, FTFrameworks, feature flags, or consumer validation.
4. If the answer depends on current Apple APIs, Xcode versions, dependency tooling, package-manager behavior, testing frameworks, or migration guidance, verify with official/primary documentation before making strong claims.
5. Separate:
- current best practice
- project-safe recommendation
- assumptions to confirm
## Output Rules
- Be direct and senior-engineer practical.
- Avoid generic architecture advice when project constraints matter.
- Do not assume deployment target, Xcode version, or framework migration status.
- Do not characterize CocoaPods, SPM, podspec repos, trunk/CDN behavior, CI/build behavior, or testing framework practices as good or bad practice without corroborating current primary docs when the recommendation matters.
- Mention tradeoffs and validation path when relevant.

1
.opencode/skills/ios-swift-answering/SKILL.md Symbolic link
View File

@@ -0,0 +1 @@
../../../.agents/rules/ios-swift-answering.md

34
.opencode/skills/ios-testing-strategy/SKILL.md
View File

@@ -1,34 +0,0 @@
---
name: ios-testing-strategy
description: Recommend iOS testing approaches for Swift, SwiftUI, XFlow, Fid4, and REST migration work while respecting existing XCTest/Swift Testing/project constraints.
compatibility: opencode
---
## When To Use
Use this skill for unit tests, UI tests, integration tests, regression coverage, XFlow flow validation, or REST/GraphQL migration testing questions.
## Workflow
1. Identify the behavior under test.
2. Classify the test level:
- unit
- integration
- UI / consumer flow
- exploratory validation
3. Check whether the behavior depends on backend configuration, auth state, entry point, feature flags, or Fid4 integration.
4. Prefer the test framework already used by the project unless the user asks about migration.
5. If suggesting Swift Testing, confirm Xcode/project support first and do not mix APIs inside the same test.
## Project-Specific Guidance
- XFlow behavior may require exploratory validation beyond unit tests.
- AO/Discourse issues often need auth-state and entry-point coverage.
- REST migration tests must distinguish REST path from GraphQL fallback.
- Consumer-facing changes may require Fid4 validation even when SDK tests pass.
## Output Rules
- Recommend the smallest useful test strategy.
- Include what cannot be proven by that test layer.
- Mention manual/exploratory validation when code-level tests are insufficient.

1
.opencode/skills/ios-testing-strategy/SKILL.md Symbolic link
View File

@@ -0,0 +1 @@
../../../.agents/rules/ios-testing-strategy.md

24
.opencode/skills/professional-communication/SKILL.md
View File

@@ -1,24 +0,0 @@
---
name: professional-communication
description: Rewrite rough technical notes into clear, concise, stakeholder-ready professional English while preserving scope and technical meaning.
compatibility: opencode
---
## When To Use
Use this skill for manager updates, stakeholder messages, translations, issue clarification, Jira comments, and communication polishing.
## Workflow
1. Identify audience, purpose, scope, and requested action.
2. Preserve technical meaning and uncertainty.
3. Make ownership, reproducibility, environment, and next action explicit when relevant.
4. Use Context, Observation, Action when it improves readability.
5. Avoid vague comparisons and generic progress language.
## Output Rules
- Write natural professional US English.
- Keep messages concise enough for workplace chat unless the user asks for a longer document.
- Do not invent facts, evidence, or commitments.

1
.opencode/skills/professional-communication/SKILL.md Symbolic link
View File

@@ -0,0 +1 @@
../../../.agents/rules/professional-communication.md

25
.opencode/skills/status-reporting/SKILL.md
View File

@@ -1,25 +0,0 @@
---
name: status-reporting
description: Generate work-item-aware standups and status summaries from current workspace memory, recent logs, and communication evidence.
compatibility: opencode
---
## When To Use
Use this skill for standups, daily scrum updates, end-of-day summaries, and short progress reports.
## Workflow
1. Read current state, active work items, recent logs, and latest communication evidence.
2. Use the previous workday as the default source for "Yesterday" style updates.
3. Group updates by work item when possible.
4. If one work item has multiple concrete updates, use one top-level work-item bullet with indented markdown sub-bullets.
5. Exclude side chatter unless it changed work scope, priority, risk, or blockers.
## Output Rules
- Use explicit work-item ID and title when available.
- Keep the report concise and ready to send.
- Do not mention internal evidence sources unless the user asks.
- Use `Blockers: None` only when no blocker is visible in current memory.

1
.opencode/skills/status-reporting/SKILL.md Symbolic link
View File

@@ -0,0 +1 @@
../../../.agents/rules/status-reporting.md

31
.opencode/skills/swiftui-xflow-review/SKILL.md
View File

@@ -1,31 +0,0 @@
---
name: swiftui-xflow-review
description: Review or reason about SwiftUI code in XFlow/Fidelity contexts, especially lifecycle, modal presentation, navigation, backend-driven UI, and UIKit bridge removal.
compatibility: opencode
---
## When To Use
Use this skill when a SwiftUI question touches XFlow, Fid4, XFlowViewMaker, modal presentation, dismissal sequencing, navigation, `UIHostingController`, or backend-driven UI behavior.
## Review Heuristics
- Check whether behavior is driven by backend configuration before blaming local SwiftUI code.
- Identify data ownership and view lifecycle boundaries.
- Treat dismissal sequencing as high risk when delegate callbacks, `onDisappear`, or upstream state changes are involved.
- Treat UIKit bridge removal as rollout-sensitive, not just cleanup.
- Separate SwiftUI best practice from Fidelity-safe migration strategy.
## Fidelity-Specific Checks
- Does the change preserve UIKit/SwiftUI parity?
- Does it require a feature flag?
- Does it need validation in Fid4 or only XFlowSDK?
- Could XFlowViewMaker or FTFrameworks block consumer visibility?
- Is the issue external behavior, existing behavior, or a regression?
## Output Rules
- Provide a clear recommendation.
- Include risks and validation path.
- Avoid recommending a pure SwiftUI approach without noting rollout and consumer validation impact.

1
.opencode/skills/swiftui-xflow-review/SKILL.md Symbolic link
View File

@@ -0,0 +1 @@
../../../.agents/rules/swiftui-xflow-review.md

25
.opencode/skills/workspace-memory-curation/SKILL.md
View File

@@ -1,25 +0,0 @@
---
name: workspace-memory-curation
description: Maintain file-based operational memory by deciding what to log, promote, correct, or route into tool behavior across reusable AI workspaces.
compatibility: opencode
---
## When To Use
Use this skill when new information may change workspace memory, project state, work-item context, people context, decisions, or reusable agent/tool behavior.
## Workflow
1. Read `core/memory/operational-memory.md`.
2. Classify the information as daily, state, work-item, stable-context, people, decision, or tooling-behavior.
3. Update the smallest correct canonical file.
4. If new information corrects older memory, replace or refine the stale statement instead of appending a contradiction.
5. If a correction affects future output, update the command, prompt, agent, skill, or knowledge file that controls that behavior.
6. Keep imported evidence separate from promoted memory.
## Output Rules
- Report updated files and the memory change.
- Preserve uncertainty when confidence is mixed.
- Do not promote tool failures, sync noise, or generic chat chatter as project facts.

1
.opencode/skills/workspace-memory-curation/SKILL.md Symbolic link
View File

@@ -0,0 +1 @@
../../../.agents/rules/workspace-memory-curation.md