Consolidate agent guidance for Copilot and Claude Code

.github/skills/atlassian-readonly-skills/SKILL.md → .claude/skills/atlassian-readonly-skills/SKILL.md

@@ -33,13 +33,13 @@ Read-only Python utilities for Jira, Confluence, and Bitbucket integration, supp
 
 ```powershell
 # Get a single issue (inline Python one-liner)
-python -c "import sys; sys.path.insert(0, '.github/skills/atlassian-readonly-skills/scripts'); from jira_issues import jira_get_issue; print(jira_get_issue('LT-22382'))"
+python -c "import sys; sys.path.insert(0, '.claude/skills/atlassian-readonly-skills/scripts'); from jira_issues import jira_get_issue; print(jira_get_issue('LT-22382'))"
 
 # Search for issues (JQL query)
-python -c "import sys; sys.path.insert(0, '.github/skills/atlassian-readonly-skills/scripts'); from jira_search import jira_search; print(jira_search('project = LT AND status = Open'))"
+python -c "import sys; sys.path.insert(0, '.claude/skills/atlassian-readonly-skills/scripts'); from jira_search import jira_search; print(jira_search('project = LT AND status = Open'))"
 
 # Get issue workflow transitions
-python -c "import sys; sys.path.insert(0, '.github/skills/atlassian-readonly-skills/scripts'); from jira_workflow import jira_get_transitions; print(jira_get_transitions('LT-22382'))"
+python -c "import sys; sys.path.insert(0, '.claude/skills/atlassian-readonly-skills/scripts'); from jira_workflow import jira_get_transitions; print(jira_get_transitions('LT-22382'))"
 ```
 
 Use the script modules in this skill directly.

.github/skills/atlassian-skills/SKILL.md → .claude/skills/atlassian-skills/SKILL.md

@@ -33,16 +33,16 @@ Python utilities for Jira, Confluence, and Bitbucket integration, supporting bot
 
 ```powershell
 # Create a new issue
-python -c "import sys; sys.path.insert(0, '.github/skills/atlassian-skills/scripts'); from jira_issues import jira_create_issue; print(jira_create_issue('LT', 'Issue title', 'Bug'))"
+python -c "import sys; sys.path.insert(0, '.claude/skills/atlassian-skills/scripts'); from jira_issues import jira_create_issue; print(jira_create_issue('LT', 'Issue title', 'Bug'))"
 
 # Update an existing issue
-python -c "import sys; sys.path.insert(0, '.github/skills/atlassian-skills/scripts'); from jira_issues import jira_update_issue; print(jira_update_issue('LT-22382', summary='Updated title'))"
+python -c "import sys; sys.path.insert(0, '.claude/skills/atlassian-skills/scripts'); from jira_issues import jira_update_issue; print(jira_update_issue('LT-22382', summary='Updated title'))"
 
 # Add a comment
-python -c "import sys; sys.path.insert(0, '.github/skills/atlassian-skills/scripts'); from jira_issues import jira_add_comment; print(jira_add_comment('LT-22382', 'Comment text'))"
+python -c "import sys; sys.path.insert(0, '.claude/skills/atlassian-skills/scripts'); from jira_issues import jira_add_comment; print(jira_add_comment('LT-22382', 'Comment text'))"
 
 # Transition issue status
-python -c "import sys; sys.path.insert(0, '.github/skills/atlassian-skills/scripts'); from jira_workflow import jira_transition_issue; print(jira_transition_issue('LT-22382', 'In Progress'))"
+python -c "import sys; sys.path.insert(0, '.claude/skills/atlassian-skills/scripts'); from jira_workflow import jira_transition_issue; print(jira_transition_issue('LT-22382', 'In Progress'))"
 ```
 
 For read-only operations (get issue, search, get comments), use `atlassian-readonly-skills` instead.

.github/skills/jira-bugfix/SKILL.md → .claude/skills/jira-bugfix/SKILL.md

@@ -53,7 +53,7 @@ Then proceed through the steps below.
 Use the `atlassian-readonly-skills` scripts to get the issue:
 
 ```powershell
-python -c "import sys; sys.path.insert(0, '.github/skills/atlassian-readonly-skills/scripts'); from jira_issues import jira_get_issue; print(jira_get_issue('LT-XXXXX'))"
+python -c "import sys; sys.path.insert(0, '.claude/skills/atlassian-readonly-skills/scripts'); from jira_issues import jira_get_issue; print(jira_get_issue('LT-XXXXX'))"
 ```
 
 Extract and present to the user:
@@ -76,7 +76,7 @@ the user for their JIRA username and assign it:
 # Assign the issue (Data Center uses 'name' field)
 python -c "
 import sys, json
-sys.path.insert(0, '.github/skills/atlassian-skills/scripts')
+sys.path.insert(0, '.claude/skills/atlassian-skills/scripts')
 from jira_issues import jira_update_issue
 print(jira_update_issue('LT-XXXXX', assignee='username'))
 "
@@ -94,15 +94,15 @@ print(jira_update_issue('LT-XXXXX', assignee='username'))
 # Get available transitions
 python -c "
 import sys
-sys.path.insert(0, '.github/skills/atlassian-readonly-skills/scripts')
+sys.path.insert(0, '.claude/skills/atlassian-readonly-skills/scripts')
 from jira_workflow import jira_get_transitions
 print(jira_get_transitions('LT-XXXXX'))
 "
 
 # Transition (use the ID for "In Progress" from above)
 python -c "
 import sys
-sys.path.insert(0, '.github/skills/atlassian-skills/scripts')
+sys.path.insert(0, '.claude/skills/atlassian-skills/scripts')
 from jira_workflow import jira_transition_issue
 print(jira_transition_issue('LT-XXXXX', 'TRANSITION_ID'))
 "
@@ -350,7 +350,7 @@ PR link:
 ```powershell
 python -c "
 import sys
-sys.path.insert(0, '.github/skills/atlassian-skills/scripts')
+sys.path.insert(0, '.claude/skills/atlassian-skills/scripts')
 from jira_issues import jira_add_comment
 comment = '''Fix implemented and PR created.
 

.github/AGENTS.md

@@ -1,6 +1,7 @@
-# FieldWorks Agentic Instructions
+# FieldWorks GitHub Compatibility
 
-Short repo-level instructions for agents.
+This folder exists for GitHub-required repository configuration and Copilot
+entrypoints.
 
 ## Build and test
 
@@ -10,8 +11,11 @@ Short repo-level instructions for agents.
 
 ## Documentation model
 
-- Keep AGENTS guidance minimal and requirement-only.
-- Source of prescriptive constraints is `.github/instructions/*.instructions.md`.
+- Shared standing guidance lives in `../AGENTS.md`.
+- GitHub-required custom instructions live in `.github/copilot-instructions.md`
+	and `.github/instructions/*.instructions.md`.
+- Claude-only workflows live in `../.claude/skills/` and should not be
+	duplicated under `.github/`.
 
 ## Serena operating model
 
@@ -32,14 +36,16 @@ Short repo-level instructions for agents.
 
 ## Relevant files
 
+- `../AGENTS.md`
+- `../CLAUDE.md`
 - `.github/instructions/build.instructions.md`
 - `.github/instructions/navigation.instructions.md`
 - `.github/instructions/testing.instructions.md`
 - `.github/instructions/managed.instructions.md`
 - `.github/instructions/native.instructions.md`
 - `.github/instructions/installer.instructions.md`
 - `.github/rubrics/*.yaml`
-- `.github/skills/rubric-verify/SKILL.md`
+- `../.claude/skills/rubric-verify/SKILL.md`
 - `Src/AGENTS.md`
 - `FLExInstaller/AGENTS.md`
 

.github/AI_GOVERNANCE.md

@@ -1,33 +1,44 @@
 # AI guidance governance
 
 ## Purpose
-This repo uses a **tool-agnostic, agent-first** documentation strategy:
-- Component knowledge lives with the component (`Src/**/AGENTS.md`).
-- A small set of scoped instruction files in `.github/instructions/` provides **prescriptive, enforceable constraints**.
-- `.github/AGENTS.md` is the short “front door” that links to the right places.
-- Agent definitions in `.github/agents/` and role chatmodes in `.github/chatmodes/` describe **behavior/persona**, not system architecture.
+This repo targets **GitHub Copilot** and **Claude Code** with a minimal,
+two-tool documentation model:
+- Shared standing guidance lives in root and nested `AGENTS.md` files.
+- GitHub-required custom instructions stay in `.github/` only where GitHub
+	requires exact paths.
+- Claude-only workflows live in `.claude/skills/`.
+- Agent definitions in `.github/agents/` and role chatmodes in
+	`.github/chatmodes/` describe behavior/persona, not system architecture.
 
 ## Source of truth
+- **Shared repo workflow**: `AGENTS.md` plus the nearest nested `AGENTS.md`
 - **Component architecture & entry points**: `Src/<Component>/AGENTS.md`
-- **Repo-wide workflow** (how to build/test, safety constraints): `.github/AGENTS.md`
-- **Non-negotiable rules** (security, terminal restrictions, installer rules, etc.): `.github/instructions/*.instructions.md`
+- **GitHub Copilot custom instructions**: `.github/copilot-instructions.md` and `.github/instructions/*.instructions.md`
+- **Claude Code workflows**: `.claude/skills/*/SKILL.md`
 
 ## No duplication rule
-- Do not copy component descriptions into `.github/instructions/`.
-- Do not restate rules in multiple places. Prefer linking.
-- If a rule must be enforced by agents for a subtree, add a scoped `.instructions.md`; otherwise document it in the relevant `AGENTS.md`.
+- Do not duplicate shared standing guidance across `AGENTS.md`, `CLAUDE.md`,
+	and GitHub compatibility files.
+- Keep each Claude skill in exactly one place: `.claude/skills/`.
+- GitHub prompt files may reference Claude skill paths, but do not keep a
+  mirrored `.github/skills/` tree.
+- If a rule must be auto-applied by GitHub Copilot, keep it in
+	`.github/instructions/*.instructions.md`; otherwise prefer the relevant
+	`AGENTS.md` or a Claude skill.
 
 ## What goes where
 
-### `.github/AGENTS.md`
+### `AGENTS.md`
 Use for:
-- One-page onboarding for agents: build/test commands, repo constraints, and links.
-- Pointers to the curated instruction set and the component docs.
+- One-page onboarding for both tools: build/test commands, repo constraints,
+  and links.
+- Stable, always-on guidance that should apply across sessions.
 
 ### `.github/instructions/*.instructions.md`
 Use for:
 - Prescriptive constraints that must be applied during editing/review.
-- Cross-cutting rules that prevent expensive mistakes (security, terminal command restrictions, installer rules, managed/native boundary rules).
+- Cross-cutting rules that GitHub Copilot needs through its official,
+  path-scoped instruction mechanism.
 
 **Curated keep set (intentionally small):**
 - `build.instructions.md`
@@ -53,9 +64,14 @@ Baseline expectations for a component agent doc:
 - **Dependencies** (other components/layers)
 - **Tests** (test projects and the recommended `./test.ps1` invocation)
 
+### `.claude/skills/`
+Use for:
+- Claude-only workflows, repeatable procedures, and task-specific guidance.
+- Put multi-step procedures here instead of inflating `CLAUDE.md`.
+
 ### `.github/agents/` and `.github/chatmodes/`
 Use for:
-- Role definitions, boundaries, and tool preferences.
+- GitHub Copilot role definitions, boundaries, and tool preferences.
 - Do not put component architecture here; link to the component `AGENTS.md`.
 
 ## External standards alignment (post-2025)
@@ -68,5 +84,6 @@ Add a new `.github/instructions/<name>.instructions.md` only when:
 - It applies broadly or to a subtree, and
 - It would be harmful if Copilot ignored it.
 
-Otherwise, update the appropriate `Src/**/AGENTS.md`.
+Otherwise, update the appropriate `AGENTS.md` or add a Claude skill under
+`.claude/skills/`.
 

.github/copilot-instructions.md

@@ -1,5 +1,10 @@
 # FieldWorks Copilot Code Review Instructions
 
+Prefer the shared repo guidance in `AGENTS.md` and the nearest nested
+`AGENTS.md` first. Keep GitHub-specific, path-scoped constraints in
+`.github/instructions/*.instructions.md`. Claude-only task workflows live in
+`.claude/skills/` and should not be mirrored under `.github/skills/`.
+
 ## Purpose
 
 Review FieldWorks pull requests for the project-specific risks most likely to

.github/prompts/pr-preflight.prompt.md

@@ -4,6 +4,6 @@ agent: "agent"
 argument-hint: "Optional branch purpose or PR goal"
 ---
 
-Use the `pr-preflight` skill from `.github/skills/pr-preflight/SKILL.md` for the current branch.
+Use the `pr-preflight` skill from `.claude/skills/pr-preflight/SKILL.md` for the current branch.
 
 Treat any text supplied with this prompt as the optional branch purpose or PR goal. If no purpose is available, ask for it during the skill setup. Load `CONTEXT.md`, `.github/context/codebase.context.md`, and `.github/instructions/review-analyzer.instructions.md`, then follow the skill workflow through `.review/summary.md` creation and, when posting or updating a PR, a Quick Summary-first PR description.

.github/prompts/respond-to-review-comments.prompt.md

@@ -4,7 +4,7 @@ agent: "agent"
 argument-hint: "Optional PR URL, reviewer name, comment ID, or focus area"
 ---
 
-Use the `respond-to-review-comments` skill from `.github/skills/respond-to-review-comments/SKILL.md`.
+Use the `respond-to-review-comments` skill from `.claude/skills/respond-to-review-comments/SKILL.md`.
 
 Treat any text supplied with this prompt as optional input: a PR URL, PR number, reviewer name, comment ID, pasted review comments, or a focus area.