feat: Refactor retained learning governance and documentation

.github/CHANGELOG.md

@@ -6,6 +6,14 @@ Use this format for new updates:
 - One bullet per meaningful change.
 - Include file/path scope when useful.
 
+## 2026-04-12
+- Renamed the workflow skill from `internal-cicd-workflow` to `internal-github-actions`, renamed `internal-github-composite-action` to `internal-github-action-composite`, and realigned the GitHub Actions instructions so the umbrella instruction is the family baseline while the composite instruction now carries only composite-specific delta guidance.
+- Added a retained-learning governance contract: root `AGENTS.md` now defines repository-root `LESSONS.md` as a non-canonical ledger for durable lessons learned during completed tasks, `.github/copilot-instructions.md` projects the same behavior into native Copilot flows, `INTERNAL_CONTRACT.md` source-governs the invariant, and the new `LESSONS.md` file records retained lessons with canonical-owner pointers.
+- Slimmed the retained-learning section in root `AGENTS.md` so the bridge keeps only strategic ownership and boundary language while `.github/copilot-instructions.md` remains the detailed operational projection.
+- Expanded the retained-learning contract so `LESSONS.md` may also keep durable corrections to repeated or consequential misapplication of already-codified repository rules, then recorded the bridge-vs-projection lesson for `AGENTS.md` and `.github/copilot-instructions.md`.
+- Restructured `LESSONS.md` into two tables so new or still-pending lessons stay separate from codified rules.
+- Simplified `LESSONS.md` again so it now keeps only pending lessons; once a lesson is codified into a canonical owner, it is removed from the ledger instead of being duplicated there.
+
 ## 2026-04-11
 - Tightened the Python skill split instead of collapsing it: clarified the shared baseline in `.github/instructions/internal-python.instructions.md`, sharpened `internal-project-python` around structured package and application boundaries, and expanded `internal-script-python` plus its layout reference to cover the repository-aligned toolkit pattern used under `.github/scripts/` with shared `lib/`, hash-locked `requirements.txt`, shared `run.sh`, root-level tests, and thin wrapper entrypoints.
 - Renamed the sync engine skill from `.github/skills/internal-sync-global-copilot-configs-into-repo/` to `.github/skills/internal-agent-sync-global-copilot-configs-into-repo/`, then realigned the paired agent contract and skill invocation metadata to the new canonical skill name.

.github/DEPRECATION.md

@@ -1,7 +1,7 @@
 # Deprecation Policy
 
 ## Purpose
-Define a predictable process for deprecating Copilot customization assets (`instructions`, `prompts`, `skills`, `agents`, and templates).
+Define a predictable process for deprecating Copilot customization assets (`instructions`, `skills`, `agents`, and templates).
 
 ## Lifecycle states
 - Active: recommended for current use.
@@ -16,7 +16,6 @@ Define a predictable process for deprecating Copilot customization assets (`inst
 5. Remove only after the window ends and no blocking consumers remain.
 
 ## Backward compatibility rules
-- Prompts: avoid renaming/removing slash commands without replacement mapping.
 - Instructions: avoid changing mandatory behavior without documenting impact.
 - Skills: keep old skill path available during transition.
 - Agents: keep objective and restriction semantics stable where possible.

.github/INVENTORY.md

@@ -22,10 +22,6 @@ This file is the exact path inventory for the live GitHub Copilot catalog in thi
 - `.github/instructions/internal-terraform.instructions.md`
 - `.github/instructions/internal-yaml.instructions.md`
 
-## Prompts
-
-No prompt files currently ship in the live catalog.
-
 ## Skills
 
 - `.github/skills/antigravity-api-design-principles/SKILL.md`
@@ -61,10 +57,9 @@ No prompt files currently ship in the live catalog.
 - `.github/skills/internal-azure-strategic/SKILL.md`
 - `.github/skills/internal-change-impact-analysis/SKILL.md`
 - `.github/skills/internal-changelog-automation/SKILL.md`
-- `.github/skills/internal-cicd-workflow/SKILL.md`
+- `.github/skills/internal-github-actions/SKILL.md`
 - `.github/skills/internal-cloud-policy/SKILL.md`
 - `.github/skills/internal-code-review/SKILL.md`
-- `.github/skills/internal-composite-action/SKILL.md`
 - `.github/skills/internal-copilot-audit/SKILL.md`
 - `.github/skills/internal-copilot-docs-research/SKILL.md`
 - `.github/skills/internal-copilot-instructions-creator/SKILL.md`
@@ -75,6 +70,7 @@ No prompt files currently ship in the live catalog.
 - `.github/skills/internal-gcp-operations/SKILL.md`
 - `.github/skills/internal-gcp-organization-structure/SKILL.md`
 - `.github/skills/internal-gcp-strategic/SKILL.md`
+- `.github/skills/internal-github-action-composite/SKILL.md`
 - `.github/skills/internal-github-governance/SKILL.md`
 - `.github/skills/internal-github-operations/SKILL.md`
 - `.github/skills/internal-github-strategic/SKILL.md`

.github/PULL_REQUEST_TEMPLATE.md

@@ -1,6 +1,6 @@
 <!-- markdownlint-disable-file MD041 -->
 <!-- PR title format: <type>(<scope>): <summary> -->
-<!-- Examples: feat(prompts): add reusable prompt template -->
+<!-- Examples: feat(skills): add reusable review workflow -->
 <!--           fix(workflows): tighten customization validation -->
 
 ## Description
@@ -11,7 +11,6 @@
 
 - [ ] Agent update
 - [ ] Instruction update
-- [ ] Prompt update
 - [ ] Skill update
 - [ ] Workflow/automation update
 - [ ] Verification/automation update

.github/README.md

@@ -3,14 +3,13 @@
 This directory is the source-side catalog for reusable GitHub Copilot customization assets maintained in `cloud-strategy.github`.
 
 - `.github/copilot-instructions.md` is the primary detailed policy layer.
-- Root [`AGENTS.md`](../AGENTS.md) is the thin bridge for routing, naming, discovery, and the pointer to exact path inventory.
+- Root [`AGENTS.md`](../AGENTS.md) is the strategic entrypoint, precedence anchor, and bridge for routing, naming, discovery, and the pointer to exact path inventory.
 - [`INVENTORY.md`](INVENTORY.md) is the exact path inventory for the live catalog.
 - This README is an orientation guide for maintainers of the source catalog. It should describe the live on-disk catalog only.
 
 ## Live Catalog Summary
 
 - Instructions: 17 total (`13 internal-*`, `4 awesome-copilot-*`)
-- Prompts: 0 total
 - Skills: 85 total (`45 internal-*`, `14 obra-*`, `9 awesome-copilot-*`, `8 antigravity-*`, `7 openai-*`, `2 terraform-*`)
 - Agents: 7 total (`7 internal-*`)
 - Scripts: 21 tracked files
@@ -23,7 +22,7 @@ This directory is the source-side catalog for reusable GitHub Copilot customizat
 | Path | Purpose |
 | --- | --- |
 | `copilot-instructions.md` | Primary detailed policy, validation baseline, routing model, and completion-report contract. |
-| `INVENTORY.md` | Exact path inventory for live instructions, prompts, skills, and agents. |
+| `INVENTORY.md` | Exact path inventory for live instructions, skills, and agents. |
 | `copilot-code-review-instructions.md` | Review-specific severity and defect-first guidance. |
 | `copilot-commit-message-instructions.md` | Commit message conventions. |
 | `security-baseline.md` | Cross-cutting security bar for workflows and infrastructure changes. |
@@ -32,8 +31,6 @@ This directory is the source-side catalog for reusable GitHub Copilot customizat
 | `CHANGELOG.md` | Source-side history of meaningful catalog changes. |
 | `PULL_REQUEST_TEMPLATE.md` | PR section order for this repository. |
 | `dependabot.yml` | Dependency update configuration for this source repository. |
-| `obra-superpowers-source-of-truth.json` | Pinned upstream mapping contract for imported `obra-*` skills. |
-| `.bootstrap-ignore` | Legacy compatibility artifact retained outside the primary sync workflow. |
 
 ### Instructions (`instructions/`)
 
@@ -42,13 +39,7 @@ Instructions are path-driven and auto-apply via `applyTo`.
 - Repository-owned `internal-*` instructions: `internal-bash`, `internal-docker`, `internal-github-action-composite`, `internal-github-actions`, `internal-java`, `internal-json`, `internal-lambda`, `internal-makefile`, `internal-markdown`, `internal-nodejs`, `internal-python`, `internal-terraform`, `internal-yaml`
 - Imported `awesome-copilot-*` instructions: `awesome-copilot-azure-devops-pipelines`, `awesome-copilot-go`, `awesome-copilot-kubernetes-manifests`, `awesome-copilot-shell`
 
-Use instructions as automatic file-path guidance. Do not hardcode instruction references into prompts when `applyTo` already resolves the behavior.
-
-### Prompts (`prompts/`)
-
-No prompt files currently ship in the live catalog.
-
-If prompt assets are reintroduced, they must stay aligned with real files under `instructions/`, `skills/`, and `scripts/`.
+Use instructions as automatic file-path guidance. Do not restate path-driven behavior in skills when `applyTo` already resolves it.
 
 ### Skills (`skills/`)
 
@@ -65,8 +56,8 @@ Skills are grouped into three functional lanes plus imported support families.
 Some skill directories include support material beyond `SKILL.md`. Current live examples include:
 
 - provider families with bundled references and UI metadata: `internal-aws-*`, `internal-azure-*`, `internal-gcp-*`, `internal-github-*`
-- repository-owned support bundles such as `internal-agent-*`, `internal-change-impact-analysis`, `internal-cicd-workflow`, `internal-cloud-policy`, `internal-code-review`, `internal-composite-action`, `internal-copilot-*`, `internal-ddd`, `internal-docker`, `internal-kubernetes`, `internal-kubernetes-deployment`, `internal-oop-design-patterns`, `internal-performance-optimization`, `internal-pr-editor`, `internal-project-*`, `internal-script-*`, `internal-spring-boot-development`, `internal-sync-*`, and `internal-terraform`
-- workflow packs with bundled references or helpers such as `obra-brainstorming`, `obra-requesting-code-review`, `obra-subagent-driven-development`, `obra-systematic-debugging`, `obra-test-driven-development`, `obra-using-superpowers`, `obra-writing-plans`, and `obra-writing-skills`
+- repository-owned support bundles such as `internal-agent-*`, `internal-change-impact-analysis`, `internal-github-actions`, `internal-cloud-policy`, `internal-code-review`, `internal-github-action-composite`, `internal-copilot-*`, `internal-ddd`, `internal-docker`, `internal-kubernetes`, `internal-kubernetes-deployment`, `internal-oop-design-patterns`, `internal-performance-optimization`, `internal-pr-editor`, `internal-project-*`, `internal-script-*`, `internal-spring-boot-development`, `internal-sync-*`, and `internal-terraform`
+- workflow packs with bundled references or helpers such as `obra-brainstorming`, `obra-requesting-code-review`, `obra-subagent-driven-development`, `obra-systematic-debugging`, `obra-test-driven-development`, `obra-using-superpowers`, and `obra-writing-plans`
 - imported or upstream-derived bundles such as `awesome-copilot-agentic-eval`, `awesome-copilot-azure-devops-cli`, `awesome-copilot-azure-pricing`, `awesome-copilot-azure-role-selector`, `awesome-copilot-cloud-design-patterns`, `openai-docx`, `openai-gh-address-comments`, `openai-gh-fix-ci`, `openai-pdf`, `openai-skill-creator`, `openai-slides`, `openai-spreadsheet`, `terraform-terraform-search-import`, and `terraform-terraform-test`
 
 Use [`INVENTORY.md`](INVENTORY.md) for the exact path inventory. Use root [`AGENTS.md`](../AGENTS.md) for bridge-level routing and discovery. Use this README for family-level orientation only.
@@ -105,7 +96,7 @@ The matching `.py` entrypoints and `scripts/lib/*.py` modules are part of the sa
 - Trust real on-disk paths and [`INVENTORY.md`](INVENTORY.md) over remembered historical names. Use root [`AGENTS.md`](../AGENTS.md) for bridge-level routing and discovery.
 - Keep `.github/copilot-instructions.md` as the normative policy layer and update it before root `AGENTS.md` when both must change.
 - Treat this README as maintainer-facing orientation, not as the normative contract.
-- Historical documents such as `../COPILOT_REVIEW.md` and older changelog entries may intentionally mention removed legacy assets. Do not use them as live catalog references.
+- Historical documents and older changelog entries may intentionally mention removed legacy assets. Do not use them as live catalog references.
 
 ## Maintenance Workflow
 
@@ -133,11 +124,6 @@ Completed operations must end with a concise recap.
 - Include this section only when instructions were used.
 - State which instructions were used and why they mattered.
 
-### 📝 Prompts
-
-- Include this section only when prompts were used.
-- State which prompts were used and why they were relevant.
-
 ### 🧩 Skills
 
 - Include this section only when skills were used.

.github/agents/README.md

@@ -6,14 +6,14 @@ This folder contains deliberate custom agents for repository-owned operational r
 1. Apply repository non-negotiables from `copilot-instructions.md`.
 2. Apply explicit user request and selected agent behavior (agent-first).
 3. Apply matching `instructions/*.instructions.md` (`applyTo` by path).
-4. Apply prompt and referenced skill details.
+4. Apply referenced skill details.
 
 ## Recommended routing
 - Default operational front door: `internal-router` (routes only; it does not edit files or implement changes).
 - Direct canonical owners: `internal-fast-executor`, `internal-planning-leader`, `internal-review-guard`, `internal-critical-challenger`.
 - Source-side catalog sync, rationalization, overlap cleanup, and governance drift correction in this repository: `internal-sync-control-center`.
 - Cross-repository baseline propagation: `internal-sync-global-copilot-configs-into-repo`.
-- PR-focused work should use the `internal-pr-editor` prompt and skill because this repository does not currently ship a dedicated PR editor agent.
+- PR-focused work should use the `internal-pr-editor` skill because this repository does not currently ship a dedicated PR editor agent.
 
 ## Repo-only agents (not synced to consumers)
 - `internal-sync-control-center`
@@ -25,7 +25,7 @@ This folder contains deliberate custom agents for repository-owned operational r
 - Keep the operational front door explicit, keep the four canonical owners non-overlapping, and keep reusable logic in skills instead of bloating agent bodies.
 - Keep downstream owner selection in `internal-router` only; canonical owners define boundaries and recommend a better owner instead of handing off automatically unless a scoped contract explicitly allows invoking `internal-router` as a second parallel lane.
 - Technology is resolved from file paths and prompt inputs (for example, `**/*.py` -> Python instructions).
-- Prefer prompts and skills for detailed task procedures unless a dedicated agent file is present.
+- Prefer skills for detailed task procedures unless a dedicated agent file is present.
 
 ## Selection guide
 1. Use `internal-router` when the user has not yet chosen the right owner or the request could plausibly be execution, planning, review, or challenge. Treat it as dispatch-only.
@@ -35,4 +35,4 @@ This folder contains deliberate custom agents for repository-owned operational r
 5. Use `internal-critical-challenger` for pre-mortems, objection-first pressure tests, lateral reframing, and failure-mode analysis.
 6. Use `internal-sync-control-center` when governing the live `.github/` catalog in this repository: refresh approved external assets, align naming, consolidate overlap, retire obsolete entries, and clean up downstream governance references. Unless the user explicitly asks for an audit or plan first, treat `sync` as a full apply request.
 7. Use `internal-sync-global-copilot-configs-into-repo` when aligning a consumer repository with the managed Copilot baseline from this standards repository.
-8. Use prompts and skills from `.github/prompts/` and `.github/skills/` for work that does not need a dedicated agent file.
+8. Use skills from `.github/skills/` for work that does not need a dedicated agent file.

.github/agents/internal-critical-challenger.agent.md

@@ -23,7 +23,7 @@ You are the repository-owned pressure-test and reframing lane for reasoning, ass
 ## Core Rules
 
 - Challenge one proposal, decision, or assumption set at a time.
-- Do not edit files, implement changes, or provide solutions through this route. The value is in the pressure, not in the fix.
+- Do not edit files, implement changes, or provide solutions through this route. The value is in the pressure, not in the fix, and the `edit` tool is granted only for saving retained analysis artifacts when needed.
 - The only write owned by this lane is saving the current challenge analysis as a retained artifact when the user asks for it or when a lane change would otherwise discard it.
 - The only subagent this lane may invoke is `internal-router`, and only when the user explicitly wants a second parallel operational lane without abandoning the challenge lane.
 - Do not assume the user's expertise level, intent quality, or context maturity without evidence in the conversation.

.github/agents/internal-planning-leader.agent.md

@@ -29,7 +29,7 @@ You are the planning, authoring, and decision owner for non-trivial operational
 ## Core Rules
 
 - Make assumptions, tradeoffs, and the selected direction explicit.
-- Own non-trivial repository-owned authoring for agents, skills, prompts, instructions, routing, and governance updates.
+- Own non-trivial repository-owned authoring for agents, skills, instructions, routing, and governance updates.
 - Do not default into implementation once the design is settled; recommend the right next owner instead.
 - If this agent is entered by router handoff, use the supplied routing package as input and avoid re-running front-door classification unless the boundary clearly breaks.
 

.github/agents/internal-sync-control-center.agent.md

@@ -2,6 +2,7 @@
 name: internal-sync-control-center
 description: Use this agent when governing or synchronizing the Copilot customization catalog in this repository. Keep root governance canonical in `AGENTS.md` and `.github/copilot-instructions.md`, keep sync-specific scope and managed external resources here, remove obsolete overlap instead of keeping fallbacks, and align downstream governance after catalog changes.
 tools: ["read", "edit", "search", "execute", "web", "agent"]
+agents: []
 ---
 
 # Internal Sync Control Center
@@ -43,7 +44,7 @@ Treat `.github/skills/internal-agent-sync-control-center/SKILL.md` as the mandat
 - Do not preserve fallback assets, compatibility aliases, or deprecated variants unless `AGENTS.md` explicitly requires them.
 - Do not introduce new prefixes, naming schemes, or external asset families unless the user explicitly expands scope.
 - When a managed `openai/skills` asset is declared below, install or refresh only the mapped skills into `.github/skills/` using the required `openai-` prefix. Do not keep unprefixed copies or add sibling OpenAI skills unless the user explicitly expands scope.
-- Do not leave stale references in `AGENTS.md`, prompts, skills, agents, instructions, or scripts after catalog changes. Update README-based catalogs only when README edits are explicitly in scope.
+- Do not leave stale references in `AGENTS.md`, skills, agents, instructions, or scripts after catalog changes. Update README-based catalogs only when README edits are explicitly in scope.
 - Keep agents cohesive around routing and orchestration. Move reusable procedures into skills.
 - Do not route cross-repository baseline propagation through this agent. Use `internal-sync-global-copilot-configs-into-repo` for consumer-repository alignment.
 - When the intended managed scope changes, update this file so the policy remains self-consistent over time.