@williambeto/ai-workflow 2.4.8 → 2.6.3

package/dist-assets/prompts/03-create-tech-plan.md

@@ -27,15 +27,15 @@ Do not use this prompt to implement code directly.
 Use this prompt with:
 
 ```txt
-.agents/skills/tech-lead/SKILL.md
+.ai-workflow/opencode/skills/technical-leadership/SKILL.md
 ```
 
 Supporting skills:
 
 ```txt
-.agents/skills/tester/SKILL.md
-.agents/skills/build-and-validate/SKILL.md
-.agents/skills/pr-orchestrator/SKILL.md
+.ai-workflow/opencode/skills/qa-workflow/SKILL.md
+.ai-workflow/opencode/skills/qa-workflow/SKILL.md
+.ai-workflow/opencode/skills/pr-workflow/SKILL.md
 ```
 
 Use `tester` to check whether the plan is testable.

package/dist-assets/prompts/04-breakdown-prs.md

@@ -27,15 +27,15 @@ Do not use this prompt to implement the PR directly.
 Use this prompt with:
 
 ```txt
-.agents/skills/pr-orchestrator/SKILL.md
+.ai-workflow/opencode/skills/pr-workflow/SKILL.md
 ```
 
 Supporting skills:
 
 ```txt
-.agents/skills/tech-lead/SKILL.md
-.agents/skills/tester/SKILL.md
-.agents/skills/build-and-validate/SKILL.md
+.ai-workflow/opencode/skills/technical-leadership/SKILL.md
+.ai-workflow/opencode/skills/qa-workflow/SKILL.md
+.ai-workflow/opencode/skills/qa-workflow/SKILL.md
 ```
 
 Use `tech-lead` to verify technical sequencing.

package/dist-assets/prompts/05-implement-pr.md

@@ -30,16 +30,16 @@ Common options:
 ```txt
 .agents/skills/frontend-implementer/SKILL.md
 .agents/skills/backend-implementer/SKILL.md
-.agents/skills/docs-writer/SKILL.md
-.agents/skills/build-and-validate/SKILL.md
-.agents/skills/deploy-engineer/SKILL.md
+.ai-workflow/opencode/skills/documentation/SKILL.md
+.ai-workflow/opencode/skills/qa-workflow/SKILL.md
+.ai-workflow/opencode/skills/deployment/SKILL.md
 ```
 
 Supporting skills:
 
 ```txt
-.agents/skills/pr-orchestrator/SKILL.md
-.agents/skills/tester/SKILL.md
+.ai-workflow/opencode/skills/pr-workflow/SKILL.md
+.ai-workflow/opencode/skills/qa-workflow/SKILL.md
 ```
 
 Use `pr-orchestrator` to keep the PR scoped.

package/dist-assets/prompts/06-review-and-fix.md

@@ -27,14 +27,14 @@ Do not use this prompt to implement a new PR.
 Use this prompt with:
 
 ```txt
-.agents/skills/tester/SKILL.md
+.ai-workflow/opencode/skills/qa-workflow/SKILL.md
 ```
 
 Supporting skills:
 
 ```txt
-.agents/skills/build-and-validate/SKILL.md
-.agents/skills/pr-orchestrator/SKILL.md
+.ai-workflow/opencode/skills/qa-workflow/SKILL.md
+.ai-workflow/opencode/skills/pr-workflow/SKILL.md
 ```
 
 Use `tester` to verify correctness, regressions, edge cases, and acceptance criteria.

package/dist-assets/prompts/07-apply-design.md

@@ -33,8 +33,8 @@ Use this prompt with:
 Supporting skills:
 
 ```txt
-.agents/skills/tester/SKILL.md
-.agents/skills/docs-writer/SKILL.md
+.ai-workflow/opencode/skills/qa-workflow/SKILL.md
+.ai-workflow/opencode/skills/documentation/SKILL.md
 ```
 
 Use `tester` to check regressions, accessibility risks, and behavior preservation.

package/dist-assets/prompts/08-validate.md

@@ -28,16 +28,16 @@ Do not use this prompt to implement new features or expand scope.
 Use this prompt with:
 
 ```txt
-.agents/skills/tester/SKILL.md
+.ai-workflow/opencode/skills/qa-workflow/SKILL.md
 ```
 
 Supporting skills:
 
 ```txt
-.agents/skills/build-and-validate/SKILL.md
-.agents/skills/pr-orchestrator/SKILL.md
-.agents/skills/docs-writer/SKILL.md
-.agents/skills/deploy-engineer/SKILL.md
+.ai-workflow/opencode/skills/qa-workflow/SKILL.md
+.ai-workflow/opencode/skills/pr-workflow/SKILL.md
+.ai-workflow/opencode/skills/documentation/SKILL.md
+.ai-workflow/opencode/skills/deployment/SKILL.md
 ```
 
 Use `build-and-validate` for command execution and failure analysis.

package/dist-assets/prompts/09-deploy.md

@@ -28,16 +28,16 @@ Do not use this prompt to implement features, refactor code, or bypass validatio
 Use this prompt with:
 
 ```txt
-.agents/skills/deploy-engineer/SKILL.md
+.ai-workflow/opencode/skills/deployment/SKILL.md
 ```
 
 Supporting skills:
 
 ```txt
-.agents/skills/build-and-validate/SKILL.md
-.agents/skills/tester/SKILL.md
-.agents/skills/pr-orchestrator/SKILL.md
-.agents/skills/docs-writer/SKILL.md
+.ai-workflow/opencode/skills/qa-workflow/SKILL.md
+.ai-workflow/opencode/skills/qa-workflow/SKILL.md
+.ai-workflow/opencode/skills/pr-workflow/SKILL.md
+.ai-workflow/opencode/skills/documentation/SKILL.md
 ```
 
 Use `build-and-validate` to verify build, tests, artifacts, and command results.

package/dist-assets/prompts/commands/implement.md

@@ -7,7 +7,7 @@ Implement one selected PR from a plan.
 ## Read first
 
 - `.agents/skills/frontend-implementer/SKILL.md` or `.agents/skills/backend-implementer/SKILL.md`
-- `.agents/skills/tester/SKILL.md`
+- `.ai-workflow/opencode/skills/qa-workflow/SKILL.md`
 - `prompts/05-implement-pr.md`
 
 ## Input needed

package/dist-assets/prompts/commands/tech-plan.md

@@ -6,8 +6,8 @@ Turn a specification into a technical approach.
 
 ## Read first
 
-- `.agents/skills/tech-lead/SKILL.md`
-- `.agents/skills/build-and-validate/SKILL.md`
+- `.ai-workflow/opencode/skills/technical-leadership/SKILL.md`
+- `.ai-workflow/opencode/skills/qa-workflow/SKILL.md`
 - `prompts/03-create-tech-plan.md`
 
 ## Input needed

package/dist-assets/prompts/commands/validate.md

@@ -6,8 +6,8 @@ Validate a PR before merge or moving to next step.
 
 ## Read first
 
-- `.agents/skills/tester/SKILL.md`
-- `.agents/skills/build-and-validate/SKILL.md`
+- `.ai-workflow/opencode/skills/qa-workflow/SKILL.md`
+- `.ai-workflow/opencode/skills/qa-workflow/SKILL.md`
 - `prompts/08-validate.md`
 
 ## Input needed

package/dist-assets/runbooks/deploy-checklist.md

@@ -25,16 +25,16 @@ Use this checklist when:
 Primary skill:
 
 ```txt
-.agents/skills/deploy-engineer/SKILL.md
+.ai-workflow/opencode/skills/deployment/SKILL.md
 ```
 
 Supporting skills:
 
 ```txt
-.agents/skills/build-and-validate/SKILL.md
-.agents/skills/tester/SKILL.md
-.agents/skills/pr-orchestrator/SKILL.md
-.agents/skills/docs-writer/SKILL.md
+.ai-workflow/opencode/skills/qa-workflow/SKILL.md
+.ai-workflow/opencode/skills/qa-workflow/SKILL.md
+.ai-workflow/opencode/skills/pr-workflow/SKILL.md
+.ai-workflow/opencode/skills/documentation/SKILL.md
 ```
 
 ## Deployment readiness rule

package/dist-assets/runbooks/how-to-use-skills.md

@@ -25,6 +25,16 @@ Use this runbook to choose the right capability skill for each workflow step in
 | Prepare release/deploy | `deployment` | `qa-workflow` |
 | Preserve durable decisions | `project-memory` | `optimize-tokens` |
 
+## Specialized Domain Skills (v2.4.8+)
+
+| Domain | Primary skill | Objective |
+| --- | --- | --- |
+| Security audits & privacy | `cyber-security` | Review codebase for vulnerabilities, credentials, and supply chain risks |
+| Database & migrations | `database` | Schema design, index optimization, and data migrations |
+| CI/CD & Infrastructure | `devops` | Workflow automation, containerization, and infrastructure scripts |
+| Translations & i18n | `localization` | Multi-language setup, key verification, and cultural audits |
+| System optimization | `performance` | Bundle sizes, latency profiling, and caching strategies |
+
 ## Agent-to-skill baseline
 
 | Agent owner | Primary skill set |

package/dist-assets/runbooks/validation-checklist.md

@@ -26,16 +26,16 @@ Use this checklist when validating:
 Primary skill:
 
 ```txt
-.agents/skills/tester/SKILL.md
+.ai-workflow/opencode/skills/qa-workflow/SKILL.md
 ```
 
 Supporting skills:
 
 ```txt
-.agents/skills/build-and-validate/SKILL.md
-.agents/skills/pr-orchestrator/SKILL.md
-.agents/skills/docs-writer/SKILL.md
-.agents/skills/deploy-engineer/SKILL.md
+.ai-workflow/opencode/skills/qa-workflow/SKILL.md
+.ai-workflow/opencode/skills/pr-workflow/SKILL.md
+.ai-workflow/opencode/skills/documentation/SKILL.md
+.ai-workflow/opencode/skills/deployment/SKILL.md
 ```
 
 ## Core validation rule

package/dist-assets/schemas/evidence.schema.json

@@ -0,0 +1,109 @@
+{
+  "$id": "https://github.com/williambeto/ai-workflow/schemas/evidence.schema.json",
+  "title": "Evidence Artifact",
+  "type": "object",
+  "additionalProperties": false,
+  "required": [
+    "timestamp",
+    "changedFiles",
+    "status",
+    "internalStatus",
+    "commands"
+  ],
+  "properties": {
+    "timestamp": {
+      "type": "string"
+    },
+    "taskSlug": {
+      "type": ["string", "null"]
+    },
+    "executionMode": {
+      "type": "string"
+    },
+    "workflowProfile": {
+      "type": "string"
+    },
+    "branchRecovery": {
+      "type": "string"
+    },
+    "branch": {
+      "type": "string"
+    },
+    "changedFiles": {
+      "type": "array",
+      "items": {
+        "type": "string"
+      }
+    },
+    "status": {
+      "enum": ["COMPLETED", "COMPLETED_WITH_NOTES", "BLOCKED"]
+    },
+    "internalStatus": {
+      "enum": ["PASS", "PASS_WITH_NOTES", "BLOCKED"]
+    },
+    "commands": {
+      "type": "array",
+      "items": {
+        "type": "object",
+        "additionalProperties": true,
+        "required": [
+          "name",
+          "command",
+          "kind",
+          "status"
+        ],
+        "properties": {
+          "name": {
+            "type": "string"
+          },
+          "command": {
+            "type": ["string", "object", "array"]
+          },
+          "kind": {
+            "type": "string"
+          },
+          "status": {
+            "type": "string"
+          },
+          "exitCode": {
+            "type": ["number", "null"]
+          },
+          "signal": {
+            "type": ["string", "null"]
+          },
+          "summary": {
+            "type": "string"
+          },
+          "output": {
+            "type": "string"
+          },
+          "commitHash": {
+            "type": "string"
+          }
+        }
+      }
+    },
+    "checks": {
+      "type": ["object", "null"],
+      "additionalProperties": true
+    },
+    "limitations": {
+      "type": "array",
+      "items": {
+        "type": "string"
+      }
+    },
+    "deliveryDecision": {
+      "type": ["object", "null"],
+      "additionalProperties": true
+    },
+    "artifactFidelityCheck": {
+      "type": ["object", "null"],
+      "additionalProperties": true
+    },
+    "visualEvidence": {
+      "type": ["object", "null"],
+      "additionalProperties": true
+    }
+  }
+}

package/dist-assets/templates/ANTIGRAVITY.md.template

@@ -3,10 +3,12 @@
 Use AGENTS.md and the relevant contracts.
 
 ```txt
-readonly → Inspect → Report → Recommendation
-quick → Branch recovery/check → Implement → Document if behavior or usage changed → Test/Validate → Evidence
-standard → Mini spec → Mini review → Mini plan → Scoped PR plan → Implement → Document → Test/Validate → Evidence
-full → Spec draft → Spec review → Technical plan → PR breakdown → Implementation → Documentation → Test/Validate → Evidence report
+Request → Planning → Branch Gate → Delegation → Implementation → Validation → Evidence
+
+Proportional policies:
+- low risk / optional evidence / low remediationLimit
+- medium risk / optional evidence / normal remediationLimit
+- high risk / required evidence / specPolicy required / higher remediationLimit
 ```
 
 Use professional taxonomy: Primary Agents, Skill-backed Specialist Roles, Skills, Commands.
@@ -17,4 +19,4 @@ Use professional taxonomy: Primary Agents, Skill-backed Specialist Roles, Skills
 - Explicit requirements, clean code, generated specs, and inline comments do not replace documentation.
 - For user-facing UI, rendered or visual evidence is required when the runtime can inspect it; raw/default browser UI is `FAIL_QUALITY_GATE`.
 - High/Critical security findings must be classified in evidence.
-- Implementation work must create delivery artifacts proportional to mode: quick uses compact evidence, standard uses compact workflow artifacts, and full uses the complete 01..07 set.
+- Implementation work must create delivery artifacts proportional to the active policies (evidencePolicy, riskLevel, specPolicy).

package/dist-assets/templates/CLAUDE.md.template

@@ -3,10 +3,12 @@
 Use AGENTS.md and the relevant contracts.
 
 ```txt
-readonly → Inspect → Report → Recommendation
-quick → Branch recovery/check → Implement → Document if behavior or usage changed → Test/Validate → Evidence
-standard → Mini spec → Mini review → Mini plan → Scoped PR plan → Implement → Document → Test/Validate → Evidence
-full → Spec draft → Spec review → Technical plan → PR breakdown → Implementation → Documentation → Test/Validate → Evidence report
+Request → Planning → Branch Gate → Delegation → Implementation → Validation → Evidence
+
+Proportional policies:
+- low risk / optional evidence / low remediationLimit
+- medium risk / optional evidence / normal remediationLimit
+- high risk / required evidence / specPolicy required / higher remediationLimit
 ```
 
 Provide evidence for completed work.
@@ -17,4 +19,4 @@ Provide evidence for completed work.
 - Explicit requirements, clean code, generated specs, and inline comments do not replace documentation.
 - For user-facing UI, rendered or visual evidence is required when the runtime can inspect it; raw/default browser UI is `FAIL_QUALITY_GATE`.
 - High/Critical security findings must be classified in evidence.
-- Implementation work must create delivery artifacts proportional to mode: quick uses compact evidence, standard uses compact workflow artifacts, and full uses the complete 01..07 set.
+- Implementation work must create delivery artifacts proportional to the active policies (evidencePolicy, riskLevel, specPolicy).

package/dist-assets/templates/CODEX.md.template

@@ -3,10 +3,12 @@
 Use AGENTS.md and the relevant contracts.
 
 ```txt
-readonly → Inspect → Report → Recommendation
-quick → Branch recovery/check → Implement → Document if behavior or usage changed → Test/Validate → Evidence
-standard → Mini spec → Mini review → Mini plan → Scoped PR plan → Implement → Document → Test/Validate → Evidence
-full → Spec draft → Spec review → Technical plan → PR breakdown → Implementation → Documentation → Test/Validate → Evidence report
+Request → Planning → Branch Gate → Delegation → Implementation → Validation → Evidence
+
+Proportional policies:
+- low risk / optional evidence / low remediationLimit
+- medium risk / optional evidence / normal remediationLimit
+- high risk / required evidence / specPolicy required / higher remediationLimit
 ```
 
 Never publish, tag, release, deploy, merge, push, force-push, or change package version without explicit approval.
@@ -17,4 +19,4 @@ Never publish, tag, release, deploy, merge, push, force-push, or change package
 - Explicit requirements, clean code, generated specs, and inline comments do not replace documentation.
 - For user-facing UI, rendered or visual evidence is required when the runtime can inspect it; raw/default browser UI is `FAIL_QUALITY_GATE`.
 - High/Critical security findings must be classified in evidence.
-- Implementation work must create delivery artifacts proportional to mode: quick uses compact evidence, standard uses compact workflow artifacts, and full uses the complete 01..07 set.
+- Implementation work must create delivery artifacts proportional to the active policies (evidencePolicy, riskLevel, specPolicy).