@zeyue0329/xiaoma-cli 1.0.49 → 1.0.66

package/src/xmc/workflows/4-implementation/xiaoma-code-review/steps/step-03-triage.md

@@ -0,0 +1,50 @@
+---
+---
+
+# Step 3: Triage
+
+## RULES
+
+- YOU MUST ALWAYS SPEAK OUTPUT in your Agent communication style with the config `{communication_language}`
+- Be precise. When uncertain between categories, prefer the more conservative classification.
+
+## INSTRUCTIONS
+
+1. **Normalize** findings into a common format. Expected input formats:
+   - Adversarial (Blind Hunter): markdown list of descriptions
+   - Edge Case Hunter: JSON array with `location`, `trigger_condition`, `guard_snippet`, `potential_consequence` fields
+   - Acceptance Auditor: markdown list with title, AC/constraint reference, and evidence
+
+   If a layer's output does not match its expected format, attempt best-effort parsing. Note any parsing issues for the user.
+
+   Convert all to a unified list where each finding has:
+   - `id` -- sequential integer
+   - `source` -- `blind`, `edge`, `auditor`, or merged sources (e.g., `blind+edge`)
+   - `title` -- one-line summary
+   - `detail` -- full description
+   - `location` -- file and line reference (if available)
+
+2. **Deduplicate.** If two or more findings describe the same issue, merge them into one:
+   - Use the most specific finding as the base (prefer edge-case JSON with location over adversarial prose).
+   - Append any unique detail, reasoning, or location references from the other finding(s) into the surviving `detail` field.
+   - Set `source` to the merged sources (e.g., `blind+edge`).
+
+3. **Classify** each finding into exactly one bucket:
+   - **intent_gap** -- The spec/intent is incomplete; cannot resolve from existing information. Only possible if `{review_mode}` = `"full"`.
+   - **bad_spec** -- The spec should have prevented this; spec is wrong or ambiguous. Only possible if `{review_mode}` = `"full"`.
+   - **patch** -- Code issue that is trivially fixable without human input. Just needs a code change.
+   - **defer** -- Pre-existing issue not caused by the current change. Real but not actionable now.
+   - **reject** -- Noise, false positive, or handled elsewhere.
+
+   If `{review_mode}` = `"no-spec"` and a finding would otherwise be `intent_gap` or `bad_spec`, reclassify it as `patch` (if code-fixable) or `defer` (if not).
+
+4. **Drop** all `reject` findings. Record the reject count for the summary.
+
+5. If `{failed_layers}` is non-empty, report which layers failed before announcing results. If zero findings remain after dropping rejects AND `{failed_layers}` is non-empty, warn the user that the review may be incomplete rather than announcing a clean review.
+
+6. If zero findings remain after dropping rejects and no layers failed, note clean review.
+
+
+## NEXT
+
+Read fully and follow `./step-04-present.md`

package/src/xmc/workflows/4-implementation/xiaoma-code-review/steps/step-04-present.md

@@ -0,0 +1,38 @@
+---
+---
+
+# Step 4: Present
+
+## RULES
+
+- YOU MUST ALWAYS SPEAK OUTPUT in your Agent communication style with the config `{communication_language}`
+- Do NOT auto-fix anything. Present findings and let the user decide next steps.
+
+## INSTRUCTIONS
+
+1. Group remaining findings by category.
+
+2. Present to the user in this order (include a section only if findings exist in that category):
+
+   - **Intent Gaps**: "These findings suggest the captured intent is incomplete. Consider clarifying intent before proceeding."
+     - List each with title + detail.
+
+   - **Bad Spec**: "These findings suggest the spec should be amended. Consider regenerating or amending the spec with this context:"
+     - List each with title + detail + suggested spec amendment.
+
+   - **Patch**: "These are fixable code issues:"
+     - List each with title + detail + location (if available).
+
+   - **Defer**: "Pre-existing issues surfaced by this review (not caused by current changes):"
+     - List each with title + detail.
+
+3. Summary line: **X** intent_gap, **Y** bad_spec, **Z** patch, **W** defer findings. **R** findings rejected as noise.
+
+4. If clean review (zero findings across all layers after triage): state that N findings were raised but all were classified as noise, or that no findings were raised at all (as applicable).
+
+5. Offer the user next steps (recommendations, not automated actions):
+   - If `patch` findings exist: "These can be addressed in a follow-up implementation pass or manually."
+   - If `intent_gap` or `bad_spec` findings exist: "Consider running the planning workflow to clarify intent or amend the spec before continuing."
+   - If only `defer` findings remain: "No action needed for this change. Deferred items are noted for future attention."
+
+Workflow complete.

package/src/xmc/workflows/4-implementation/xiaoma-code-review/workflow.md

@@ -0,0 +1,54 @@
+---
+main_config: '{project-root}/_xiaoma/xmc/config.yaml'
+---
+
+# Code Review Workflow
+
+**Goal:** Review code changes adversarially using parallel review layers and structured triage.
+
+**Your Role:** You are an elite code reviewer. You gather context, launch parallel adversarial reviews, triage findings with precision, and present actionable results. No noise, no filler.
+
+
+## WORKFLOW ARCHITECTURE
+
+This uses **step-file architecture** for disciplined execution:
+
+- **Micro-file Design**: Each step is self-contained and followed exactly
+- **Just-In-Time Loading**: Only load the current step file
+- **Sequential Enforcement**: Complete steps in order, no skipping
+- **State Tracking**: Persist progress via in-memory variables
+- **Append-Only Building**: Build artifacts incrementally
+
+### Step Processing Rules
+
+1. **READ COMPLETELY**: Read the entire step file before acting
+2. **FOLLOW SEQUENCE**: Execute sections in order
+3. **WAIT FOR INPUT**: Halt at checkpoints and wait for human
+4. **LOAD NEXT**: When directed, read fully and follow the next step file
+
+### Critical Rules (NO EXCEPTIONS)
+
+- **NEVER** load multiple step files simultaneously
+- **ALWAYS** read entire step file before execution
+- **NEVER** skip steps or optimize the sequence
+- **ALWAYS** follow the exact instructions in the step file
+- **ALWAYS** halt at checkpoints and wait for human input
+
+
+## INITIALIZATION SEQUENCE
+
+### 1. Configuration Loading
+
+Load and read full config from `{main_config}` and resolve:
+
+- `project_name`, `planning_artifacts`, `implementation_artifacts`, `user_name`
+- `communication_language`, `document_output_language`, `user_skill_level`
+- `date` as system-generated current datetime
+- `project_context` = `**/project-context.md` (load if exists)
+- CLAUDE.md / memory files (load if exist)
+
+YOU MUST ALWAYS SPEAK OUTPUT in your Agent communication style with the config `{communication_language}`.
+
+### 2. First Step Execution
+
+Read fully and follow: `./steps/step-01-gather-context.md` to begin the workflow.

package/src/xmc/workflows/4-implementation/xiaoma-code-review/xiaoma-skill-manifest.yaml

@@ -0,0 +1 @@
+type: skill

package/src/xmc/workflows/4-implementation/xiaoma-correct-course/SKILL.md

@@ -0,0 +1,6 @@
+---
+name: xiaoma-correct-course
+description: 'Manage significant changes during sprint execution. Use when the user says "correct course" or "propose sprint change"'
+---
+
+Follow the instructions in ./workflow.md.

package/src/xmc/workflows/4-implementation/xiaoma-correct-course/checklist.md

@@ -0,0 +1,288 @@
+# Change Navigation Checklist
+
+<critical>This checklist is executed as part of: ./workflow.md</critical>
+<critical>Work through each section systematically with the user, recording findings and impacts</critical>
+
+<checklist>
+
+<section n="1" title="Understand the Trigger and Context">
+
+<check-item id="1.1">
+<prompt>Identify the triggering story that revealed this issue</prompt>
+<action>Document story ID and brief description</action>
+<status>[ ] Done / [ ] N/A / [ ] Action-needed</status>
+</check-item>
+
+<check-item id="1.2">
+<prompt>Define the core problem precisely</prompt>
+<action>Categorize issue type:</action>
+  - Technical limitation discovered during implementation
+  - New requirement emerged from stakeholders
+  - Misunderstanding of original requirements
+  - Strategic pivot or market change
+  - Failed approach requiring different solution
+<action>Write clear problem statement</action>
+<status>[ ] Done / [ ] N/A / [ ] Action-needed</status>
+</check-item>
+
+<check-item id="1.3">
+<prompt>Assess initial impact and gather supporting evidence</prompt>
+<action>Collect concrete examples, error messages, stakeholder feedback, or technical constraints</action>
+<action>Document evidence for later reference</action>
+<status>[ ] Done / [ ] N/A / [ ] Action-needed</status>
+</check-item>
+
+<halt-condition>
+<action if="trigger is unclear">HALT: "Cannot proceed without understanding what caused the need for change"</action>
+<action if="no evidence provided">HALT: "Need concrete evidence or examples of the issue before analyzing impact"</action>
+</halt-condition>
+
+</section>
+
+<section n="2" title="Epic Impact Assessment">
+
+<check-item id="2.1">
+<prompt>Evaluate current epic containing the trigger story</prompt>
+<action>Can this epic still be completed as originally planned?</action>
+<action>If no, what modifications are needed?</action>
+<status>[ ] Done / [ ] N/A / [ ] Action-needed</status>
+</check-item>
+
+<check-item id="2.2">
+<prompt>Determine required epic-level changes</prompt>
+<action>Check each scenario:</action>
+  - Modify existing epic scope or acceptance criteria
+  - Add new epic to address the issue
+  - Remove or defer epic that's no longer viable
+  - Completely redefine epic based on new understanding
+<action>Document specific epic changes needed</action>
+<status>[ ] Done / [ ] N/A / [ ] Action-needed</status>
+</check-item>
+
+<check-item id="2.3">
+<prompt>Review all remaining planned epics for required changes</prompt>
+<action>Check each future epic for impact</action>
+<action>Identify dependencies that may be affected</action>
+<status>[ ] Done / [ ] N/A / [ ] Action-needed</status>
+</check-item>
+
+<check-item id="2.4">
+<prompt>Check if issue invalidates future epics or necessitates new ones</prompt>
+<action>Does this change make any planned epics obsolete?</action>
+<action>Are new epics needed to address gaps created by this change?</action>
+<status>[ ] Done / [ ] N/A / [ ] Action-needed</status>
+</check-item>
+
+<check-item id="2.5">
+<prompt>Consider if epic order or priority should change</prompt>
+<action>Should epics be resequenced based on this issue?</action>
+<action>Do priorities need adjustment?</action>
+<status>[ ] Done / [ ] N/A / [ ] Action-needed</status>
+</check-item>
+
+</section>
+
+<section n="3" title="Artifact Conflict and Impact Analysis">
+
+<check-item id="3.1">
+<prompt>Check PRD for conflicts</prompt>
+<action>Does issue conflict with core PRD goals or objectives?</action>
+<action>Do requirements need modification, addition, or removal?</action>
+<action>Is the defined MVP still achievable or does scope need adjustment?</action>
+<status>[ ] Done / [ ] N/A / [ ] Action-needed</status>
+</check-item>
+
+<check-item id="3.2">
+<prompt>Review Architecture document for conflicts</prompt>
+<action>Check each area for impact:</action>
+  - System components and their interactions
+  - Architectural patterns and design decisions
+  - Technology stack choices
+  - Data models and schemas
+  - API designs and contracts
+  - Integration points
+<action>Document specific architecture sections requiring updates</action>
+<status>[ ] Done / [ ] N/A / [ ] Action-needed</status>
+</check-item>
+
+<check-item id="3.3">
+<prompt>Examine UI/UX specifications for conflicts</prompt>
+<action>Check for impact on:</action>
+  - User interface components
+  - User flows and journeys
+  - Wireframes or mockups
+  - Interaction patterns
+  - Accessibility considerations
+<action>Note specific UI/UX sections needing revision</action>
+<status>[ ] Done / [ ] N/A / [ ] Action-needed</status>
+</check-item>
+
+<check-item id="3.4">
+<prompt>Consider impact on other artifacts</prompt>
+<action>Review additional artifacts for impact:</action>
+  - Deployment scripts
+  - Infrastructure as Code (IaC)
+  - Monitoring and observability setup
+  - Testing strategies
+  - Documentation
+  - CI/CD pipelines
+<action>Document any secondary artifacts requiring updates</action>
+<status>[ ] Done / [ ] N/A / [ ] Action-needed</status>
+</check-item>
+
+</section>
+
+<section n="4" title="Path Forward Evaluation">
+
+<check-item id="4.1">
+<prompt>Evaluate Option 1: Direct Adjustment</prompt>
+<action>Can the issue be addressed by modifying existing stories?</action>
+<action>Can new stories be added within the current epic structure?</action>
+<action>Would this approach maintain project timeline and scope?</action>
+<action>Effort estimate: [High/Medium/Low]</action>
+<action>Risk level: [High/Medium/Low]</action>
+<status>[ ] Viable / [ ] Not viable</status>
+</check-item>
+
+<check-item id="4.2">
+<prompt>Evaluate Option 2: Potential Rollback</prompt>
+<action>Would reverting recently completed stories simplify addressing this issue?</action>
+<action>Which stories would need to be rolled back?</action>
+<action>Is the rollback effort justified by the simplification gained?</action>
+<action>Effort estimate: [High/Medium/Low]</action>
+<action>Risk level: [High/Medium/Low]</action>
+<status>[ ] Viable / [ ] Not viable</status>
+</check-item>
+
+<check-item id="4.3">
+<prompt>Evaluate Option 3: PRD MVP Review</prompt>
+<action>Is the original PRD MVP still achievable with this issue?</action>
+<action>Does MVP scope need to be reduced or redefined?</action>
+<action>Do core goals need modification based on new constraints?</action>
+<action>What would be deferred to post-MVP if scope is reduced?</action>
+<action>Effort estimate: [High/Medium/Low]</action>
+<action>Risk level: [High/Medium/Low]</action>
+<status>[ ] Viable / [ ] Not viable</status>
+</check-item>
+
+<check-item id="4.4">
+<prompt>Select recommended path forward</prompt>
+<action>Based on analysis of all options, choose the best path</action>
+<action>Provide clear rationale considering:</action>
+  - Implementation effort and timeline impact
+  - Technical risk and complexity
+  - Impact on team morale and momentum
+  - Long-term sustainability and maintainability
+  - Stakeholder expectations and business value
+<action>Selected approach: [Option 1 / Option 2 / Option 3 / Hybrid]</action>
+<action>Justification: [Document reasoning]</action>
+<status>[ ] Done / [ ] N/A / [ ] Action-needed</status>
+</check-item>
+
+</section>
+
+<section n="5" title="Sprint Change Proposal Components">
+
+<check-item id="5.1">
+<prompt>Create identified issue summary</prompt>
+<action>Write clear, concise problem statement</action>
+<action>Include context about discovery and impact</action>
+<status>[ ] Done / [ ] N/A / [ ] Action-needed</status>
+</check-item>
+
+<check-item id="5.2">
+<prompt>Document epic impact and artifact adjustment needs</prompt>
+<action>Summarize findings from Epic Impact Assessment (Section 2)</action>
+<action>Summarize findings from Artifact Conflict Analysis (Section 3)</action>
+<action>Be specific about what changes are needed and why</action>
+<status>[ ] Done / [ ] N/A / [ ] Action-needed</status>
+</check-item>
+
+<check-item id="5.3">
+<prompt>Present recommended path forward with rationale</prompt>
+<action>Include selected approach from Section 4</action>
+<action>Provide complete justification for recommendation</action>
+<action>Address trade-offs and alternatives considered</action>
+<status>[ ] Done / [ ] N/A / [ ] Action-needed</status>
+</check-item>
+
+<check-item id="5.4">
+<prompt>Define PRD MVP impact and high-level action plan</prompt>
+<action>State clearly if MVP is affected</action>
+<action>Outline major action items needed for implementation</action>
+<action>Identify dependencies and sequencing</action>
+<status>[ ] Done / [ ] N/A / [ ] Action-needed</status>
+</check-item>
+
+<check-item id="5.5">
+<prompt>Establish agent handoff plan</prompt>
+<action>Identify which roles/agents will execute the changes:</action>
+  - Development team (for implementation)
+  - Product Owner / Scrum Master (for backlog changes)
+  - Product Manager / Architect (for strategic changes)
+<action>Define responsibilities for each role</action>
+<status>[ ] Done / [ ] N/A / [ ] Action-needed</status>
+</check-item>
+
+</section>
+
+<section n="6" title="Final Review and Handoff">
+
+<check-item id="6.1">
+<prompt>Review checklist completion</prompt>
+<action>Verify all applicable sections have been addressed</action>
+<action>Confirm all [Action-needed] items have been documented</action>
+<action>Ensure analysis is comprehensive and actionable</action>
+<status>[ ] Done / [ ] N/A / [ ] Action-needed</status>
+</check-item>
+
+<check-item id="6.2">
+<prompt>Verify Sprint Change Proposal accuracy</prompt>
+<action>Review complete proposal for consistency and clarity</action>
+<action>Ensure all recommendations are well-supported by analysis</action>
+<action>Check that proposal is actionable and specific</action>
+<status>[ ] Done / [ ] N/A / [ ] Action-needed</status>
+</check-item>
+
+<check-item id="6.3">
+<prompt>Obtain explicit user approval</prompt>
+<action>Present complete proposal to user</action>
+<action>Get clear yes/no approval for proceeding</action>
+<action>Document approval and any conditions</action>
+<status>[ ] Done / [ ] N/A / [ ] Action-needed</status>
+</check-item>
+
+<check-item id="6.4">
+<prompt>Update sprint-status.yaml to reflect approved epic changes</prompt>
+<action>If epics were added: Add new epic entries with status 'backlog'</action>
+<action>If epics were removed: Remove corresponding entries</action>
+<action>If epics were renumbered: Update epic IDs and story references</action>
+<action>If stories were added/removed: Update story entries within affected epics</action>
+<status>[ ] Done / [ ] N/A / [ ] Action-needed</status>
+</check-item>
+
+<check-item id="6.5">
+<prompt>Confirm next steps and handoff plan</prompt>
+<action>Review handoff responsibilities with user</action>
+<action>Ensure all stakeholders understand their roles</action>
+<action>Confirm timeline and success criteria</action>
+<status>[ ] Done / [ ] N/A / [ ] Action-needed</status>
+</check-item>
+
+<halt-condition>
+<action if="any critical section cannot be completed">HALT: "Cannot proceed to proposal without complete impact analysis"</action>
+<action if="user approval not obtained">HALT: "Must have explicit approval before implementing changes"</action>
+<action if="handoff responsibilities unclear">HALT: "Must clearly define who will execute the proposed changes"</action>
+</halt-condition>
+
+</section>
+
+</checklist>
+
+<execution-notes>
+<note>This checklist is for SIGNIFICANT changes affecting project direction</note>
+<note>Work interactively with user - they make final decisions</note>
+<note>Be factual, not blame-oriented when analyzing issues</note>
+<note>Handle changes professionally as opportunities to improve the project</note>
+<note>Maintain conversation context throughout - this is collaborative work</note>
+</execution-notes>