ac-framework 2.3.0 → 2.4.0

package/framework/make_your_own/.opencode/command/opsx-verify.md

@@ -0,0 +1,161 @@
+---
+description: Verify implementation matches change artifacts before archiving
+---
+
+Verify that an implementation matches the change artifacts (specs, tasks, design).
+
+**Input**: Optionally specify a change name after `/opsx-verify` (e.g., `/opsx-verify add-auth`). If omitted, check if it can be inferred from conversation context. If vague or ambiguous you MUST prompt for available changes.
+
+**Steps**
+
+1. **If no change name provided, prompt for selection**
+
+   Run `acfm spec list --json` to get available changes. Use the **AskUserQuestion tool** to let the user select.
+
+   Show changes that have implementation tasks (tasks artifact exists).
+   Include the schema used for each change if available.
+   Mark changes with incomplete tasks as "(In Progress)".
+
+   **IMPORTANT**: Do NOT guess or auto-select a change. Always let the user choose.
+
+2. **Check status to understand the schema**
+   ```bash
+   acfm spec status --change "<name>" --json
+   ```
+   Parse the JSON to understand:
+   - `schemaName`: The workflow being used (e.g., "spec-driven")
+   - Which artifacts exist for this change
+
+3. **Get the change directory and load artifacts**
+
+   ```bash
+   acfm spec instructions apply --change "<name>" --json
+   ```
+
+   This returns the change directory and context files. Read all available artifacts from `contextFiles`.
+
+4. **Initialize verification report structure**
+
+   Create a report structure with three dimensions:
+   - **Completeness**: Track tasks and spec coverage
+   - **Correctness**: Track requirement implementation and scenario coverage
+   - **Coherence**: Track design adherence and pattern consistency
+
+   Each dimension can have CRITICAL, WARNING, or SUGGESTION issues.
+
+5. **Verify Completeness**
+
+   **Task Completion**:
+   - If tasks.md exists in contextFiles, read it
+   - Parse checkboxes: `- [ ]` (incomplete) vs `- [x]` (complete)
+   - Count complete vs total tasks
+   - If incomplete tasks exist:
+     - Add CRITICAL issue for each incomplete task
+     - Recommendation: "Complete task: <description>" or "Mark as done if already implemented"
+
+   **Spec Coverage**:
+   - If delta specs exist in `openspec/changes/<name>/specs/`:
+     - Extract all requirements (marked with "### Requirement:")
+     - For each requirement:
+       - Search codebase for keywords related to the requirement
+       - Assess if implementation likely exists
+     - If requirements appear unimplemented:
+       - Add CRITICAL issue: "Requirement not found: <requirement name>"
+       - Recommendation: "Implement requirement X: <description>"
+
+6. **Verify Correctness**
+
+   **Requirement Implementation Mapping**:
+   - For each requirement from delta specs:
+     - Search codebase for implementation evidence
+     - If found, note file paths and line ranges
+     - Assess if implementation matches requirement intent
+     - If divergence detected:
+       - Add WARNING: "Implementation may diverge from spec: <details>"
+       - Recommendation: "Review <file>:<lines> against requirement X"
+
+   **Scenario Coverage**:
+   - For each scenario in delta specs (marked with "#### Scenario:"):
+     - Check if conditions are handled in code
+     - Check if tests exist covering the scenario
+     - If scenario appears uncovered:
+       - Add WARNING: "Scenario not covered: <scenario name>"
+       - Recommendation: "Add test or implementation for scenario: <description>"
+
+7. **Verify Coherence**
+
+   **Design Adherence**:
+   - If design.md exists in contextFiles:
+     - Extract key decisions (look for sections like "Decision:", "Approach:", "Architecture:")
+     - Verify implementation follows those decisions
+     - If contradiction detected:
+       - Add WARNING: "Design decision not followed: <decision>"
+       - Recommendation: "Update implementation or revise design.md to match reality"
+   - If no design.md: Skip design adherence check, note "No design.md to verify against"
+
+   **Code Pattern Consistency**:
+   - Review new code for consistency with project patterns
+   - Check file naming, directory structure, coding style
+   - If significant deviations found:
+     - Add SUGGESTION: "Code pattern deviation: <details>"
+     - Recommendation: "Consider following project pattern: <example>"
+
+8. **Generate Verification Report**
+
+   **Summary Scorecard**:
+   ```
+   ## Verification Report: <change-name>
+
+   ### Summary
+   | Dimension    | Status           |
+   |--------------|------------------|
+   | Completeness | X/Y tasks, N reqs|
+   | Correctness  | M/N reqs covered |
+   | Coherence    | Followed/Issues  |
+   ```
+
+   **Issues by Priority**:
+
+   1. **CRITICAL** (Must fix before archive):
+      - Incomplete tasks
+      - Missing requirement implementations
+      - Each with specific, actionable recommendation
+
+   2. **WARNING** (Should fix):
+      - Spec/design divergences
+      - Missing scenario coverage
+      - Each with specific recommendation
+
+   3. **SUGGESTION** (Nice to fix):
+      - Pattern inconsistencies
+      - Minor improvements
+      - Each with specific recommendation
+
+   **Final Assessment**:
+   - If CRITICAL issues: "X critical issue(s) found. Fix before archiving."
+   - If only warnings: "No critical issues. Y warning(s) to consider. Ready for archive (with noted improvements)."
+   - If all clear: "All checks passed. Ready for archive."
+
+**Verification Heuristics**
+
+- **Completeness**: Focus on objective checklist items (checkboxes, requirements list)
+- **Correctness**: Use keyword search, file path analysis, reasonable inference - don't require perfect certainty
+- **Coherence**: Look for glaring inconsistencies, don't nitpick style
+- **False Positives**: When uncertain, prefer SUGGESTION over WARNING, WARNING over CRITICAL
+- **Actionability**: Every issue must have a specific recommendation with file/line references where applicable
+
+**Graceful Degradation**
+
+- If only tasks.md exists: verify task completion only, skip spec/design checks
+- If tasks + specs exist: verify completeness and correctness, skip design
+- If full artifacts: verify all three dimensions
+- Always note which checks were skipped and why
+
+**Output Format**
+
+Use clear markdown with:
+- Table for summary scorecard
+- Grouped lists for issues (CRITICAL/WARNING/SUGGESTION)
+- Code references in format: `file.ts:123`
+- Specific, actionable recommendations
+- No vague suggestions like "consider reviewing"

package/framework/make_your_own/.opencode/skills/acfm-memory/SKILL.md

@@ -0,0 +1,312 @@
+---
+name: acfm-memory
+description: Autonomous memory system for persistent learning across sessions. Automatically saves architectural decisions, bugfixes, patterns, and insights. Use to recall context from previous work and build institutional knowledge.
+---
+
+# AC Framework Memory System
+
+## Overview
+
+The AC Framework Memory System provides **autonomous persistent memory** for AI agents. It automatically detects and saves valuable knowledge during development, then recalls relevant context when needed.
+
+**Key Capabilities:**
+- **Automatic saving**: Detects and stores important decisions, patterns, and solutions
+- **Full-text search**: Find relevant memories instantly
+- **Context recall**: Get relevant knowledge before starting tasks
+- **Pattern analysis**: Detect recurring themes and errors
+- **Timeline view**: See chronological context around any memory
+
+## When to Use This Skill
+
+### Before Starting Work
+- **Recall relevant context**: `acfm memory recall "<task description>"`
+- **Check for similar changes**: `acfm memory search "<topic>"`
+- **Review patterns**: `acfm memory patterns`
+
+### During Work (Automatic)
+The agent automatically saves memories when:
+- Completing architectural proposals
+- Fixing bugs (especially after multiple attempts)
+- Refactoring code successfully
+- Optimizing performance
+- Discovering important patterns
+
+### After Work
+- **Review learnings**: `acfm memory stats`
+- **Export for sharing**: `acfm memory export team-memory.json`
+- **Find gaps**: `acfm memory patterns --min-frequency 1`
+
+## Memory Types
+
+| Type | Description | Auto-Trigger |
+|------|-------------|--------------|
+| `architectural_decision` | Major design decisions | After proposal/design |
+| `bugfix_pattern` | Solutions to bugs | After fixing error |
+| `refactor_technique` | Successful refactoring patterns | After refactor |
+| `performance_insight` | Optimization learnings | After performance work |
+| `security_fix` | Security vulnerability fixes | After security patch |
+| `api_pattern` | API design patterns | After API work |
+| `convention` | Project conventions | After establishing pattern |
+| `workaround` | Temporary solutions | After implementing hack |
+| `context_boundary` | System limitations | After defining boundaries |
+
+## Commands
+
+### Core Commands
+
+#### Initialize Memory System
+```bash
+acfm memory init
+```
+Creates the SQLite database at `~/.acfm/memory.db`.
+
+#### Save Memory (Manual)
+```bash
+acfm memory save "Descripción de la decisión o patrón" \
+  --type architectural_decision \
+  --importance high \
+  --tags "react,performance"
+```
+
+#### Recall Context
+```bash
+# For specific task
+acfm memory recall "implementing authentication"
+
+# For current project (general context)
+acfm memory recall
+```
+
+#### Search Memories
+```bash
+# Basic search
+acfm memory search "JWT"
+
+# Filtered search
+acfm memory search "database" --type architectural_decision --importance high
+```
+
+### Advanced Commands
+
+#### Timeline View
+```bash
+acfm memory timeline <memory-id>
+```
+Shows what happened before and after a specific memory.
+
+#### Connections
+```bash
+acfm memory connections <memory-id> --depth 2
+```
+Shows related memories as a graph.
+
+#### Pattern Detection
+```bash
+acfm memory patterns
+acfm memory patterns --type bugfix_pattern
+```
+Finds recurring topics and frequent error types.
+
+#### Predictive Recall
+```bash
+acfm memory anticipate "caching strategy"
+```
+Predicts which memories will be relevant for a future task.
+
+#### Statistics
+```bash
+acfm memory stats
+acfm memory stats --project /path/to/project
+```
+
+#### Export/Import
+```bash
+# Export for sharing
+acfm memory export team-memory.json
+
+# Import shared knowledge
+acfm memory import team-memory.json
+```
+
+## Auto-Save Behavior
+
+### What Triggers Auto-Save
+
+The agent evaluates content using a confidence score (0-1):
+
+**High confidence triggers (auto-save):**
+- Contains decision keywords: "decidimos", "optamos", "mejor usar"
+- Describes solution to problem
+- Contains architectural guidance
+- Has error + solution pair
+- Takes >10 minutes to resolve
+
+**Low confidence (skip):**
+- Very short content (<50 chars)
+- Contains specific IDs/UUIDs
+- Temporary TODOs
+- Obvious/common knowledge
+
+### Confidence Scoring
+
+```
+Base: 0.5
++ Decision keywords: +0.25
++ Contains solution: +0.20
++ Bug fix: +0.15
++ Architecture: +0.20
++ Optimization: +0.15
++ Security: +0.25
+- Too short: -0.20
+- Specific IDs: -0.15
+- TODO/FIXME: -0.20
+
+Threshold for auto-save: 0.60
+```
+
+### Notification
+
+When auto-saving, the agent will display:
+```
+💾 Memory saved: [Brief description of what was learned]
+   Type: bugfix_pattern | Confidence: 85%
+```
+
+## Privacy
+
+Content between `<private>` tags is automatically redacted:
+
+```markdown
+Decidimos usar AWS para hosting. <private>Usaremos la cuenta
+producción-env-123</private> para el deployment.
+```
+
+Saved as:
+```
+Decidimos usar AWS para hosting. [REDACTED PRIVATE CONTENT]
+```
+
+## Integration with Spec Workflow
+
+### Before Creating Artifacts
+
+When you request `acfm spec instructions`, the system automatically:
+
+1. Queries memories related to the change topic
+2. Includes relevant memories in the response
+3. Displays them as context for the agent
+
+Example output:
+```json
+{
+  "instruction": "...",
+  "relevantMemories": [
+    {
+      "id": 42,
+      "type": "architectural_decision",
+      "content": "Previous auth system used JWT...",
+      "importance": "high"
+    }
+  ]
+}
+```
+
+### During Apply Phase
+
+When implementing tasks, the system recalls:
+- Patterns from similar previous tasks
+- Bugfixes related to current work
+- Performance insights for optimization tasks
+
+## Best Practices
+
+### For Agents
+
+1. **Always recall before starting**: Check `acfm memory recall` for relevant context
+2. **Let auto-save work**: Don't manually save everything - trust the confidence scoring
+3. **Use topic keys**: When manually saving, use consistent topic keys for deduplication
+4. **Mark importance**: Critical decisions should be marked `critical` or `high`
+5. **Add tags**: Tags improve searchability
+
+### For Users
+
+1. **Initialize once**: Run `acfm memory init` per machine
+2. **Review periodically**: Check `acfm memory stats` to see what's been learned
+3. **Export regularly**: Share knowledge with team via `acfm memory export`
+4. **Prune old data**: Use `acfm memory prune` to archive obsolete memories
+5. **Use private tags**: Mark sensitive content with `<private>` tags
+
+## Examples
+
+### Example 1: Bug Fix
+
+**Agent fixes an authentication bug:**
+```
+💾 Memory saved: JWT refresh token fails when expired during request
+   Type: bugfix_pattern | Confidence: 87%
+   Solution: Implement token refresh interceptor
+```
+
+**Later, similar task:**
+```bash
+$ acfm memory recall "authentication token"
+→ [Memory #42] JWT refresh token fails when expired...
+```
+
+### Example 2: Architectural Decision
+
+**Agent completes proposal:**
+```
+💾 Memory saved: Microservices architecture chosen for scalability
+   Type: architectural_decision | Confidence: 92%
+   Tags: ["architecture", "microservices", "scalability"]
+```
+
+**Weeks later, new service:**
+```bash
+$ acfm memory search "microservices" --type architectural_decision
+→ [Memory #15] Microservices architecture chosen for scalability
+```
+
+### Example 3: Pattern Detection
+
+```bash
+$ acfm memory patterns --type bugfix_pattern
+
+Detected patterns:
+- null-check-react (3×) - Null checks in React components
+- async-race-condition (2×) - Race conditions in async code
+- cors-preflight (2×) - CORS preflight issues
+
+Recommendation: Consider adding ESLint rules for null checks
+```
+
+## Troubleshooting
+
+### Memory not saving
+- Check initialization: `acfm memory init`
+- Content may be below confidence threshold
+- May contain too many specific IDs
+
+### Search not finding results
+- Try broader keywords
+- Use `acfm memory recall` without query for general context
+- Check if memories exist: `acfm memory stats`
+
+### Database locked
+- Close other instances of `acfm`
+- SQLite is single-writer; wait a moment and retry
+
+## Related Skills
+
+- `acfm-spec-workflow` - Foundation for spec-driven development
+- `context-synthesizer` - For managing context in long conversations
+- `systematic-debugging` - For complex problem resolution
+
+## CLI Reference
+
+See `acfm memory --help` for all commands and options.
+
+---
+
+**Remember**: The memory system learns from every interaction. The more you use it, the more valuable it becomes.