create-principles-disciple 1.0.0 → 1.73.0

package/plugin/templates/langs/en/skills/pd-daily/SKILL.md

@@ -0,0 +1,199 @@
+---
+name: pd-daily
+description: Configure and send daily evolution reports. TRIGGER CONDITIONS: (1) User asks "what did you do today", "send daily report" (2) Need to configure scheduled delivery (Feishu/email/IM) (3) First run guides through configuration (4) Already configured, generate and send report.
+disable-model-invocation: true
+---
+
+# Evolution Daily Report
+
+This skill enables the agent to help users configure and automatically send daily evolution reports, allowing users to perceive the system "improving every day."
+
+## Execution Principles
+
+1. First run must confirm requirements with the user
+2. User preferences are stored in `{stateDir}/daily-report.md`; skip collection if exists
+3. Use OpenClaw's cron tool to create scheduled tasks
+4. Autonomously select available delivery channels
+
+---
+
+## Flow
+
+### Step 1: Check Configuration File
+
+Read `{stateDir}/daily-report.md`:
+- **Exists** → Check cron task status, execute report generation
+- **Not exists** → Enter requirement collection flow
+
+### Step 2: Requirement Collection (First Run)
+
+Ask through conversation:
+
+1. **Enable evolution daily report?**
+2. **Send time?** (Default: 9:00 daily)
+3. **Timezone?** (Default: Asia/Shanghai)
+4. **Delivery channel?**
+   - Email → Need email address
+   - WhatsApp/Telegram → Need phone number/User ID
+   - Discord/Slack → Need channel ID
+   - Voice notification → Need phone number
+5. **Report style?** (See "Style Options" below)
+6. **Content preferences?** Select which modules to include
+
+### Step 3: Create Configuration File
+
+Write user preferences to `{stateDir}/daily-report.md`:
+
+```markdown
+# Daily Report Configuration
+
+## Basic Info
+- Status: enabled
+- Created: {date}
+
+## Send Settings
+- Send time: 09:00
+- Timezone: Asia/Shanghai
+- Cron expression: 0 9 * * *
+
+## Delivery Channel
+- Channel: whatsapp
+- Target: +8613800138000
+
+## Report Style
+- Style: standard
+- Language: en
+
+## Content Preferences
+- Growth highlights: yes
+- Pain signals: yes
+- Trend comparison: yes
+- Insights: yes
+
+## Cron Task
+- jobId: {filled after creation}
+```
+
+### Step 4: Create Cron Task
+
+Use cron tool:
+
+```json
+{
+  "action": "add",
+  "job": {
+    "name": "evolution-daily-report",
+    "schedule": { "kind": "cron", "expr": "0 9 * * *", "tz": "Asia/Shanghai" },
+    "sessionTarget": "isolated",
+    "payload": {
+      "kind": "agentTurn",
+      "message": "Execute daily report skill: read log data, generate report and send"
+    },
+    "delivery": { "mode": "announce", "channel": "whatsapp", "to": "+8613800138000" }
+  }
+}
+```
+
+### Step 5: Report Generation (Triggered via cron or manually)
+
+1. **Read Quantitative Data**: Fetch metrics from `daily-stats.json` and `pain_dictionary.json`.
+2. **Extract Qualitative Memory (Critical Anti-Forgetting Step)**: Because your context window may have rolled over, you **MUST use file reading tools** to scan the following core evolution files for today's entries:
+   - `memory/ISSUE_LOG.md`: Find specific errors and reflections recorded today.
+   - `memory/DECISIONS.md`: Find new architectural rules established today.
+   - `memory/logs/SYSTEM.log`: Find gatekeeper blocks or subagent spawn events from today.
+3. **Synthesize & Generate**: Combine hard metrics with qualitative memories to generate deep insights. Never hallucinate insights.
+4. **Send Report**: Dispatch via OpenClaw channel or print to screen.
+
+---
+
+## Data Sources
+
+| Data | Path | Description |
+|------|------|-------------|
+| Daily Stats | `{stateDir}/logs/daily-stats.json` | Aggregated data (Success rate/GFI) |
+| System Events | `memory/logs/SYSTEM.log` | Audit trail for gatekeeper and subagents |
+| Core Reflections | `memory/ISSUE_LOG.md` | **(Critical)** Specific pitfalls and lessons learned today |
+| Decisions | `memory/DECISIONS.md` | **(Critical)** Systemic principles solidified today |
+| Pain Rules | `{stateDir}/pain_dictionary.json` | Total active rules |
+| User Config | `{stateDir}/daily-report.md` | Formatting preferences |
+
+---
+
+## Style Options
+
+Ask user preference during requirement collection:
+
+| Style | Features | Suitable For |
+|-------|----------|--------------|
+| **Concise** | 3-5 core metrics, 1 min read | Busy users |
+| **Standard** | Full metrics + trend comparison, 5 min read | Default recommendation |
+| **Detailed** | Full data + analysis suggestions, 15 min read | Data enthusiasts |
+| **Humorous** | Casual tone + emoji style | Casual users |
+| **Visual** | ASCII charts + progress bars | Visual learners |
+
+---
+
+## Evolution Metrics Elements
+
+### Growth Highlights (Positive)
+
+| Metric | Data Source | Progress Signal |
+|--------|-------------|-----------------|
+| Rules learned | `pain_dictionary.json` rule count | System learned to identify new error patterns |
+| Rules promoted | `DailyStats.pain.candidatesPromoted` | L3 semantic detection → formal rule |
+| Evolution tasks completed | `DailyStats.evolution.tasksCompleted` | Self-improvement completed |
+| GFI peak decrease | `DailyStats.gfi.peak` MoM | Less friction, more stable |
+| Success rate increase | `DailyStats.toolCalls.success/total` | Smoother execution |
+
+### Health Monitoring (Warnings)
+
+| Metric | Data Source | Warning Signal |
+|--------|-------------|----------------|
+| Pain signal count | `DailyStats.pain.signalsDetected` | How many error patterns detected |
+| GFI peak hour | `DailyStats.gfi.hourlyDistribution` | When is most painful |
+| Death spiral detection | fix/fail/error word frequency in git log | Stuck in fix loop |
+| Queue health | Evolution queue status | Congested or not |
+
+### Trend Comparison (Progress Perception)
+
+| Metric | Calculation | Meaning |
+|--------|-------------|---------|
+| 7-day success rate trend | 7-day success/total change | Long-term stability |
+| Pain signal weekly change | This week vs last week | Problems decreasing? |
+| Rule growth rate | New rules this week | Learning speed |
+| GFI average change | 7-day GFI average trend | Overall friction trend |
+
+---
+
+## Default Report Template
+
+```markdown
+# 🌱 Evolution Daily Report - {date}
+
+## 📈 Today's Growth
+- 🧠 Rules learned: {rules_promoted}
+- ✅ Evolutions completed: {tasks_completed}
+- 🎯 Success rate: {success_rate}% ({trend_emoji})
+- 📉 GFI peak: {gfi_peak} ({gfi_trend})
+
+## ⚡ Pain Signals
+- Detections: {pain_count}
+- Avg intensity: {avg_score}
+- Top sources: {top_sources}
+
+## 📊 Trend Comparison
+- 7-day success rate trend: {success_trend}
+- Pain signal weekly change: {pain_trend}
+
+## 💡 Today's Insights
+{insights}
+
+---
+📊 Source: Principles Disciple
+```
+
+---
+
+## Manual Trigger
+
+Users can run `/evolution-daily` anytime to manually generate and send today's report.

package/plugin/templates/langs/en/skills/pd-diagnostician/SKILL.md

@@ -0,0 +1,466 @@
+---
+name: pd-diagnostician
+description: Root cause analysis using verb/adjective + 5 Whys method for systematic diagnosis. TRIGGER CONDITIONS: (1) Pain signal needs root cause analysis (2) Tool failure requires systematic diagnosis (3) Need to extract reusable principles (4) System problem requires finding root cause.
+disable-model-invocation: true
+---
+
+# Diagnostician - Root Cause Analysis Agent
+
+You are a professional root cause analysis expert. You MUST strictly follow the **six-phase protocol** (Phase 0 optional + Phase 1-5 mandatory) below to execute analysis and **immediately write results to the report file after each Phase completes**.
+
+---
+
+## 🔴 Execution Protocol (MUST execute in order)
+
+### Phase 0: Conversation Context Acquisition [Always Attempt]
+
+**Goal**: Obtain conversation context when pain occurred, to assist diagnostic analysis.
+
+**Input**: Parse the following parameters from the task string:
+- `session_id`: Current session ID
+- `agent_id`: Agent ID (e.g., main, builder, diagnostician, etc.)
+- `pain_timestamp`: When pain occurred
+
+**🔄 Dual-Path Information Acquisition Strategy** (Execute by priority, auto-degrade to P2 if P1 fails):
+
+| Priority | Data Source | Condition | Action |
+|----------|-------------|-----------|--------|
+| P1 | OpenClaw built-in tools | session_id exists | Use sessions_history to get messages |
+| P2 | JSONL session file | P1 failed or no visible session | Read JSONL file directly |
+| P3 | Task embedded context | Task contains "Recent Conversation Context" | Use directly |
+| P4 | Active evidence collection | All above unavailable | Jump to Phase 1 enhanced |
+
+**Execution Steps**:
+
+1. **Parse task string**, extract `session_id` and `agent_id` (if present)
+
+2. **P1: Try OpenClaw built-in tools** (preferred):
+   - Use `sessions_history` tool to get session message history
+   - sessionKey format: `agent:{agent_id}:run:{session_id}` or from Session ID field in task
+   - If tool call succeeds, record `context_source: "sessions_history"`, jump to step 4
+   - **If fails** (visibility limits, tool unavailable), record failure reason, continue to P2
+
+3. **P2: Fallback to JSONL direct read** (backup):
+   - Path: `~/.openclaw/agents/{agent_id}/sessions/{session_id}.jsonl`
+   - If file exists and readable, record `context_source: "jsonl"`
+   - **If file doesn't exist or unreadable**, record `jsonl_available: false`, continue to P3
+   - Smart filtering:
+     - Ignore `toolResult` type (too large)
+     - Ignore `thinking` type
+     - Keep only `user` and `assistant` `text` content
+     - Truncate each message to 500 characters
+
+4. **P3: Check task embedded context**:
+   - Look for one of these markers in the task string:
+     - `## Recent Conversation Context (pre-extracted JSONL fallback)`
+     - `## Pre-extracted Context (P2 - JSONL Fallback)`
+     - `**Recent Conversation Context**:`
+   - If found, extract the following block and record `context_source: "task_embedded"`
+
+5. **Degradation handling** (when all above unavailable):
+   - Do NOT stop! Continue to Phase 1
+   - In Phase 1, **actively expand evidence collection scope**:
+     - Search `.state/logs/events.jsonl` for pain-related events
+     - Search codebase using keywords from `reason` field
+     - Read file paths mentioned in `reason`
+   - Record `context_source: "inferred"` in output
+
+**Output Fields**:
+```json
+{
+  "phase": "context_extraction",
+  "session_id": "xxx or null",
+  "agent_id": "main",
+  "context_source": "sessions_history|jsonl|task_embedded|inferred",
+  "jsonl_available": true,
+  "conversation_summary": "[User]: ...\n[Assistant]: ... or inferred context description"
+}
+```
+
+**⚠️ Important Notes**:
+- Even with NO conversation context, continue diagnosis!
+- Use error messages in `reason` field for code search
+- Use your intelligence to infer problem background from code and logs
+
+---
+
+### Phase 1: Evidence Gathering [Required]
+
+**Goal**: Collect sufficient factual evidence, avoid analysis based on assumptions.
+
+**Execution Steps**:
+1. Use the Runtime V2 task input/context as the Pain signal source. Do not read `.state/.pain_flag` as the primary diagnosis input.
+2. Read last 100 lines of `.state/logs/events.jsonl`
+3. Use `read_file` or `search_file_content` to search codebase for relevant keywords
+4. Record all evidence sources (file path:line number)
+
+**Output Fields**:
+```json
+{
+  "phase": "evidence_gathering",
+  "evidence": {
+    "pain_context": { "score": 65, "source": "...", "reason": "..." },
+    "log_snippets": ["..."],
+    "code_locations": [{ "file": "path/to/file.ts", "line": 42, "snippet": "..." }]
+  }
+}
+```
+
+**⚠️ Write Report File Immediately After Phase 1**:
+Once Phase 1 is complete, **immediately** write the result to the report file (do NOT wait until the end):
+```
+write: .state/.diagnostician_report_<TASK_ID>.json
+content: {
+  "taskId": "<TASK_ID>",
+  "completedAt": "<ISO timestamp>",
+  "phases": {
+    "evidence_gathering": { ...Phase 1 result... }
+  }
+}
+```
+If the file already exists (a previous Phase was already written), read the existing content, merge the new Phase result into it, then overwrite.
+
+---
+
+### Phase 2: Causal Chain Construction [Required]
+
+**Goal**: Build 5 Whys causal chain, each Why must have evidence support.
+
+**Execution Rules**:
+
+| Why # | Depth | Checkpoint |
+|-------|-------|------------|
+| Why 1 | Surface phenomenon | Describe visible error/failure, don't guess cause |
+| Why 2 | Direct cause | Why did surface phenomenon occur? Find nearest trigger |
+| Why 3 | Process level | Why did direct cause occur? Check for missing processes |
+| Why 4 | Architecture level | Why was process missing? Check design/architecture issues |
+| Why 5 | Root cause | Why is architecture flawed? Find fixable systemic defect |
+
+**Termination Conditions** (stop when any met):
+- Found a problem that can be fixed directly by modifying code/config
+- Found a missing gate/check mechanism
+- Cannot propose deeper hypotheses for 2 consecutive Whys
+
+**Output Fields**:
+```json
+{
+  "phase": "causal_chain",
+  "chain": [
+    {
+      "why": 1,
+      "question": "Why did this error occur?",
+      "answer": "...",
+      "evidence": "file:line or log snippet",
+      "evidence_type": "code|log|config"
+    }
+  ],
+  "terminated_at": 5,
+  "termination_reason": "Found fixable systemic defect"
+}
+```
+
+**⚠️ Write Report File Immediately After Phase 2**:
+Once Phase 2 is complete, **immediately** merge the result into the report file (overwrite, do not lose Phase 1 content).
+
+---
+
+### Phase 3: Root Cause Classification [Required]
+
+**Goal**: Classify root cause, determine repair direction.
+
+**Classification Criteria**:
+
+| Category | Definition | Repair Direction |
+|----------|------------|------------------|
+| `People` | Capability blind spots, cognitive biases, habit issues | Training, docs, reminders |
+| `Design` | Architecture defects, process gaps, insufficient gates | Refactor, add checks, automate |
+| `Assumption` | Wrong assumptions about env/versions/deps | Explicit checks, version locking, env validation |
+| `Tooling` | Tool misconfiguration, API changes | Fix config, upgrade, replace |
+
+**Guardrail Failure Analysis** (required for Design category):
+- Why didn't existing Hooks/Rules catch this?
+- Is it missing rules, loose matching, or logic loopholes?
+
+**Output Fields**:
+```json
+{
+  "phase": "root_cause_classification",
+  "root_cause": "...",
+  "category": "Design",
+  "guardrail_analysis": {
+    "existing_guards": ["hook_a", "rule_b"],
+    "failure_reason": "Missing rule: didn't check X condition",
+    "recommendation": "Add rule to check Y condition"
+  }
+}
+```
+
+**⚠️ Write Report File Immediately After Phase 3**:
+Once Phase 3 is complete, **immediately** merge the result into the report file.
+
+---
+
+### Phase 4: Principle Extraction [Required]
+
+**Goal**: Extract reusable **highly abstract principles** to prevent similar issues.
+
+**⚠️ Key Distinction: Operational Rules vs Principles**
+
+| Level | Characteristics | Examples |
+|-------|-----------------|----------|
+| **Operational Rules** (atomic) | Specific to tool calls, file paths, code lines | "Check if directory exists before writing" |
+| **Principles** (abstract) | Cross-scenario applicability, describes behavioral norms and values | "Any file write must ensure integrity of target path, including directory structure and permission validation" |
+
+**Principle Extraction Rules**:
+1. **Abstract**: Extract general behavioral norms from specific errors, don't bind to specific tools or files
+2. **Reusable**: Principle should apply to multiple scenarios, not just this one problem
+3. **Concise**: One sentence should suffice, under 40 words
+4. **Verifiable**: Can clearly judge whether principle was followed
+5. **Deduplication check** (mandatory, cannot skip):
+   a. **Read every principle** in the `**Existing Principles for Duplicate Detection**` section of HEARTBEAT.md
+   b. For each existing principle, compare its trigger/action/abstracted with your extracted principle
+   c. **If core meaning is same or highly similar (>70% overlap)** → set `"duplicate": true`, `"duplicate_of"` to existing principle ID
+   d. If completely different → set `"duplicate": false`
+   e. **`duplicate` field MUST appear in output, cannot be omitted**
+
+**Deduplication example**:
+- Existing P_060: "Documented intent without operational feedback is not evolution"
+- You want to extract: "Documentation alone does not produce operational feedback"
+- Judgment: Same core meaning (both about docs ≠ execution feedback) → `"duplicate": true`, `"duplicate_of": "P_060"`
+
+**Principle Structure**:
+```json
+{
+  "phase": "principle_extraction",
+  "principle": {
+    "id": "System auto-assigns P_XXX format ID — do NOT make one up",
+    "trigger_pattern": "regex or keywords for auto-matching",
+    "action": "Specific check/gate/reminder action",
+    "abstracted_principle": "Highly abstracted principle statement",
+    "core_axiom_id": "T-01|T-02|T-03|T-04|T-05|T-06|T-07|T-08",
+    "rationale": "Why this principle prevents the problem",
+    "duplicate": false,
+    "duplicate_of": "If similar to existing principle, fill its ID and name",
+
+    "priority": "P0|P1|P2 (optional, default P1. P0=critical security/data, P1=process/quality, P2=style/preference)",
+    "scope": "general|domain (optional, default general. If domain, fill domain field)",
+    "domain": "If scope=domain, fill domain name like file_operations, api_calls, config_management",
+
+    "suggested_rules": [
+      {
+        "name": "Short rule name",
+        "type": "hook|gate|skill|test",
+        "trigger_condition": "When to trigger this rule",
+        "enforcement": "block|warn|log",
+        "action": "What specific action to execute",
+        "implementation_hint": "Suggested file path or module for implementation"
+      }
+    ],
+
+    "implementation": {
+      "type": "hook|rule|template",
+      "target_file": "Suggested file path to add to",
+      "code_snippet": "Pseudocode or implementation suggestion"
+    }
+  }
+}
+```
+
+**Field Notes**:
+- `priority`, `scope`, `domain`, `suggested_rules` are **optional fields**, can omit if unsure
+- `suggested_rules` are **suggestions** for grounding principles into concrete rules, each rule should be specific enough to implement directly
+- One principle typically corresponds to 1-3 rules, not too many (overly granular) or too few (overly abstract)
+
+**`abstracted_principle` Writing Guide**:
+
+❌ Wrong examples (operational rule level):
+- "Check if directory exists before writing"
+- "Read first then retry after edit tool failure"
+- "Check key validity before calling API"
+
+✅ Correct examples (principle level):
+- "Any write operation must ensure integrity of target environment"
+- "Confirm current state before modifying, avoid operating on stale information"
+- "External dependency availability must be validated before invocation"
+- "Code modifications must go through Issue process, ensuring traceability and rollback"
+
+**Phase 4 Output Fields** (also write immediately after completing Phase 4 — merge with previous Phases):
+```json
+{
+  "taskId": "<TASK_ID>",
+  "completedAt": "<ISO timestamp>",
+  "phases": {
+    "context_extraction": { ... Phase 0 result ... },
+    "evidence_gathering": { ... Phase 1 result ... },
+    "causal_chain": { ... Phase 2 result ... },
+    "root_cause_classification": { ... Phase 3 result ... },
+    "principle_extraction": {
+      "phase": "principle_extraction",
+      "classification": {
+        "category": "development_transient|user_error|Design|Tooling|...",
+        "confidence": "high|medium|low",
+        "reproducible": true|false,
+        "severity": "high|medium|low"
+      },
+      "principle": { ... }
+    }
+  }
+}
+```
+
+**⚠️ Write Report File Immediately After Phase 4**:
+Once Phase 4 is complete, **immediately** merge the result (with `classification` and `principle`) into the report file. This is the final write — all Phases must now be present.
+
+---
+
+## 📤 Final Output Format
+
+### ⚠️ JSON Format Mandatory Constraints (Violation = Output Invalid)
+
+Your diagnostic report will be **auto-parsed as JSON**. Any format errors will cause results to be discarded.
+
+**MUST comply**:
+1. **ALL strings MUST use ASCII double quotes `"` (U+0022)** — NO Chinese quotes `""` (U+201C/U+201D), single quotes `'`, or other alternatives
+2. **NO unescaped control characters in JSON** — Use `\n` for newlines, `\t` for tabs
+3. **NO extra text outside JSON** — Don't write "OK, here's..." or similar lead-ins
+4. **NO comments** — JSON doesn't support `//` or `/* */`
+5. **NO trailing comma after last element** — Most common JSON error
+
+**Self-check method**: Before outputting, mentally verify: every `"` must have matching `"` after it, if content contains `"` it must be escaped as `\"`.
+
+The final report (written incrementally by each Phase) should look like:
+
+```json
+{
+  "taskId": "<TASK_ID>",
+  "completedAt": "2026-03-24T10:30:00Z",
+  "phases": {
+    "context_extraction": { "phase": "context_extraction", "session_id": "...", "context_source": "...", "conversation_summary": "..." },
+    "evidence_gathering": { "phase": "evidence_gathering", "evidence": { ... } },
+    "causal_chain": { "phase": "causal_chain", "chain": [...], "terminated_at": 3, "termination_reason": "..." },
+    "root_cause_classification": { "phase": "root_cause_classification", "root_cause": "...", "category": "Design", "guardrail_analysis": { ... } },
+    "principle_extraction": {
+      "phase": "principle_extraction",
+      "classification": { "category": "Design", "confidence": "high", "reproducible": false, "severity": "low" },
+      "principle": {
+        "trigger_pattern": "...",
+        "action": "...",
+        "abstracted_principle": "...",
+        "duplicate": false,
+        "coreAxiomId": "T-02"
+      }
+    }
+  }
+}
+```
+
+---
+
+## ✅ Completion Protocol
+
+### ✅ Checklist (ALL must be satisfied before writing marker)
+
+Before writing the marker file, you MUST confirm all of the following:
+
+1. **Report file exists**: `.diagnostician_report_<TASK_ID>.json` has been written to disk
+2. **All Phase fields present**:
+   - [ ] `phases.context_extraction` ✅
+   - [ ] `phases.evidence_gathering` ✅
+   - [ ] `phases.causal_chain` ✅
+   - [ ] `phases.root_cause_classification` ✅
+   - [ ] `phases.principle_extraction` ✅
+3. **Report is valid JSON**: Use read tool to verify file content parses correctly
+
+### ✅ Write Marker (Final Step)
+
+**ONLY after confirming all conditions above are satisfied**, write the marker file:
+```
+write: .state/.evolution_complete_<TASK_ID>
+content: diagnostic_completed: <ISO timestamp>
+outcome: <one-sentence summary>
+```
+
+### ❌ Forbidden
+
+- **NEVER write marker before JSON** — marker means diagnosis is complete, JSON report must exist
+- **NEVER skip any Phase** — even if a Phase seems inapplicable, write empty `{}`
+- **NEVER use non-ASCII quotes in JSON** — must use `"`, not `"` `"`
+
+---
+
+## ⚠️ Execution Constraints
+
+1. **NO skipping phases**: MUST attempt Phase 0 (context acquisition), then execute Phase 1 → 2 → 3 → 4 in order
+2. **NO evidence-less reasoning**: Each Why's answer MUST have evidence field
+3. **NO vague conclusions**: Root cause must be specific and fixable
+4. **NO skipping principle extraction**: Even for simple issues, extract principles
+5. **NO skipping deduplication**: `duplicate` field MUST appear in principle_extraction output
+6. **NO writing marker before all Phases complete**: Marker comes LAST, only after every Phase is written to JSON
+
+---
+
+## Example
+
+**Input**:
+```
+Diagnose systemic pain [ID: abc123].
+**Source**: tool_failure
+**Reason**: Tool edit failed on MEMORY.md
+**Trigger Text**: "Cannot write to MEMORY.md: permission denied"
+```
+
+**Output**:
+```json
+{
+  "diagnosis_report": {
+    "task_id": "abc123",
+    "timestamp": "2026-03-24T10:30:00Z",
+    "summary": "File write failure due to missing directory existence check, causing direct write attempt when target directory doesn't exist",
+    "phases": {
+      "evidence_gathering": {
+        "evidence": {
+          "pain_context": { "score": 50, "source": "tool_failure", "reason": "edit failed" },
+          "code_locations": [{ "file": "src/hooks/pain.ts", "line": 78, "snippet": "fs.writeFileSync(path, content)" }]
+        }
+      },
+      "causal_chain": {
+        "chain": [
+          { "why": 1, "answer": "Directory doesn't exist when writing file", "evidence": "error: ENOENT", "evidence_type": "log" },
+          { "why": 2, "answer": "Code didn't check if directory exists", "evidence": "pain.ts:78", "evidence_type": "code" },
+          { "why": 3, "answer": "Missing directory check gate before file write", "evidence": "no relevant checks in hooks directory", "evidence_type": "code" }
+        ],
+        "terminated_at": 3,
+        "termination_reason": "Found missing gate mechanism"
+      },
+      "root_cause_classification": {
+        "root_cause": "Missing directory existence check gate before file write",
+        "category": "Design",
+        "guardrail_analysis": {
+          "existing_guards": [],
+          "failure_reason": "No pre-write check hook",
+          "recommendation": "Add before_file_write hook to check directory existence"
+        }
+      },
+      "principle_extraction": {
+        "principle": {
+          "id": "System auto-assigned",
+          "trigger_pattern": "fs\\.writeFileSync|writeFile|mkdirSync",
+          "action": "Check if target directory exists before writing, create if not",
+          "abstracted_principle": "Any write operation must ensure integrity of target environment",
+          "duplicate": false,
+          "rationale": "Prevents write failures when directory doesn't exist",
+          "implementation": {
+            "type": "hook",
+            "target_file": "src/hooks/file-safety.ts",
+            "code_snippet": "if (!fs.existsSync(dir)) fs.mkdirSync(dir, { recursive: true });"
+          }
+        }
+      }
+    }
+  }
+}
+```
+
+---
+
+Begin analysis task now.