[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77EVHJSDABMQ8R5VM9T5RTP":3,"skill-same:01M77EVHJSDABMQ8R5VM9T5RTP":73},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":50,"commitSha":51,"skillDirectory":52,"forksCount":53,"repositoryHtmlUrl":54,"repositoryHomepageUrl":55,"ownerHtmlUrl":56,"ownerBlogUrl":6,"ownerDescription":57,"updatedAt":58,"install":59,"resources":72},"01M77EVHJSDABMQ8R5VM9T5RTP","failure-memory",null,"Stop making the same mistakes — turn failures into patterns that prevent recurrence","Lord1Egypt\u002Fawesome-skill-forge","Lord1Egypt","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F99746359?v=4","01M7592YDNT0XK9WJ0T2MQVPDN","Mohamed Mounir Ali AL Keshita","01M75GRFNHC8VZNWEB8DKDE433",3,"MIT","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fclawhub\u002Ff\u002Ffailure-memory\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: failure-memory\nversion: 1.5.0\ndescription: Stop making the same mistakes — turn failures into patterns that prevent recurrence\nauthor: Live Neon \u003Ccontact@liveneon.dev>\nhomepage: https:\u002F\u002Fgithub.com\u002Flive-neon\u002Fskills\u002Ftree\u002Fmain\u002Fagentic\u002Ffailure-memory\nrepository: leegitw\u002Ffailure-memory\nlicense: MIT\ntags: [agentic, memory, learning, self-improving, error-tracking, observability, patterns, adaptive, feedback]\nlayer: core\nstatus: active\nalias: fm\nmetadata:\n  openclaw:\n    requires:\n      config:\n        - .openclaw\u002Ffailure-memory.yaml\n        - .claude\u002Ffailure-memory.yaml\n      workspace:\n        - .learnings\u002F\n        - .learnings\u002Fobservations\u002F\n---\n\n# failure-memory (記憶)\n\nUnified skill for failure detection, observation recording, memory search, and pattern convergence.\nConsolidates 10 granular skills into a single coherent memory system.\n\n**Trigger**: 失敗発生 (failure occurred)\n\n**Source skills**: failure-tracker, observation-recorder, memory-search, topic-tagger, failure-detector, evidence-tier, effectiveness-metrics, pattern-convergence-detector, positive-framer, contextual-injection\n\n## Installation\n\n```bash\nopenclaw install leegitw\u002Ffailure-memory\n```\n\n**Dependencies**: `leegitw\u002Fcontext-verifier` (for file change detection)\n\n```bash\n# Install with dependencies\nopenclaw install leegitw\u002Fcontext-verifier\nopenclaw install leegitw\u002Ffailure-memory\n```\n\n**Standalone usage**: This skill can function independently for basic failure tracking.\nFor full lifecycle management, install the complete suite (see [Neon Agentic Suite](..\u002FREADME.md)).\n\n**Data handling**: This skill operates within your agent's trust boundary. When triggered,\nit uses your agent's configured model for failure detection and pattern recording. No external APIs\nor third-party services are called. Results are written to `.learnings\u002F` in your workspace.\n\n## What This Solves\n\nAI systems often make the same mistakes repeatedly — deleting working code, missing edge cases, forgetting context. This skill turns failures into learning by:\n\n1. **Detecting failures** when they happen (not after)\n2. **Recording observations** with R\u002FC\u002FD counters (Recurrence\u002FConfirmations\u002FDisconfirmations)\n3. **Finding patterns** within the workspace's `.learnings\u002F` directory\n4. **Promoting to constraints** when evidence threshold is met\n\n**The insight**: Systems learn better from consequences than instructions. A failure that happened teaches more than a rule that might apply.\n\n> **Scope note**: Pattern detection operates within the current workspace only. Observations\n> are stored in `.learnings\u002F` and searched locally. No cross-project data access occurs.\n\n## Usage\n\n```\n\u002Ffm \u003Csub-command> [arguments]\n```\n\n## Sub-Commands\n\n| Command | CJK | Logic | Trigger |\n|---------|-----|-------|---------|\n| `\u002Ffm detect` | 検出 | fail∈{test,user,API}→record | Next Steps (auto) |\n| `\u002Ffm record` | 記録 | pattern→obs, R++∨C++∨D++ | Next Steps (auto) |\n| `\u002Ffm search` | 索引 | query(pattern∨tag∨slug)→obs[] | Explicit |\n| `\u002Ffm classify` | 分類 | obs→tier∈{N=1:弱,N=2:中,N≥3:強} | Explicit |\n| `\u002Ffm status` | 状態 | eligible:R≥3∧C≥2, recent:30d | Explicit |\n| `\u002Ffm refactor` | 整理 | obs[]→merge∨split∨restructure | Explicit |\n| `\u002Ffm converge` | 収束 | pattern[]→detect(similarity≥0.8) | Explicit |\n\n## Arguments\n\n### \u002Ffm detect\n\n| Argument | Required | Description |\n|----------|----------|-------------|\n| type | Yes | Failure type: `test`, `user`, `api`, `error` |\n| context | No | Additional context for the failure |\n\n### \u002Ffm record\n\n| Argument | Required | Description |\n|----------|----------|-------------|\n| pattern | Yes | Pattern description or observation ID |\n| counter | No | Counter to increment: `R` (default), `C`, or `D` |\n\n### \u002Ffm search\n\n| Argument | Required | Description |\n|----------|----------|-------------|\n| query | Yes | Search pattern, tag, or slug |\n| status | No | Filter by status: `pending`, `eligible`, `all` (default) |\n\n### \u002Ffm classify\n\n| Argument | Required | Description |\n|----------|----------|-------------|\n| observation | Yes | Observation ID or pattern |\n\n### \u002Ffm status\n\n| Argument | Required | Description |\n|----------|----------|-------------|\n| --eligible | No | Show only eligible observations (R≥3 ∧ C≥2) |\n| --recent | No | Show only observations from last 30 days |\n\n### \u002Ffm refactor\n\n| Argument | Required | Description |\n|----------|----------|-------------|\n| observations | Yes | Comma-separated observation IDs |\n| action | Yes | Action: `merge`, `split`, `restructure` |\n\n### \u002Ffm converge\n\n| Argument | Required | Description |\n|----------|----------|-------------|\n| --threshold | No | Similarity threshold (default: 0.8) |\n\n## Detection Triggers\n\nThese patterns indicate when `\u002Ffm detect` should be invoked (user or orchestrator triggers):\n\n| Pattern | Source | Action |\n|---------|--------|--------|\n| `test.exit_code != 0` | Tool output | `\u002Ffm detect test` |\n| \"Actually...\", \"No, that's wrong\" | User message | `\u002Ffm record correction` |\n| \"I meant...\", \"Not X, Y\" | User message | `\u002Ffm record correction` |\n| API 4xx\u002F5xx response | Tool output | `\u002Ffm detect api` |\n| \"error:\", \"failed\", \"Exception\" | Tool output | `\u002Ffm detect error` |\n| Deployment rollback | CI\u002FCD output | `\u002Ffm detect deployment` |\n| Database migration failed | Tool output | `\u002Ffm detect migration` |\n\n### Example: API Failure Detection\n\n```\n[DETECTED] api failure\nPattern: payment-api-timeout\nContext: Payment API returned 504 after 30s\nObservation: OBS-20260215-002\nR: 1 → 3\nStatus: Eligible for constraint (R≥3)\n```\n\n### Example: Deployment Failure Detection\n\n```\n[DETECTED] deployment failure\nPattern: staging-healthcheck-fail\nContext: Staging deployment failed health check on \u002Fapi\u002Fhealth\nObservation: OBS-20260215-003\nR: 1 → 2\nStatus: Monitoring (R\u003C3)\n```\n\n## Core Logic\n\n### R\u002FC\u002FD Counters\n\n| Counter | Meaning | Updated By |\n|---------|---------|------------|\n| **R** (Recurrence) | Auto-detected occurrences | `\u002Ffm detect`, `\u002Ffm record` |\n| **C** (Confirmations) | Human-verified true positives | Human via `\u002Ffm record C` |\n| **D** (Disconfirmations) | Human-verified false positives | Human via `\u002Ffm record D` |\n\n### Evidence Tiers\n\n| Tier | Criteria | Meaning |\n|------|----------|---------|\n| 弱 (weak) | N=1 | Single occurrence, may be noise |\n| 中 (emerging) | N=2 | Pattern emerging, monitor |\n| 強 (strong) | N≥3 | Established pattern, actionable |\n\n### Slug Taxonomy\n\nObservations are tagged with slugs: `git-*`, `test-*`, `workflow-*`, `security-*`, `docs-*`, `quality-*`\n\n### Metrics\n\n- `prevention_rate`: Failures prevented \u002F Total potential failures\n- `false_positive_rate`: D \u002F (C + D)\n\n## Output\n\n### \u002Ffm detect output\n\n```\n[DETECTED] test failure\nPattern: lint-before-commit\nObservation: OBS-20260215-001\nR: 1 → 2\nStatus: Monitoring (R\u003C3)\n```\n\n### \u002Ffm status output\n\n```\n=== Failure Memory Status ===\n\nEligible for constraint (R≥3 ∧ C≥2):\n- OBS-20260210-003: lint-before-commit (R=4, C=2, D=0)\n- OBS-20260212-007: test-before-push (R=3, C=3, D=1)\n\nRecent (last 30d): 12 observations\nPending review: 3 observations\n```\n\n## Configuration\n\nConfiguration is loaded from (in order of precedence):\n1. `.openclaw\u002Ffailure-memory.yaml` (OpenClaw standard)\n2. `.claude\u002Ffailure-memory.yaml` (Claude Code compatibility)\n3. Defaults (built-in)\n\n```yaml\n# .openclaw\u002Ffailure-memory.yaml\ndetection:\n  auto_detect: true          # Enable automatic failure detection\n  patterns:                   # Custom detection patterns\n    - \"FATAL:\"\n    - \"CRITICAL:\"\nthresholds:\n  eligibility_R: 3           # Recurrence threshold (default: 3)\n  eligibility_C: 2           # Confirmation threshold (default: 2)\n  false_positive_max: 0.2    # Max D\u002F(C+D) ratio (default: 0.2)\n```\n\n## Integration\n\n- **Layer**: Core\n- **Depends on**: context-verifier (for file change detection)\n- **Used by**: constraint-engine (for eligibility checks), governance (for state queries)\n\n## Failure Modes\n\n| Condition | Behavior |\n|-----------|----------|\n| Invalid sub-command | List available sub-commands |\n| Missing observation ID | Error with usage example |\n| No matches found | \"No observations match query\" |\n| Duplicate detection | Increment R counter, don't create new observation |\n\n## Next Steps\n\nAfter invoking this skill:\n\n| Condition | Action |\n|-----------|--------|\n| R incremented | Check eligibility: R≥3 ∧ C≥2 → notify user |\n| R≥3 ∧ C≥2 | Suggest `\u002Fce generate` for constraint |\n| Pattern recurring | Link with `See Also`, bump priority |\n| Always | Update `.learnings\u002FERRORS.md` or `.learnings\u002FLEARNINGS.md` |\n\n## Workspace Files\n\nThis skill reads\u002Fwrites:\n\n```\n.learnings\u002F\n├── ERRORS.md        # [ERR-YYYYMMDD-XXX] command failures\n├── LEARNINGS.md     # [LRN-YYYYMMDD-XXX] corrections, best practices\n└── observations\u002F    # Individual observation files\n    └── OBS-YYYYMMDD-XXX.md\n```\n\n## Security Considerations\n\n**What this skill accesses:**\n- Configuration files in `.openclaw\u002Ffailure-memory.yaml` and `.claude\u002Ffailure-memory.yaml`\n- Tool output and user messages in the current session (for failure detection)\n- Its own workspace directory `.learnings\u002F` (read\u002Fwrite)\n\n**What this skill does NOT access:**\n- Files outside declared workspace paths\n- System environment variables\n- Other projects or sessions (observations are workspace-local)\n- Network resources or external APIs\n\n**What this skill does NOT do:**\n- Send data to external services\n- Access \"across sessions and projects\" beyond the current workspace\n- Execute arbitrary code or run external commands\n\n**Data scope clarification:**\n- \"Failure detection\" scans tool output and user messages within the current agent session\n- Observations are stored in `.learnings\u002F` within the current workspace only\n- No cross-project or cross-session data access occurs\n- Pattern matching is local to the configured workspace\n\n**Detection trigger clarification:**\nThe \"Detection Triggers\" table describes patterns that indicate when this skill should be\ninvoked. The agent can auto-invoke `\u002Ffm detect` when these patterns are detected, or users\ncan invoke manually. This enables true agentic behavior — failures are captured automatically.\n\n**Provenance note:**\nThis skill is developed by Live Neon (https:\u002F\u002Fgithub.com\u002Flive-neon\u002Fskills) and published\nto ClawHub under the `leegitw` account. Both refer to the same maintainer.\n\n## Acceptance Criteria\n\n- [ ] `\u002Ffm detect` creates or updates observation with R++\n- [ ] `\u002Ffm record` supports R, C, D counter updates\n- [ ] `\u002Ffm search` finds observations by pattern, tag, or slug\n- [ ] `\u002Ffm classify` returns correct tier based on N count\n- [ ] `\u002Ffm status` shows eligible observations\n- [ ] `\u002Ffm refactor` merges\u002Fsplits observations correctly\n- [ ] `\u002Ffm converge` detects similar patterns (≥0.8 similarity)\n- [ ] Detection triggers work for test failures, user corrections, API errors\n- [ ] Workspace files follow self-improving-agent format\n\n---\n\n*Consolidated from 10 skills as part of agentic skills consolidation (2026-02-15).*\n","# failure-memory (記憶)\n\nUnified skill for failure detection, observation recording, memory search, and pattern convergence.\nConsolidates 10 granular skills into a single coherent memory system.\n\n**Trigger**: 失敗発生 (failure occurred)\n\n**Source skills**: failure-tracker, observation-recorder, memory-search, topic-tagger, failure-detector, evidence-tier, effectiveness-metrics, pattern-convergence-detector, positive-framer, contextual-injection\n\n## Installation\n\n```bash\nopenclaw install leegitw\u002Ffailure-memory\n```\n\n**Dependencies**: `leegitw\u002Fcontext-verifier` (for file change detection)\n\n```bash\n# Install with dependencies\nopenclaw install leegitw\u002Fcontext-verifier\nopenclaw install leegitw\u002Ffailure-memory\n```\n\n**Standalone usage**: This skill can function independently for basic failure tracking.\nFor full lifecycle management, install the complete suite (see [Neon Agentic Suite](..\u002FREADME.md)).\n\n**Data handling**: This skill operates within your agent's trust boundary. When triggered,\nit uses your agent's configured model for failure detection and pattern recording. No external APIs\nor third-party services are called. Results are written to `.learnings\u002F` in your workspace.\n\n## What This Solves\n\nAI systems often make the same mistakes repeatedly — deleting working code, missing edge cases, forgetting context. This skill turns failures into learning by:\n\n1. **Detecting failures** when they happen (not after)\n2. **Recording observations** with R\u002FC\u002FD counters (Recurrence\u002FConfirmations\u002FDisconfirmations)\n3. **Finding patterns** within the workspace's `.learnings\u002F` directory\n4. **Promoting to constraints** when evidence threshold is met\n\n**The insight**: Systems learn better from consequences than instructions. A failure that happened teaches more than a rule that might apply.\n\n> **Scope note**: Pattern detection operates within the current workspace only. Observations\n> are stored in `.learnings\u002F` and searched locally. No cross-project data access occurs.\n\n## Usage\n\n```\n\u002Ffm \u003Csub-command> [arguments]\n```\n\n## Sub-Commands\n\n| Command | CJK | Logic | Trigger |\n|---------|-----|-------|---------|\n| `\u002Ffm detect` | 検出 | fail∈{test,user,API}→record | Next Steps (auto) |\n| `\u002Ffm record` | 記録 | pattern→obs, R++∨C++∨D++ | Next Steps (auto) |\n| `\u002Ffm search` | 索引 | query(pattern∨tag∨slug)→obs[] | Explicit |\n| `\u002Ffm classify` | 分類 | obs→tier∈{N=1:弱,N=2:中,N≥3:強} | Explicit |\n| `\u002Ffm status` | 状態 | eligible:R≥3∧C≥2, recent:30d | Explicit |\n| `\u002Ffm refactor` | 整理 | obs[]→merge∨split∨restructure | Explicit |\n| `\u002Ffm converge` | 収束 | pattern[]→detect(similarity≥0.8) | Explicit |\n\n## Arguments\n\n### \u002Ffm detect\n\n| Argument | Required | Description |\n|----------|----------|-------------|\n| type | Yes | Failure type: `test`, `user`, `api`, `error` |\n| context | No | Additional context for the failure |\n\n### \u002Ffm record\n\n| Argument | Required | Description |\n|----------|----------|-------------|\n| pattern | Yes | Pattern description or observation ID |\n| counter | No | Counter to increment: `R` (default), `C`, or `D` |\n\n### \u002Ffm search\n\n| Argument | Required | Description |\n|----------|----------|-------------|\n| query | Yes | Search pattern, tag, or slug |\n| status | No | Filter by status: `pending`, `eligible`, `all` (default) |\n\n### \u002Ffm classify\n\n| Argument | Required | Description |\n|----------|----------|-------------|\n| observation | Yes | Observation ID or pattern |\n\n### \u002Ffm status\n\n| Argument | Required | Description |\n|----------|----------|-------------|\n| --eligible | No | Show only eligible observations (R≥3 ∧ C≥2) |\n| --recent | No | Show only observations from last 30 days |\n\n### \u002Ffm refactor\n\n| Argument | Required | Description |\n|----------|----------|-------------|\n| observations | Yes | Comma-separated observation IDs |\n| action | Yes | Action: `merge`, `split`, `restructure` |\n\n### \u002Ffm converge\n\n| Argument | Required | Description |\n|----------|----------|-------------|\n| --threshold | No | Similarity threshold (default: 0.8) |\n\n## Detection Triggers\n\nThese patterns indicate when `\u002Ffm detect` should be invoked (user or orchestrator triggers):\n\n| Pattern | Source | Action |\n|---------|--------|--------|\n| `test.exit_code != 0` | Tool output | `\u002Ffm detect test` |\n| \"Actually...\", \"No, that's wrong\" | User message | `\u002Ffm record correction` |\n| \"I meant...\", \"Not X, Y\" | User message | `\u002Ffm record correction` |\n| API 4xx\u002F5xx response | Tool output | `\u002Ffm detect api` |\n| \"error:\", \"failed\", \"Exception\" | Tool output | `\u002Ffm detect error` |\n| Deployment rollback | CI\u002FCD output | `\u002Ffm detect deployment` |\n| Database migration failed | Tool output | `\u002Ffm detect migration` |\n\n### Example: API Failure Detection\n\n```\n[DETECTED] api failure\nPattern: payment-api-timeout\nContext: Payment API returned 504 after 30s\nObservation: OBS-20260215-002\nR: 1 → 3\nStatus: Eligible for constraint (R≥3)\n```\n\n### Example: Deployment Failure Detection\n\n```\n[DETECTED] deployment failure\nPattern: staging-healthcheck-fail\nContext: Staging deployment failed health check on \u002Fapi\u002Fhealth\nObservation: OBS-20260215-003\nR: 1 → 2\nStatus: Monitoring (R\u003C3)\n```\n\n## Core Logic\n\n### R\u002FC\u002FD Counters\n\n| Counter | Meaning | Updated By |\n|---------|---------|------------|\n| **R** (Recurrence) | Auto-detected occurrences | `\u002Ffm detect`, `\u002Ffm record` |\n| **C** (Confirmations) | Human-verified true positives | Human via `\u002Ffm record C` |\n| **D** (Disconfirmations) | Human-verified false positives | Human via `\u002Ffm record D` |\n\n### Evidence Tiers\n\n| Tier | Criteria | Meaning |\n|------|----------|---------|\n| 弱 (weak) | N=1 | Single occurrence, may be noise |\n| 中 (emerging) | N=2 | Pattern emerging, monitor |\n| 強 (strong) | N≥3 | Established pattern, actionable |\n\n### Slug Taxonomy\n\nObservations are tagged with slugs: `git-*`, `test-*`, `workflow-*`, `security-*`, `docs-*`, `quality-*`\n\n### Metrics\n\n- `prevention_rate`: Failures prevented \u002F Total potential failures\n- `false_positive_rate`: D \u002F (C + D)\n\n## Output\n\n### \u002Ffm detect output\n\n```\n[DETECTED] test failure\nPattern: lint-before-commit\nObservation: OBS-20260215-001\nR: 1 → 2\nStatus: Monitoring (R\u003C3)\n```\n\n### \u002Ffm status output\n\n```\n=== Failure Memory Status ===\n\nEligible for constraint (R≥3 ∧ C≥2):\n- OBS-20260210-003: lint-before-commit (R=4, C=2, D=0)\n- OBS-20260212-007: test-before-push (R=3, C=3, D=1)\n\nRecent (last 30d): 12 observations\nPending review: 3 observations\n```\n\n## Configuration\n\nConfiguration is loaded from (in order of precedence):\n1. `.openclaw\u002Ffailure-memory.yaml` (OpenClaw standard)\n2. `.claude\u002Ffailure-memory.yaml` (Claude Code compatibility)\n3. Defaults (built-in)\n\n```yaml\n# .openclaw\u002Ffailure-memory.yaml\ndetection:\n  auto_detect: true          # Enable automatic failure detection\n  patterns:                   # Custom detection patterns\n    - \"FATAL:\"\n    - \"CRITICAL:\"\nthresholds:\n  eligibility_R: 3           # Recurrence threshold (default: 3)\n  eligibility_C: 2           # Confirmation threshold (default: 2)\n  false_positive_max: 0.2    # Max D\u002F(C+D) ratio (default: 0.2)\n```\n\n## Integration\n\n- **Layer**: Core\n- **Depends on**: context-verifier (for file change detection)\n- **Used by**: constraint-engine (for eligibility checks), governance (for state queries)\n\n## Failure Modes\n\n| Condition | Behavior |\n|-----------|----------|\n| Invalid sub-command | List available sub-commands |\n| Missing observation ID | Error with usage example |\n| No matches found | \"No observations match query\" |\n| Duplicate detection | Increment R counter, don't create new observation |\n\n## Next Steps\n\nAfter invoking this skill:\n\n| Condition | Action |\n|-----------|--------|\n| R incremented | Check eligibility: R≥3 ∧ C≥2 → notify user |\n| R≥3 ∧ C≥2 | Suggest `\u002Fce generate` for constraint |\n| Pattern recurring | Link with `See Also`, bump priority |\n| Always | Update `.learnings\u002FERRORS.md` or `.learnings\u002FLEARNINGS.md` |\n\n## Workspace Files\n\nThis skill reads\u002Fwrites:\n\n```\n.learnings\u002F\n├── ERRORS.md        # [ERR-YYYYMMDD-XXX] command failures\n├── LEARNINGS.md     # [LRN-YYYYMMDD-XXX] corrections, best practices\n└── observations\u002F    # Individual observation files\n    └── OBS-YYYYMMDD-XXX.md\n```\n\n## Security Considerations\n\n**What this skill accesses:**\n- Configuration files in `.openclaw\u002Ffailure-memory.yaml` and `.claude\u002Ffailure-memory.yaml`\n- Tool output and user messages in the current session (for failure detection)\n- Its own workspace directory `.learnings\u002F` (read\u002Fwrite)\n\n**What this skill does NOT access:**\n- Files outside declared workspace paths\n- System environment variables\n- Other projects or sessions (observations are workspace-local)\n- Network resources or external APIs\n\n**What this skill does NOT do:**\n- Send data to external services\n- Access \"across sessions and projects\" beyond the current workspace\n- Execute arbitrary code or run external commands\n\n**Data scope clarification:**\n- \"Failure detection\" scans tool output and user messages within the current agent session\n- Observations are stored in `.learnings\u002F` within the current workspace only\n- No cross-project or cross-session data access occurs\n- Pattern matching is local to the configured workspace\n\n**Detection trigger clarification:**\nThe \"Detection Triggers\" table describes patterns that indicate when this skill should be\ninvoked. The agent can auto-invoke `\u002Ffm detect` when these patterns are detected, or users\ncan invoke manually. This enables true agentic behavior — failures are captured automatically.\n\n**Provenance note:**\nThis skill is developed by Live Neon (https:\u002F\u002Fgithub.com\u002Flive-neon\u002Fskills) and published\nto ClawHub under the `leegitw` account. Both refer to the same maintainer.\n\n## Acceptance Criteria\n\n- [ ] `\u002Ffm detect` creates or updates observation with R++\n- [ ] `\u002Ffm record` supports R, C, D counter updates\n- [ ] `\u002Ffm search` finds observations by pattern, tag, or slug\n- [ ] `\u002Ffm classify` returns correct tier based on N count\n- [ ] `\u002Ffm status` shows eligible observations\n- [ ] `\u002Ffm refactor` merges\u002Fsplits observations correctly\n- [ ] `\u002Ffm converge` detects similar patterns (≥0.8 similarity)\n- [ ] Detection triggers work for test failures, user corrections, API errors\n- [ ] Workspace files follow self-improving-agent format\n\n---\n\n*Consolidated from 10 skills as part of agentic skills consolidation (2026-02-15).*\n",{"name":5,"tags":24,"alias":34,"layer":35,"author":36,"status":37,"license":15,"version":38,"homepage":39,"metadata":40,"repository":49,"description":7},[25,26,27,28,29,30,31,32,33],"agentic","memory","learning","self-improving","error-tracking","observability","patterns","adaptive","feedback","fm","core","Live Neon \u003Ccontact@liveneon.dev>","active","1.5.0","https:\u002F\u002Fgithub.com\u002Flive-neon\u002Fskills\u002Ftree\u002Fmain\u002Fagentic\u002Ffailure-memory",{"openclaw":41},{"requires":42},{"config":43,"workspace":46},[44,45],".openclaw\u002Ffailure-memory.yaml",".claude\u002Ffailure-memory.yaml",[47,48],".learnings\u002F",".learnings\u002Fobservations\u002F","leegitw\u002Ffailure-memory","master","4aa004da461d820f4ea5499e58eb8d196cf99016","community\u002Fclawhub\u002Ff\u002Ffailure-memory",0,"https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge","https:\u002F\u002Fskill-explorer-rho.vercel.app","https:\u002F\u002Fgithub.com\u002FLord1Egypt","Unbreakable. Unstoppable. Unmatched⚡.\r\n Speaker of machine tongues 🤖  | World-builder of decentralized dreams 🌐 | Defender of the digital realm🛡️.","2026-06-10 08:21:01",{"source":8,"skillName":5,"commands":60,"prompt":70,"zipAvailable":71},[61,64,67],{"tool":62,"command":63},"npx","npx skills add Lord1Egypt\u002Fawesome-skill-forge --skill failure-memory",{"tool":65,"command":66},"bunx","bunx skills add Lord1Egypt\u002Fawesome-skill-forge --skill failure-memory",{"tool":68,"command":69},"pnpm","pnpm dlx skills add Lord1Egypt\u002Fawesome-skill-forge --skill failure-memory","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fclawhub\u002Ff\u002Ffailure-memory\u002FSKILL.md",true,[],[74,81,88,95,102,109],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":19},"01M785WKJB99G3STR1NF9NRTJW","youtube-content","YouTube transcripts to summaries, threads, blogs.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fyoutube-content\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":19},"01M785WEFHB0G2S9YA6EPR3H0E","xurl","X\u002FTwitter via xurl CLI: post, search, DM, media, v2 API.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fxurl\u002FSKILL.md",[],[],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":19},"01M785W98EDN4EFJXJPMQEHCRC","touchdesigner-mcp","Control a running TouchDesigner instance via twozero MCP — create operators, set parameters, wire connections, execute Python, build real-time visuals. 36 native tools.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Ftouchdesigner-mcp\u002FSKILL.md",[],[],{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"publishedAt":19},"01M785W5S9FP3QBH2V191E025P","test-driven-development","TDD: enforce RED-GREEN-REFACTOR, tests before code.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Ftest-driven-development\u002FSKILL.md",[],[],{"skillNo":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":106,"categories":107,"keywords":108,"publishedAt":19},"01M785W2AS08NSSH9YATCV6FJB","teams-meeting-pipeline","Operate the Teams meeting summary pipeline via Hermes CLI — summarize meetings, inspect pipeline status, replay jobs, manage Microsoft Graph subscriptions.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fteams-meeting-pipeline\u002FSKILL.md",[],[],{"skillNo":110,"name":111,"nameZh":6,"description":112,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":113,"categories":114,"keywords":115,"publishedAt":19},"01M785VXKW4T34BTP1SCHW1R7F","systematic-debugging","4-phase root cause debugging: understand bugs before fixing.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fsystematic-debugging\u002FSKILL.md",[],[]]