[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77JPYAJ2DW5GP4EN995K9Y5":3,"skill-same:01M77JPYAJ2DW5GP4EN995K9Y5":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":51,"commitSha":52,"skillDirectory":53,"forksCount":54,"repositoryHtmlUrl":55,"repositoryHomepageUrl":56,"ownerHtmlUrl":57,"ownerBlogUrl":6,"ownerDescription":58,"updatedAt":59,"install":60,"resources":72},"01M77JPYAJ2DW5GP4EN995K9Y5","intent-guardian",null,"Watches your desktop activity, maintains a real-time task stack, detects when you forget what you were doing after interruptions, and gently reminds you. Your always-on focus companion.","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\u002Fi\u002Fintent-guardian\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: intent-guardian\nversion: 1.0.0\ndescription: Watches your desktop activity, maintains a real-time task stack, detects when you forget what you were doing after interruptions, and gently reminds you. Your always-on focus companion.\nauthor: huiling-one2x\ntags: [productivity, focus, memory, awareness, context-switch]\ntools: [shell, filesystem, memory, chat]\ntrigger: \"intent guardian|task stack|what was I doing|focus guard|track my tasks\"\nconfig:\n  poll_interval_seconds: 5\n  interruption_threshold_minutes: 5\n  reminder_cooldown_minutes: 3\n  max_stack_depth: 20\n  screen_capture_enabled: false\n  screen_capture_interval_seconds: 30\n  vision_model: \"\"\n  activitywatch_enabled: true\n  activitywatch_url: \"http:\u002F\u002Flocalhost:5600\"\n  notification_channel: \"system\"\n  working_hours_start: \"09:00\"\n  working_hours_end: \"18:00\"\n  excluded_apps: [\"Finder\", \"SystemPreferences\", \"loginwindow\"]\n---\n\n# Intent Guardian\n\n**Never lose your train of thought again.**\n\nIntent Guardian continuously monitors your desktop activity, builds a real-time understanding of what you're working on, and detects when you've been derailed by an interruption and forgotten your original task. When that happens, it nudges you back on track.\n\n## The Problem\n\nKnowledge workers are interrupted every 3 minutes on average. After an interruption, it takes ~23 minutes to return to the original task -- and often, you never return at all. Not because the task isn't important, but because you simply *forgot*.\n\nIntent Guardian solves this by maintaining a **task stack** -- a living model of what you're doing, what you were doing, and what got interrupted -- so you don't have to.\n\n## When to Use\n\n- You are a multi-tasker who frequently context-switches between apps and tasks\n- You often finish replying to a message and think \"wait, what was I doing?\"\n- You want an AI companion that understands your work rhythm, not just your commands\n- You want to build long-term awareness of your own focus patterns\n\n## Core Capabilities\n\n### 1. Real-Time Activity Sensing\n\nPolls the active window title and application name to build a continuous activity stream.\n\n**macOS:**\n```bash\nbash command:\"scripts\u002Fsense_activity.sh\"\n```\n\n**With ActivityWatch (richer data):**\n```bash\nbash command:\"scripts\u002Fsense_activitywatch.sh\"\n```\n\n**With Screen Capture (optional, requires vision model):**\n```bash\nbash command:\"scripts\u002Fsense_screen.sh\"\n```\n\n### 2. Task Stack Maintenance\n\nThe agent maintains a task stack in `memory\u002Fskills\u002Fintent-guardian\u002Ftask_stack.json`:\n\n```json\n{\n  \"stack\": [\n    {\n      \"id\": \"task_001\",\n      \"intent\": \"Writing product requirements doc, section 3\",\n      \"app\": \"Google Docs\",\n      \"window_title\": \"Product Requirements v2 - Google Docs\",\n      \"started_at\": \"2026-02-26T14:28:00\",\n      \"status\": \"suspended\",\n      \"suspended_at\": \"2026-02-26T14:31:00\",\n      \"suspended_by\": \"Slack notification from Li Si\",\n      \"completion_estimate\": 0.6\n    },\n    {\n      \"id\": \"task_002\",\n      \"intent\": \"Replying to Li Si about the API bug\",\n      \"app\": \"Slack\",\n      \"window_title\": \"Slack - #engineering\",\n      \"started_at\": \"2026-02-26T14:31:00\",\n      \"status\": \"completed\",\n      \"completed_at\": \"2026-02-26T14:35:00\"\n    },\n    {\n      \"id\": \"task_003\",\n      \"intent\": \"Looking up React useEffect cleanup pattern\",\n      \"app\": \"Chrome\",\n      \"window_title\": \"Stack Overflow - React useEffect cleanup\",\n      \"started_at\": \"2026-02-26T14:35:00\",\n      \"status\": \"active\"\n    }\n  ],\n  \"current_focus\": \"task_003\",\n  \"forgotten_candidates\": [\"task_001\"]\n}\n```\n\n### 3. Interruption & Forgetting Detection\n\nThe agent analyzes the task stack to detect potential forgetting:\n\n**Signals that suggest forgetting:**\n- A suspended task has not been resumed for longer than `interruption_threshold_minutes`\n- The user has moved through 2+ unrelated contexts since the suspension\n- The user shows \"wandering\" behavior: rapid app-switching without sustained focus\n- The suspended task had low completion estimate (was in the middle of something)\n\n**Signals that suggest deliberate abandonment (do NOT remind):**\n- The user explicitly closed the application associated with the task\n- The task was at a natural completion point (e.g., finished sending an email)\n- The user started a clearly intentional new deep-work session\n\n### 4. Gentle Reminders\n\nWhen forgetting is detected, the agent sends a non-intrusive reminder:\n\n**Simple reminder:**\n> \"You were working on the product requirements doc (section 3) about 25 minutes ago, before the Slack interruption. Want to go back to it?\"\n\n**Smart reminder (with context carried forward):**\n> \"You left the product requirements doc to look up the useEffect cleanup pattern for Li Si's bug. The answer is: return a cleanup function in useEffect. Ready to bring this back to the doc?\"\n\nThe second form is more powerful -- it doesn't just remind you what you forgot, it **completes the reason you left**, so you can return to your main task with the answer in hand.\n\n### 5. Long-Term Pattern Learning\n\nOver time, the agent builds a focus profile in `memory\u002Fskills\u002Fintent-guardian\u002Ffocus_profile.json`:\n\n```json\n{\n  \"user_id\": \"default\",\n  \"updated_at\": \"2026-02-26\",\n  \"patterns\": {\n    \"avg_focus_duration_minutes\": 12,\n    \"interruption_sources\": {\n      \"Slack\": { \"count\": 45, \"forget_rate\": 0.78 },\n      \"Mail\": { \"count\": 22, \"forget_rate\": 0.18 },\n      \"Chrome\": { \"count\": 31, \"forget_rate\": 0.42 }\n    },\n    \"peak_focus_hours\": [\"09:00-11:00\", \"14:00-16:00\"],\n    \"high_risk_transitions\": [\n      { \"from\": \"VSCode\", \"to\": \"Slack\", \"forget_rate\": 0.82 },\n      { \"from\": \"Google Docs\", \"to\": \"Chrome\", \"forget_rate\": 0.55 }\n    ],\n    \"reminder_effectiveness\": {\n      \"accepted\": 34,\n      \"dismissed\": 8,\n      \"ignored\": 5\n    }\n  }\n}\n```\n\nThis profile is used to personalize detection thresholds and reminder timing.\n\n## Architecture\n\n```\n Your Desktop\n      |\n      v\n [Sensing Layer]  ---- scripts\u002Fsense_activity.sh (window title, every N sec)\n      |                 scripts\u002Fsense_activitywatch.sh (ActivityWatch API)\n      |                 scripts\u002Fsense_screen.sh (optional screenshot + vision)\n      v\n [Activity Log]   ---- memory\u002Fskills\u002Fintent-guardian\u002Factivity_log.jsonl\n      |\n      v\n [Understanding]  ---- LLM analyzes activity stream on each Heartbeat:\n      |                 - Segments activities into logical tasks\n      |                 - Infers intent for each task\n      |                 - Detects interruptions and context switches\n      v\n [Task Stack]     ---- memory\u002Fskills\u002Fintent-guardian\u002Ftask_stack.json\n      |\n      v\n [Detection]      ---- Compares stack state against forgetting heuristics\n      |                 Consults focus_profile.json for personalized thresholds\n      v\n [Reminder]       ---- Sends reminder via configured notification channel\n      |                 Logs user response for feedback loop\n      v\n [Learning]       ---- Updates focus_profile.json with new patterns\n```\n\n## Heartbeat Integration\n\nAdd to your `HEARTBEAT.md`:\n\n```markdown\n## Intent Guardian Check\nEvery heartbeat, run the intent guardian cycle:\n1. Read latest activity from memory\u002Fskills\u002Fintent-guardian\u002Factivity_log.jsonl\n2. Update task_stack.json with new activities\n3. Check for forgotten tasks (suspended > threshold, not resumed)\n4. If forgotten task detected, send reminder\n5. Log any reminder responses to focus_profile.json\n```\n\n## Cron Integration\n\nAdd a daily focus report:\n\n```bash\nopenclaw cron add --name \"intent-guardian-daily\" --schedule \"0 18 * * *\" \\\n  --prompt \"Generate my daily focus report using intent-guardian data\"\n```\n\n## Setup\n\n### Minimal Setup (macOS, no dependencies)\n\n1. Install the skill:\n```bash\nnpx playbooks add skill openclaw\u002Fskills --skill intent-guardian\n```\n\n2. The skill uses native macOS commands (`osascript`) to get the active window.\nNo additional software required.\n\n3. Add the Heartbeat integration above to your `HEARTBEAT.md`.\n\n### Enhanced Setup (with ActivityWatch)\n\n1. Install [ActivityWatch](https:\u002F\u002Factivitywatch.net\u002F) for richer window-level tracking.\n2. Set `activitywatch_enabled: true` in skill config.\n3. ActivityWatch provides detailed per-window timelines including URLs and document titles.\n\n### Full Setup (with Screen Capture)\n\n1. Set `screen_capture_enabled: true` and configure `vision_model`.\n2. Requires a vision-capable model (Claude, Gemini, Qwen3-VL).\n3. Screenshots are captured locally, analyzed locally or via API, and **never stored permanently**.\n\n## Privacy & Security\n\n- **All data stays local.** Activity logs, task stacks, and focus profiles are stored as local files in your OpenClaw memory directory.\n- **No raw screenshots are persisted.** If screen capture is enabled, frames are analyzed and immediately discarded. Only the semantic summary is kept.\n- **Excluded apps are respected.** Configure `excluded_apps` to prevent tracking specific applications.\n- **Working hours enforced.** Sensing only runs during configured `working_hours_start` to `working_hours_end`.\n- **You own the data.** All files are human-readable JSON\u002FJSONL. Review, edit, or delete at any time.\n\n## Configuration Reference\n\n| Key | Type | Default | Description |\n|-----|------|---------|-------------|\n| `poll_interval_seconds` | int | 5 | How often to check the active window |\n| `interruption_threshold_minutes` | int | 5 | Minutes before a suspended task is flagged as potentially forgotten |\n| `reminder_cooldown_minutes` | int | 3 | Minimum time between reminders to avoid nagging |\n| `max_stack_depth` | int | 20 | Maximum tasks to track in the stack |\n| `screen_capture_enabled` | bool | false | Enable periodic screenshot analysis |\n| `screen_capture_interval_seconds` | int | 30 | Interval for screenshots (if enabled) |\n| `vision_model` | string | \"\" | Model for screenshot analysis (e.g., \"gemini\", \"claude\") |\n| `activitywatch_enabled` | bool | true | Use ActivityWatch for richer activity data |\n| `activitywatch_url` | string | \"http:\u002F\u002Flocalhost:5600\" | ActivityWatch server URL |\n| `notification_channel` | string | \"system\" | Where to send reminders (\"system\", \"telegram\", \"slack\", etc.) |\n| `working_hours_start` | string | \"09:00\" | Start of active tracking window |\n| `working_hours_end` | string | \"18:00\" | End of active tracking window |\n| `excluded_apps` | list | [\"Finder\", \"SystemPreferences\", \"loginwindow\"] | Apps to ignore |\n\n## Example Interactions\n\n**User:** \"What was I doing before I got sidetracked?\"\n**Agent reads task_stack.json, responds:**\n> \"Before the Slack interruption at 14:31, you were writing section 3 of the product requirements doc in Google Docs. You were about 60% through. Want to jump back?\"\n\n**User:** \"Show me my task stack\"\n**Agent responds with current stack visualization:**\n> ```\n> Task Stack (3 items):\n> [ACTIVE]     Looking up React useEffect cleanup (Chrome) - 17 min\n> [COMPLETED]  Replying to Li Si about API bug (Slack) - 4 min\n> [SUSPENDED]  Writing product requirements doc, section 3 (Google Docs) - 25 min ago  !!\n> ```\n\n**User:** \"How's my focus today?\"\n**Agent reads activity log and focus profile:**\n> \"Today you've had 6 deep work sessions averaging 18 minutes each. You were interrupted 11 times, mostly by Slack (7 times). You forgot to return to your original task 4 times -- I caught 3 of those. Your peak focus was 09:30-10:45.\"\n\n**Proactive (via Heartbeat):**\n> \"Heads up -- you've been away from the quarterly report (Excel) for 40 minutes since that phone call. It's due tomorrow. Want to wrap up the current task and go back to it?\"\n\n## Integration with Other Skills\n\nIntent Guardian works well alongside these existing skills:\n\n| Skill | Integration |\n|-------|-------------|\n| `personal-analytics` | Feed focus_profile data into analytics for richer weekly reports |\n| `daily-review` | Include task completion stats and interruption counts in daily reviews |\n| `deepwork-tracker` | Auto-start deepwork timer when sustained focus is detected |\n| `screen-monitor` | Use screen_analyze for richer context when vision model is configured |\n| `rememberall` | Convert suspended tasks into time-based reminders as fallback |\n| `get-focus-mode` | Suppress reminders when macOS Focus mode is active |\n\n## Roadmap\n\n- [ ] Cross-device sync (remind on phone about tasks left on laptop)\n- [ ] Team mode (with consent: \"Zhang San is waiting for your review, 2 days now\")\n- [ ] Proactive task delegation (\"I can draft that email reply while you focus on the doc\")\n- [ ] Calendar-aware urgency (\"The quarterly report meeting is in 2 hours, and you're only 60% done\")\n- [ ] Intent hierarchy (L1-L4 goal tracking, not just immediate tasks)\n\n## License\n\nMIT\n","# Intent Guardian\n\n**Never lose your train of thought again.**\n\nIntent Guardian continuously monitors your desktop activity, builds a real-time understanding of what you're working on, and detects when you've been derailed by an interruption and forgotten your original task. When that happens, it nudges you back on track.\n\n## The Problem\n\nKnowledge workers are interrupted every 3 minutes on average. After an interruption, it takes ~23 minutes to return to the original task -- and often, you never return at all. Not because the task isn't important, but because you simply *forgot*.\n\nIntent Guardian solves this by maintaining a **task stack** -- a living model of what you're doing, what you were doing, and what got interrupted -- so you don't have to.\n\n## When to Use\n\n- You are a multi-tasker who frequently context-switches between apps and tasks\n- You often finish replying to a message and think \"wait, what was I doing?\"\n- You want an AI companion that understands your work rhythm, not just your commands\n- You want to build long-term awareness of your own focus patterns\n\n## Core Capabilities\n\n### 1. Real-Time Activity Sensing\n\nPolls the active window title and application name to build a continuous activity stream.\n\n**macOS:**\n```bash\nbash command:\"scripts\u002Fsense_activity.sh\"\n```\n\n**With ActivityWatch (richer data):**\n```bash\nbash command:\"scripts\u002Fsense_activitywatch.sh\"\n```\n\n**With Screen Capture (optional, requires vision model):**\n```bash\nbash command:\"scripts\u002Fsense_screen.sh\"\n```\n\n### 2. Task Stack Maintenance\n\nThe agent maintains a task stack in `memory\u002Fskills\u002Fintent-guardian\u002Ftask_stack.json`:\n\n```json\n{\n  \"stack\": [\n    {\n      \"id\": \"task_001\",\n      \"intent\": \"Writing product requirements doc, section 3\",\n      \"app\": \"Google Docs\",\n      \"window_title\": \"Product Requirements v2 - Google Docs\",\n      \"started_at\": \"2026-02-26T14:28:00\",\n      \"status\": \"suspended\",\n      \"suspended_at\": \"2026-02-26T14:31:00\",\n      \"suspended_by\": \"Slack notification from Li Si\",\n      \"completion_estimate\": 0.6\n    },\n    {\n      \"id\": \"task_002\",\n      \"intent\": \"Replying to Li Si about the API bug\",\n      \"app\": \"Slack\",\n      \"window_title\": \"Slack - #engineering\",\n      \"started_at\": \"2026-02-26T14:31:00\",\n      \"status\": \"completed\",\n      \"completed_at\": \"2026-02-26T14:35:00\"\n    },\n    {\n      \"id\": \"task_003\",\n      \"intent\": \"Looking up React useEffect cleanup pattern\",\n      \"app\": \"Chrome\",\n      \"window_title\": \"Stack Overflow - React useEffect cleanup\",\n      \"started_at\": \"2026-02-26T14:35:00\",\n      \"status\": \"active\"\n    }\n  ],\n  \"current_focus\": \"task_003\",\n  \"forgotten_candidates\": [\"task_001\"]\n}\n```\n\n### 3. Interruption & Forgetting Detection\n\nThe agent analyzes the task stack to detect potential forgetting:\n\n**Signals that suggest forgetting:**\n- A suspended task has not been resumed for longer than `interruption_threshold_minutes`\n- The user has moved through 2+ unrelated contexts since the suspension\n- The user shows \"wandering\" behavior: rapid app-switching without sustained focus\n- The suspended task had low completion estimate (was in the middle of something)\n\n**Signals that suggest deliberate abandonment (do NOT remind):**\n- The user explicitly closed the application associated with the task\n- The task was at a natural completion point (e.g., finished sending an email)\n- The user started a clearly intentional new deep-work session\n\n### 4. Gentle Reminders\n\nWhen forgetting is detected, the agent sends a non-intrusive reminder:\n\n**Simple reminder:**\n> \"You were working on the product requirements doc (section 3) about 25 minutes ago, before the Slack interruption. Want to go back to it?\"\n\n**Smart reminder (with context carried forward):**\n> \"You left the product requirements doc to look up the useEffect cleanup pattern for Li Si's bug. The answer is: return a cleanup function in useEffect. Ready to bring this back to the doc?\"\n\nThe second form is more powerful -- it doesn't just remind you what you forgot, it **completes the reason you left**, so you can return to your main task with the answer in hand.\n\n### 5. Long-Term Pattern Learning\n\nOver time, the agent builds a focus profile in `memory\u002Fskills\u002Fintent-guardian\u002Ffocus_profile.json`:\n\n```json\n{\n  \"user_id\": \"default\",\n  \"updated_at\": \"2026-02-26\",\n  \"patterns\": {\n    \"avg_focus_duration_minutes\": 12,\n    \"interruption_sources\": {\n      \"Slack\": { \"count\": 45, \"forget_rate\": 0.78 },\n      \"Mail\": { \"count\": 22, \"forget_rate\": 0.18 },\n      \"Chrome\": { \"count\": 31, \"forget_rate\": 0.42 }\n    },\n    \"peak_focus_hours\": [\"09:00-11:00\", \"14:00-16:00\"],\n    \"high_risk_transitions\": [\n      { \"from\": \"VSCode\", \"to\": \"Slack\", \"forget_rate\": 0.82 },\n      { \"from\": \"Google Docs\", \"to\": \"Chrome\", \"forget_rate\": 0.55 }\n    ],\n    \"reminder_effectiveness\": {\n      \"accepted\": 34,\n      \"dismissed\": 8,\n      \"ignored\": 5\n    }\n  }\n}\n```\n\nThis profile is used to personalize detection thresholds and reminder timing.\n\n## Architecture\n\n```\n Your Desktop\n      |\n      v\n [Sensing Layer]  ---- scripts\u002Fsense_activity.sh (window title, every N sec)\n      |                 scripts\u002Fsense_activitywatch.sh (ActivityWatch API)\n      |                 scripts\u002Fsense_screen.sh (optional screenshot + vision)\n      v\n [Activity Log]   ---- memory\u002Fskills\u002Fintent-guardian\u002Factivity_log.jsonl\n      |\n      v\n [Understanding]  ---- LLM analyzes activity stream on each Heartbeat:\n      |                 - Segments activities into logical tasks\n      |                 - Infers intent for each task\n      |                 - Detects interruptions and context switches\n      v\n [Task Stack]     ---- memory\u002Fskills\u002Fintent-guardian\u002Ftask_stack.json\n      |\n      v\n [Detection]      ---- Compares stack state against forgetting heuristics\n      |                 Consults focus_profile.json for personalized thresholds\n      v\n [Reminder]       ---- Sends reminder via configured notification channel\n      |                 Logs user response for feedback loop\n      v\n [Learning]       ---- Updates focus_profile.json with new patterns\n```\n\n## Heartbeat Integration\n\nAdd to your `HEARTBEAT.md`:\n\n```markdown\n## Intent Guardian Check\nEvery heartbeat, run the intent guardian cycle:\n1. Read latest activity from memory\u002Fskills\u002Fintent-guardian\u002Factivity_log.jsonl\n2. Update task_stack.json with new activities\n3. Check for forgotten tasks (suspended > threshold, not resumed)\n4. If forgotten task detected, send reminder\n5. Log any reminder responses to focus_profile.json\n```\n\n## Cron Integration\n\nAdd a daily focus report:\n\n```bash\nopenclaw cron add --name \"intent-guardian-daily\" --schedule \"0 18 * * *\" \\\n  --prompt \"Generate my daily focus report using intent-guardian data\"\n```\n\n## Setup\n\n### Minimal Setup (macOS, no dependencies)\n\n1. Install the skill:\n```bash\nnpx playbooks add skill openclaw\u002Fskills --skill intent-guardian\n```\n\n2. The skill uses native macOS commands (`osascript`) to get the active window.\nNo additional software required.\n\n3. Add the Heartbeat integration above to your `HEARTBEAT.md`.\n\n### Enhanced Setup (with ActivityWatch)\n\n1. Install [ActivityWatch](https:\u002F\u002Factivitywatch.net\u002F) for richer window-level tracking.\n2. Set `activitywatch_enabled: true` in skill config.\n3. ActivityWatch provides detailed per-window timelines including URLs and document titles.\n\n### Full Setup (with Screen Capture)\n\n1. Set `screen_capture_enabled: true` and configure `vision_model`.\n2. Requires a vision-capable model (Claude, Gemini, Qwen3-VL).\n3. Screenshots are captured locally, analyzed locally or via API, and **never stored permanently**.\n\n## Privacy & Security\n\n- **All data stays local.** Activity logs, task stacks, and focus profiles are stored as local files in your OpenClaw memory directory.\n- **No raw screenshots are persisted.** If screen capture is enabled, frames are analyzed and immediately discarded. Only the semantic summary is kept.\n- **Excluded apps are respected.** Configure `excluded_apps` to prevent tracking specific applications.\n- **Working hours enforced.** Sensing only runs during configured `working_hours_start` to `working_hours_end`.\n- **You own the data.** All files are human-readable JSON\u002FJSONL. Review, edit, or delete at any time.\n\n## Configuration Reference\n\n| Key | Type | Default | Description |\n|-----|------|---------|-------------|\n| `poll_interval_seconds` | int | 5 | How often to check the active window |\n| `interruption_threshold_minutes` | int | 5 | Minutes before a suspended task is flagged as potentially forgotten |\n| `reminder_cooldown_minutes` | int | 3 | Minimum time between reminders to avoid nagging |\n| `max_stack_depth` | int | 20 | Maximum tasks to track in the stack |\n| `screen_capture_enabled` | bool | false | Enable periodic screenshot analysis |\n| `screen_capture_interval_seconds` | int | 30 | Interval for screenshots (if enabled) |\n| `vision_model` | string | \"\" | Model for screenshot analysis (e.g., \"gemini\", \"claude\") |\n| `activitywatch_enabled` | bool | true | Use ActivityWatch for richer activity data |\n| `activitywatch_url` | string | \"http:\u002F\u002Flocalhost:5600\" | ActivityWatch server URL |\n| `notification_channel` | string | \"system\" | Where to send reminders (\"system\", \"telegram\", \"slack\", etc.) |\n| `working_hours_start` | string | \"09:00\" | Start of active tracking window |\n| `working_hours_end` | string | \"18:00\" | End of active tracking window |\n| `excluded_apps` | list | [\"Finder\", \"SystemPreferences\", \"loginwindow\"] | Apps to ignore |\n\n## Example Interactions\n\n**User:** \"What was I doing before I got sidetracked?\"\n**Agent reads task_stack.json, responds:**\n> \"Before the Slack interruption at 14:31, you were writing section 3 of the product requirements doc in Google Docs. You were about 60% through. Want to jump back?\"\n\n**User:** \"Show me my task stack\"\n**Agent responds with current stack visualization:**\n> ```\n> Task Stack (3 items):\n> [ACTIVE]     Looking up React useEffect cleanup (Chrome) - 17 min\n> [COMPLETED]  Replying to Li Si about API bug (Slack) - 4 min\n> [SUSPENDED]  Writing product requirements doc, section 3 (Google Docs) - 25 min ago  !!\n> ```\n\n**User:** \"How's my focus today?\"\n**Agent reads activity log and focus profile:**\n> \"Today you've had 6 deep work sessions averaging 18 minutes each. You were interrupted 11 times, mostly by Slack (7 times). You forgot to return to your original task 4 times -- I caught 3 of those. Your peak focus was 09:30-10:45.\"\n\n**Proactive (via Heartbeat):**\n> \"Heads up -- you've been away from the quarterly report (Excel) for 40 minutes since that phone call. It's due tomorrow. Want to wrap up the current task and go back to it?\"\n\n## Integration with Other Skills\n\nIntent Guardian works well alongside these existing skills:\n\n| Skill | Integration |\n|-------|-------------|\n| `personal-analytics` | Feed focus_profile data into analytics for richer weekly reports |\n| `daily-review` | Include task completion stats and interruption counts in daily reviews |\n| `deepwork-tracker` | Auto-start deepwork timer when sustained focus is detected |\n| `screen-monitor` | Use screen_analyze for richer context when vision model is configured |\n| `rememberall` | Convert suspended tasks into time-based reminders as fallback |\n| `get-focus-mode` | Suppress reminders when macOS Focus mode is active |\n\n## Roadmap\n\n- [ ] Cross-device sync (remind on phone about tasks left on laptop)\n- [ ] Team mode (with consent: \"Zhang San is waiting for your review, 2 days now\")\n- [ ] Proactive task delegation (\"I can draft that email reply while you focus on the doc\")\n- [ ] Calendar-aware urgency (\"The quarterly report meeting is in 2 hours, and you're only 60% done\")\n- [ ] Intent hierarchy (L1-L4 goal tracking, not just immediate tasks)\n\n## License\n\nMIT\n",{"name":5,"tags":24,"tools":30,"author":34,"config":35,"trigger":49,"version":50,"description":7},[25,26,27,28,29],"productivity","focus","memory","awareness","context-switch",[31,32,27,33],"shell","filesystem","chat","huiling-one2x",{"vision_model":36,"excluded_apps":37,"max_stack_depth":41,"activitywatch_url":42,"working_hours_end":43,"working_hours_start":44,"notification_channel":45,"activitywatch_enabled":46,"poll_interval_seconds":47,"screen_capture_enabled":20,"reminder_cooldown_minutes":14,"interruption_threshold_minutes":47,"screen_capture_interval_seconds":48},"",[38,39,40],"Finder","SystemPreferences","loginwindow",20,"http:\u002F\u002Flocalhost:5600","18:00","09:00","system",true,5,30,"intent guardian|task stack|what was I doing|focus guard|track my tasks","1.0.0","master","4aa004da461d820f4ea5499e58eb8d196cf99016","community\u002Fclawhub\u002Fi\u002Fintent-guardian",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":61,"prompt":71,"zipAvailable":46},[62,65,68],{"tool":63,"command":64},"npx","npx skills add Lord1Egypt\u002Fawesome-skill-forge --skill intent-guardian",{"tool":66,"command":67},"bunx","bunx skills add Lord1Egypt\u002Fawesome-skill-forge --skill intent-guardian",{"tool":69,"command":70},"pnpm","pnpm dlx skills add Lord1Egypt\u002Fawesome-skill-forge --skill intent-guardian","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fclawhub\u002Fi\u002Fintent-guardian\u002FSKILL.md",[],[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",[],[]]