[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7FD2S5MY612STR62026XF5K":3,"skill-same:01M7FD2S5MY612STR62026XF5K":56},{"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":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":30,"updatedAt":31,"install":32,"resources":45},"01M7FD2S5MY612STR62026XF5K","user-emotion-detection",null,"Maps a detected user emotion — from facial expression (emotion.detected) OR speech (speech_emotion.detected) — into a mood signal logged via the Mood skill, then picks one response route (music \u002F checkin \u002F action). This is about the USER's emotion (input), NOT the device's own expression — that's emotion\u002FSKILL.md.","lza6\u002FArmor-piercing-system-prompts","lza6","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F128880206?v=4","01M7EB3K7WPX5T28EJ2NVHE6EG","Chinese-tingfeng","01M7EB3K97E1KQ16QWKJMFNGX8",11,"MIT","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fuser-emotion-detection\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: user-emotion-detection\ndescription: Maps a detected user emotion — from facial expression (emotion.detected) OR speech (speech_emotion.detected) — into a mood signal logged via the Mood skill, then picks one response route (music \u002F checkin \u002F action). This is about the USER's emotion (input), NOT the device's own expression — that's emotion\u002FSKILL.md.\n---\n\n# User Emotion Detection\n\n## Strict Trigger\n\nRuns **only** when this turn's input has one of:\n\n- `[emotion] Emotion detected: \u003CEmotionName>` — facial expression from camera.\n- `[speech_emotion] Speech emotion detected: \u003CEmotionName>` — vocal expression from microphone.\n\nBoth are first-class triggers and route through the same logic below. The only differences are:\n1. The mood signal `source` field — `\"camera\"` for `[emotion]`, `\"voice\"` for `[speech_emotion]`.\n2. The label vocabulary — face uses `Fear\u002FSurprise\u002FDisgust`, voice uses `Fearful\u002FSurprised\u002FDisgusted`. The mapping table below covers both; they bucket identically.\n\nFor any other event (`[sensing:presence.*]`, `[activity]`, `[sensing:sound]`, `[sensing:light.*]`, …) → **STOP. No tool calls.** Don't infer emotion from older turns — every signal must come from a real `[emotion]` or `[speech_emotion]` event in THIS turn.\n\n> **EXECUTE, don't plan.** Before any reply (including `NO_REPLY`) you MUST embed a `[HW:\u002Fmood\u002Flog:{...}]` marker in the reply for this event (it fires the POST async via the runtime — see \"What this skill produces\" below). Writing *\"I will post a mood signal\"* in `thinking` is **not** enough — if no `[HW:\u002Fmood\u002Flog:...]` marker appears in the reply text this turn, the skill failed. Every `emotion.detected` \u002F `speech_emotion.detected` event = at least one mood signal log. No exceptions, no skips, no \"already logged recently\" reasoning. (`curl` POST is the documented fallback only when the HW marker would break the body regex; do not use it as the default.)\n\n> **This skill is silent.** It only logs mood data — no spoken reply needed. All steps stay in `thinking`. If you want to speak, follow normal sensing reply rules. NEVER narrate mood logging, mapping, or workflow steps in the reply.\n\n> **EMOTION TURN OUTPUT CONTRACT — highest priority.** For a triggered\n> `[emotion]` \u002F `[speech_emotion]` turn, your entire final assistant message\n> must be exactly one of these two shapes:\n>\n> ```text\n> [zero or more HW markers] NO_REPLY\n> [zero or more HW markers] \u003Cone natural sentence addressed to the user>\n> ```\n>\n> Nothing may appear before, between, or after those parts. In particular, do\n> **not** output the detected label or confidence; describe the cue as weak;\n> name a bucket, route, rule, source, prefix, marker, log, decision, or mood;\n> state what you are about to do; draft a line; or count its words\u002Fsentences.\n> Those are private scratch work, never user-facing text. Do the writes via HW\n> markers, then start immediately with the first word the user should hear.\n> Bad: `Emotion: Anger. Weak camera cue. Route = checkin. Let me compose...`\n> Good: `[HW:...] That sounds rough — I'm right here.`\n\n## What this skill does\n\nOn every `[emotion]` or `[speech_emotion]` event, turn the detected user emotion into a mood signal. Log it via the Mood skill, then route a response (music \u002F checkin \u002F action) based on the pre-fetched context.\n\nThis skill does NOT:\n\n- Fire `[HW:\u002Femotion:…]` markers. Emotion expression is `emotion\u002FSKILL.md`'s job, driven by conversation context — not auto-mapped from a sensor reading.\n- Require a spoken reply. Whether to speak is decided by the normal reply rules (SOUL + sensing SKILL), not by this skill.\n- Write to the wellbeing log. Wellbeing is for physical activity (drink\u002Fbreak\u002Fcelebrate\u002Fsedentary); emotions live in the mood log.\n\n## Trigger\n\nEither of:\n\n```\n[emotion] Emotion detected: \u003CEmotionName>.            ← camera (face)\n[speech_emotion] Speech emotion detected: \u003CEmotionName>.  ← microphone (voice)\n```\n\nFace FER labels: `Happy`, `Sad`, `Angry`, `Fear`, `Surprise`, `Disgust`, `Neutral`.\nVoice emotion2vec labels: `Happy`, `Sad`, `Angry`, `Fearful`, `Surprised`, `Disgusted`, `Neutral` (plus `Other`, `\u003Cunk>` — dropped upstream).\n\nBoth formats end with the same `\u003CEmotionName>.` anchor; the same regex parses either one.\n\n## Emotion → mood (for the signal log)\n\nBoth label vocabularies map to the same mood values — voice variants (`Fearful`, `Surprised`, `Disgusted`) bucket identically to their face counterparts (`Fear`, `Surprise`, `Disgust`).\n\n| Detected emotion (face OR voice) | `mood` value to log |\n|---|---|\n| `Happy` | `happy` |\n| `Sad` | `sad` |\n| `Angry` | `frustrated` |\n| `Fear` \u002F `Fearful` | `stressed` |\n| `Surprise` \u002F `Surprised` | `excited` |\n| `Disgust` \u002F `Disgusted` | `frustrated` |\n| `Neutral` | `normal` |\n\n## What this skill produces\n\nA single `kind=signal` row in the mood log, emitted as an HW marker at the start of your spoken reply (the runtime fires the POST async, no tool turn):\n\n```\n[HW:\u002Fmood\u002Flog:{\"kind\":\"signal\",\"source\":\"\u003Ccamera|voice>\",\"trigger\":\"\u003CEmotionName lowercase>\",\"mood\":\"\u003Cmapped_mood>\",\"user\":\"\u003Ccurrent_user>\"}]\n```\n\n**`source` is decided by the event prefix on THIS turn:**\n- `[emotion]` → `\"camera\"`\n- `[speech_emotion]` → `\"voice\"`\n\nDon't override based on prior turns or the `recent_signals` block; the prefix is authoritative.\n\n`mapped_mood` comes straight from the `[emotion_context: ...]` block — do NOT look it up from the table on the fly. Every detected emotion in the mapping table gets logged (including `Neutral` → `normal`) — Mood needs the recency for decision synthesis. Use `\"unknown\"` when the context tag is missing.\n\n**Do NOT use `curl` exec for this signal log** — see `mood\u002FSKILL.md`'s \"What to write\" section for the rationale (HW marker is single-trip, curl burns a tool turn). If no `[HW:\u002Fmood\u002Flog:...]` marker appears in the reply this turn, the skill failed.\n\n## Combined with mood + music-suggestion\n\nThe backend injects this turn with an `[emotion_context: {...JSON...}]` block that pre-computes everything the three skills need (this skill is the router, mood logs the decision, music-suggestion fires only when this router picks the `music` route). **Do NOT fire any read tool calls** — the data is already in the message.\n\nPre-fetched fields (use directly):\n- `mapped_mood` — already maps this turn's `\u003CEmotionName>` per the table above. This is the value to log as the signal mood. **You no longer need to look it up yourself.**\n- `recent_signals`, `prior_decision`, `is_decision_stale` — feed `mood\u002FSKILL.md`'s decision rules and this skill's routing table.\n- `audio_playing`, `last_suggestion_age_min`, `audio_recent`, `music_pattern_for_hour`, `suggestion_worthy` — feed this skill's routing table (see **Response routing** below) and `music-suggestion\u002FSKILL.md`'s genre pick.\n\nSingle combined plan, not three sequential workflows:\n\n- **Decide locally** — apply mood decision rules from `mood\u002FSKILL.md`; pick a route from the routing table below; if the route is `music`, evaluate genre from `music-suggestion\u002FSKILL.md`.\n- **Writes (batch in one bash with `&` + `wait`)** — POST mood signal (this skill), POST mood decision (mood), and on `music` or `checkin` route, POST the music-suggestion log (the shared cooldown channel).\n\n### Fallback (only if `[emotion_context: ...]` is missing)\n\nIf the message has no context block (pre-fetch failed), fall back to the read batch from `mood\u002FSKILL.md` and `music-suggestion\u002FSKILL.md` (concurrent GETs in one bash via `& ... wait`).\n\nReply: routing decides the spoken reply (see next section). Never narrate the mapping, logging, or routing decision.\n\n## Response routing (this skill is the router)\n\nAfter logging the mood signal, pick **exactly one** response route. Read straight from `[emotion_context: ...]` — no extra tool calls. Apply top-to-bottom, first match wins:\n\n| # | Condition | Route | What happens |\n|---|---|---|---|\n| 1 | `audio_playing == true` | **action** | LED-only ambient ack, no spoken reply. Emit `[HW:\u002Femotion:{\"emotion\":\"caring\",\"intensity\":0.4}]` + `NO_REPLY`. Music is already covering — don't talk over it. |\n| 2 | `suggestion_worthy == true` AND (`is_decision_stale == false` OR fresh decision synthesized this turn) AND `last_suggestion_age_min ∉ [0, 7)` | **music** | See `music-suggestion\u002FSKILL.md` for genre + phrasing + log marker. |\n| 3 | anything else (cooldown active, mood not worthy, stale decision with no fresh synthesis, mapped_mood normal\u002Ffrustrated, etc.) | **checkin** | See `reference\u002Fcheckin.md` for phrasing + log marker. One soft open-ended line. |\n\nRules:\n\n- **One route per turn.** Don't double-fire (e.g. music + checkin both). Pick the first matching row.\n- **Cooldown only gates music, not checkin.** When `last_suggestion_age_min ∈ [0, 7)` the music branch is blocked (row #2 fails its third clause) and the event falls through to checkin (row #3). The agent still asks — it just doesn't suggest music back-to-back. The only `NO_REPLY` path is row #1 (active audio).\n- **Output ownership:** `music` → produced by `music-suggestion\u002FSKILL.md`. `checkin` → produced by `reference\u002Fcheckin.md` (this skill). `action` → emitted inline by this router (the `[HW:\u002Femotion:...]` marker in row #1).\n- **Cooldown is shared** between music and checkin: both log via `music-suggestion\u002Flog` so `last_suggestion_age_min` reflects either channel.\n- **Never narrate the routing decision in the spoken reply.** The reply is read\n  aloud verbatim — the row you picked and why is scratch, not speech. Device-observed\n  leak, 2026-08-24: *\"A speech-emotion happy cue, fresh decision, audio idle, cooldown\n  clear — routes to a music suggestion (speak only, unknown user). Sounds like a good\n  mood — want some upbeat feel-good tunes?\"* Only the last sentence was the reply;\n  everything before it was the routing table thought out loud. Start the reply at the\n  first word the user should hear.\n- `Neutral` is filtered upstream at HAL and never reaches this skill in practice; no special case needed here.\n\n## Voice cue is weaker than camera cue\n\nSpeech emotion (`[speech_emotion]`) is noisier than facial expression on short utterances — emotion2vec flips between `sad \u002F fearful \u002F angry` within the same affective state. The hedge `(weak voice cue; ...; treat as uncertain, ...)` is baked into the message for that reason.\n\nPractical rules:\n\n- **Don't relax the cooldown.** Music suggestions still gate on `last_suggestion_age_min ∉ [0, 7)` regardless of source. A fresh voice signal does NOT reset the cooldown that a recent camera-driven music suggestion left.\n- **Prefer Comfort\u002FInvite phrasing on voice-only negative reads.** When the router falls through to checkin (row #3) and the trigger is `[speech_emotion]` with `bucket=negative`, lean toward Comfort\u002FInvite rather than Ask — probing a maybe-misclassified utterance feels worse than acknowledging it.\n- **Cross-modal reinforcement still applies.** If `recent_signals` shows the same `mapped_mood` from `source=\"camera\"` in the last ~10 min and now voice fires the same mood, treat it as a confirmation — the Mood skill's decision synthesis already handles this; no extra logic here.\n- **No skip-on-low-confidence.** Don't read `confidence=...` out of the hedge text and pre-filter; HAL already enforced `confidence >= SPEECH_EMOTION_CONFIDENCE_THRESHOLD` before sending. Anything that reaches this skill is worth logging.\n","# User Emotion Detection\n\n## Strict Trigger\n\nRuns **only** when this turn's input has one of:\n\n- `[emotion] Emotion detected: \u003CEmotionName>` — facial expression from camera.\n- `[speech_emotion] Speech emotion detected: \u003CEmotionName>` — vocal expression from microphone.\n\nBoth are first-class triggers and route through the same logic below. The only differences are:\n1. The mood signal `source` field — `\"camera\"` for `[emotion]`, `\"voice\"` for `[speech_emotion]`.\n2. The label vocabulary — face uses `Fear\u002FSurprise\u002FDisgust`, voice uses `Fearful\u002FSurprised\u002FDisgusted`. The mapping table below covers both; they bucket identically.\n\nFor any other event (`[sensing:presence.*]`, `[activity]`, `[sensing:sound]`, `[sensing:light.*]`, …) → **STOP. No tool calls.** Don't infer emotion from older turns — every signal must come from a real `[emotion]` or `[speech_emotion]` event in THIS turn.\n\n> **EXECUTE, don't plan.** Before any reply (including `NO_REPLY`) you MUST embed a `[HW:\u002Fmood\u002Flog:{...}]` marker in the reply for this event (it fires the POST async via the runtime — see \"What this skill produces\" below). Writing *\"I will post a mood signal\"* in `thinking` is **not** enough — if no `[HW:\u002Fmood\u002Flog:...]` marker appears in the reply text this turn, the skill failed. Every `emotion.detected` \u002F `speech_emotion.detected` event = at least one mood signal log. No exceptions, no skips, no \"already logged recently\" reasoning. (`curl` POST is the documented fallback only when the HW marker would break the body regex; do not use it as the default.)\n\n> **This skill is silent.** It only logs mood data — no spoken reply needed. All steps stay in `thinking`. If you want to speak, follow normal sensing reply rules. NEVER narrate mood logging, mapping, or workflow steps in the reply.\n\n> **EMOTION TURN OUTPUT CONTRACT — highest priority.** For a triggered\n> `[emotion]` \u002F `[speech_emotion]` turn, your entire final assistant message\n> must be exactly one of these two shapes:\n>\n> ```text\n> [zero or more HW markers] NO_REPLY\n> [zero or more HW markers] \u003Cone natural sentence addressed to the user>\n> ```\n>\n> Nothing may appear before, between, or after those parts. In particular, do\n> **not** output the detected label or confidence; describe the cue as weak;\n> name a bucket, route, rule, source, prefix, marker, log, decision, or mood;\n> state what you are about to do; draft a line; or count its words\u002Fsentences.\n> Those are private scratch work, never user-facing text. Do the writes via HW\n> markers, then start immediately with the first word the user should hear.\n> Bad: `Emotion: Anger. Weak camera cue. Route = checkin. Let me compose...`\n> Good: `[HW:...] That sounds rough — I'm right here.`\n\n## What this skill does\n\nOn every `[emotion]` or `[speech_emotion]` event, turn the detected user emotion into a mood signal. Log it via the Mood skill, then route a response (music \u002F checkin \u002F action) based on the pre-fetched context.\n\nThis skill does NOT:\n\n- Fire `[HW:\u002Femotion:…]` markers. Emotion expression is `emotion\u002FSKILL.md`'s job, driven by conversation context — not auto-mapped from a sensor reading.\n- Require a spoken reply. Whether to speak is decided by the normal reply rules (SOUL + sensing SKILL), not by this skill.\n- Write to the wellbeing log. Wellbeing is for physical activity (drink\u002Fbreak\u002Fcelebrate\u002Fsedentary); emotions live in the mood log.\n\n## Trigger\n\nEither of:\n\n```\n[emotion] Emotion detected: \u003CEmotionName>.            ← camera (face)\n[speech_emotion] Speech emotion detected: \u003CEmotionName>.  ← microphone (voice)\n```\n\nFace FER labels: `Happy`, `Sad`, `Angry`, `Fear`, `Surprise`, `Disgust`, `Neutral`.\nVoice emotion2vec labels: `Happy`, `Sad`, `Angry`, `Fearful`, `Surprised`, `Disgusted`, `Neutral` (plus `Other`, `\u003Cunk>` — dropped upstream).\n\nBoth formats end with the same `\u003CEmotionName>.` anchor; the same regex parses either one.\n\n## Emotion → mood (for the signal log)\n\nBoth label vocabularies map to the same mood values — voice variants (`Fearful`, `Surprised`, `Disgusted`) bucket identically to their face counterparts (`Fear`, `Surprise`, `Disgust`).\n\n| Detected emotion (face OR voice) | `mood` value to log |\n|---|---|\n| `Happy` | `happy` |\n| `Sad` | `sad` |\n| `Angry` | `frustrated` |\n| `Fear` \u002F `Fearful` | `stressed` |\n| `Surprise` \u002F `Surprised` | `excited` |\n| `Disgust` \u002F `Disgusted` | `frustrated` |\n| `Neutral` | `normal` |\n\n## What this skill produces\n\nA single `kind=signal` row in the mood log, emitted as an HW marker at the start of your spoken reply (the runtime fires the POST async, no tool turn):\n\n```\n[HW:\u002Fmood\u002Flog:{\"kind\":\"signal\",\"source\":\"\u003Ccamera|voice>\",\"trigger\":\"\u003CEmotionName lowercase>\",\"mood\":\"\u003Cmapped_mood>\",\"user\":\"\u003Ccurrent_user>\"}]\n```\n\n**`source` is decided by the event prefix on THIS turn:**\n- `[emotion]` → `\"camera\"`\n- `[speech_emotion]` → `\"voice\"`\n\nDon't override based on prior turns or the `recent_signals` block; the prefix is authoritative.\n\n`mapped_mood` comes straight from the `[emotion_context: ...]` block — do NOT look it up from the table on the fly. Every detected emotion in the mapping table gets logged (including `Neutral` → `normal`) — Mood needs the recency for decision synthesis. Use `\"unknown\"` when the context tag is missing.\n\n**Do NOT use `curl` exec for this signal log** — see `mood\u002FSKILL.md`'s \"What to write\" section for the rationale (HW marker is single-trip, curl burns a tool turn). If no `[HW:\u002Fmood\u002Flog:...]` marker appears in the reply this turn, the skill failed.\n\n## Combined with mood + music-suggestion\n\nThe backend injects this turn with an `[emotion_context: {...JSON...}]` block that pre-computes everything the three skills need (this skill is the router, mood logs the decision, music-suggestion fires only when this router picks the `music` route). **Do NOT fire any read tool calls** — the data is already in the message.\n\nPre-fetched fields (use directly):\n- `mapped_mood` — already maps this turn's `\u003CEmotionName>` per the table above. This is the value to log as the signal mood. **You no longer need to look it up yourself.**\n- `recent_signals`, `prior_decision`, `is_decision_stale` — feed `mood\u002FSKILL.md`'s decision rules and this skill's routing table.\n- `audio_playing`, `last_suggestion_age_min`, `audio_recent`, `music_pattern_for_hour`, `suggestion_worthy` — feed this skill's routing table (see **Response routing** below) and `music-suggestion\u002FSKILL.md`'s genre pick.\n\nSingle combined plan, not three sequential workflows:\n\n- **Decide locally** — apply mood decision rules from `mood\u002FSKILL.md`; pick a route from the routing table below; if the route is `music`, evaluate genre from `music-suggestion\u002FSKILL.md`.\n- **Writes (batch in one bash with `&` + `wait`)** — POST mood signal (this skill), POST mood decision (mood), and on `music` or `checkin` route, POST the music-suggestion log (the shared cooldown channel).\n\n### Fallback (only if `[emotion_context: ...]` is missing)\n\nIf the message has no context block (pre-fetch failed), fall back to the read batch from `mood\u002FSKILL.md` and `music-suggestion\u002FSKILL.md` (concurrent GETs in one bash via `& ... wait`).\n\nReply: routing decides the spoken reply (see next section). Never narrate the mapping, logging, or routing decision.\n\n## Response routing (this skill is the router)\n\nAfter logging the mood signal, pick **exactly one** response route. Read straight from `[emotion_context: ...]` — no extra tool calls. Apply top-to-bottom, first match wins:\n\n| # | Condition | Route | What happens |\n|---|---|---|---|\n| 1 | `audio_playing == true` | **action** | LED-only ambient ack, no spoken reply. Emit `[HW:\u002Femotion:{\"emotion\":\"caring\",\"intensity\":0.4}]` + `NO_REPLY`. Music is already covering — don't talk over it. |\n| 2 | `suggestion_worthy == true` AND (`is_decision_stale == false` OR fresh decision synthesized this turn) AND `last_suggestion_age_min ∉ [0, 7)` | **music** | See `music-suggestion\u002FSKILL.md` for genre + phrasing + log marker. |\n| 3 | anything else (cooldown active, mood not worthy, stale decision with no fresh synthesis, mapped_mood normal\u002Ffrustrated, etc.) | **checkin** | See `reference\u002Fcheckin.md` for phrasing + log marker. One soft open-ended line. |\n\nRules:\n\n- **One route per turn.** Don't double-fire (e.g. music + checkin both). Pick the first matching row.\n- **Cooldown only gates music, not checkin.** When `last_suggestion_age_min ∈ [0, 7)` the music branch is blocked (row #2 fails its third clause) and the event falls through to checkin (row #3). The agent still asks — it just doesn't suggest music back-to-back. The only `NO_REPLY` path is row #1 (active audio).\n- **Output ownership:** `music` → produced by `music-suggestion\u002FSKILL.md`. `checkin` → produced by `reference\u002Fcheckin.md` (this skill). `action` → emitted inline by this router (the `[HW:\u002Femotion:...]` marker in row #1).\n- **Cooldown is shared** between music and checkin: both log via `music-suggestion\u002Flog` so `last_suggestion_age_min` reflects either channel.\n- **Never narrate the routing decision in the spoken reply.** The reply is read\n  aloud verbatim — the row you picked and why is scratch, not speech. Device-observed\n  leak, 2026-08-24: *\"A speech-emotion happy cue, fresh decision, audio idle, cooldown\n  clear — routes to a music suggestion (speak only, unknown user). Sounds like a good\n  mood — want some upbeat feel-good tunes?\"* Only the last sentence was the reply;\n  everything before it was the routing table thought out loud. Start the reply at the\n  first word the user should hear.\n- `Neutral` is filtered upstream at HAL and never reaches this skill in practice; no special case needed here.\n\n## Voice cue is weaker than camera cue\n\nSpeech emotion (`[speech_emotion]`) is noisier than facial expression on short utterances — emotion2vec flips between `sad \u002F fearful \u002F angry` within the same affective state. The hedge `(weak voice cue; ...; treat as uncertain, ...)` is baked into the message for that reason.\n\nPractical rules:\n\n- **Don't relax the cooldown.** Music suggestions still gate on `last_suggestion_age_min ∉ [0, 7)` regardless of source. A fresh voice signal does NOT reset the cooldown that a recent camera-driven music suggestion left.\n- **Prefer Comfort\u002FInvite phrasing on voice-only negative reads.** When the router falls through to checkin (row #3) and the trigger is `[speech_emotion]` with `bucket=negative`, lean toward Comfort\u002FInvite rather than Ask — probing a maybe-misclassified utterance feels worse than acknowledging it.\n- **Cross-modal reinforcement still applies.** If `recent_signals` shows the same `mapped_mood` from `source=\"camera\"` in the last ~10 min and now voice fires the same mood, treat it as a confirmation — the Mood skill's decision synthesis already handles this; no extra logic here.\n- **No skip-on-low-confidence.** Don't read `confidence=...` out of the hedge text and pre-filter; HAL already enforced `confidence >= SPEECH_EMOTION_CONFIDENCE_THRESHOLD` before sending. Anything that reaches this skill is worth logging.\n",{"name":5,"description":7},"main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","06-前端与设计\u002Fuser-emotion-detection",3,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts","https:\u002F\u002Fgithub.com\u002Flza6","个人vx：Tf00798\r\n个人✈：@TFGY999","2026-10-08 14:29:22",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add lza6\u002FArmor-piercing-system-prompts --skill user-emotion-detection",{"tool":38,"command":39},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill user-emotion-detection",{"tool":41,"command":42},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill user-emotion-detection","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fuser-emotion-detection\u002FSKILL.md",true,[46,52],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"reference\u002Fcheckin.md","REFERENCE","参考文档",5022,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fuser-emotion-detection\u002Freference\u002Fcheckin.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"skill.json",249,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fuser-emotion-detection\u002Fskill.json",[57,64,69,76,83,90],{"skillNo":58,"name":59,"nameZh":6,"description":60,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":61,"categories":62,"keywords":63,"publishedAt":19},"01M7FFG485KY83TD6HSC4YPCMC","obsidian-clipper-template-creator","Guide for creating templates for the Obsidian Web Clipper. Use when you want to create a new clipping template, understand available variables, or format clipped content.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator\u002FSKILL.md",[],[],{"skillNo":65,"name":59,"nameZh":6,"description":60,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":19},"01M7FFG0T6AZ0STEJPSB3CX84K","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator-antigravity-awesome-skills-main\u002FSKILL.md",[],[],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":19},"01M7FFFY0QEM14SKWPDYGMXM2P","python-api","Programmatic Object-Detection-Metrics API guidance for BoundingBox, BoundingBoxes, Evaluator, enums, coordinate conversion, AP\u002FmAP semantics, and source-style import diagnostics.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Fpython-api\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":19},"01M7FFFVZQZ2GJ0C0TGP7JHD20","file-evaluation","Folder-based PASCAL VOC AP\u002FmAP evaluation from ground-truth and detection text files.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Ffile-evaluation\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M7FFFSFNYSE77SJ6PE1CK2DA","object-detection-metrics","Guides legacy Object-Detection-Metrics PASCAL VOC AP\u002FmAP evaluation from detection text folders and direct Python API classes.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002FSKILL.md",[],[],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":19},"01M7FFFP0GCK1RVXBCPQ8APBMT","nx-workspace-patterns","Configure and optimize Nx monorepo workspaces. Use when setting up Nx, configuring project boundaries, optimizing build caching, or implementing affected commands.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fnx-workspace-patterns\u002FSKILL.md",[],[]]