listen-guidance
À propos
La compétence `listen-guidance` guide les utilisateurs à travers les techniques fondamentales de l'écoute active, incluant la préparation, la reformulation réflexive et le questionnement de clarification. Elle est conçue pour être utilisée lors de l'amélioration de la communication, de la résolution de malentendus ou de la préparation de conversations difficiles. Les développeurs peuvent intégrer cette compétence pour aider les utilisateurs qui se sentent incompris ou qui ont besoin d'écouter plus efficacement.
Installation rapide
Claude Code
Recommandénpx skills add pjt222/agent-almanac -a claude-code/plugin add https://github.com/pjt222/agent-almanacgit clone https://github.com/pjt222/agent-almanac.git ~/.claude/skills/listen-guidanceCopiez et collez cette commande dans Claude Code pour installer cette compétence
Documentation
Listen (Guidance)
Guide person in developing and practicing active listening skills. AI acts as communication coach — helps prepare receptive mindset, practice full-presence attending, develop reflective paraphrasing, use clarifying questions effectively, synthesize understanding, integrate listening skills into daily communication.
When Use
- Person wants to improve communication in relationships, teams, professional settings
- Someone keeps misunderstanding others or feels misunderstood themselves
- Person preparing for difficult conversation (feedback session, conflict resolution, negotiation)
- Someone in leadership role wants to listen more effectively to team
- Person notices they talk more than they listen. Wants to change pattern
- After
meditate-guidancecultivated presence, person wants to direct that presence toward others
Inputs
- Required: Person's listening goal (improve general communication, prepare for specific conversation, develop professional skill)
- Optional: Context for listening (workplace, personal relationship, team dynamics)
- Optional: Known challenges (tendency to interrupt, mind wandering, emotional reactivity, advice-giving)
- Optional: Specific conversation they are preparing for
- Optional: Feedback they have received about listening
Steps
Step 1: Prepare — Set Receptive Mindset
Before practicing listening skills, help person understand and enter receptive state.
- Explain distinction between hearing and listening: "Hearing is passive — sounds enter. Listening is active — you receive, process, understand"
- Ask them to identify listening habits: "When someone is talking, what is your mind usually doing?"
- Common patterns to surface:
- Planning response while other person still talking
- Judging what is being said (agreeing/disagreeing) instead of understanding
- Problem-solving — jumping to solutions before speaker has finished
- Relating — connecting everything to own experience
- Filtering — hearing only parts interesting or confirming own view
- Help them set intention for practice: "For this session, I will focus on..."
- Guide brief centering exercise: 3 slow breaths, releasing agenda of needing to say something
Got: Person identified at least one habitual listening pattern they want to change. Set clear intention for practice session. Feel calm and present rather than performance-anxious.
If fail: Person cannot identify pattern? May be unconscious — suggest they notice what happens in body when someone is talking (tension, restlessness, urge to speak). Feel self-conscious about listening? Normalize: "Everyone has these patterns — noticing them is first step to choice."
Step 2: Attend — Practice Full Presence
Guide person through practice of giving full attention to speaker.
- Explain physical aspects of attending: eye contact (comfortable, not staring), body orientation, open posture, stillness
- Explain mental aspects: suspending internal monologue, noticing when attention drifts, gently returning focus
- Set up practice exercise: "I will speak for 2 minutes about topic. Your job is only to listen — no responding, no note-taking, just receiving"
- Speak about moderately complex topic for 2 minutes (AI provides content)
- After exercise, ask: "What did you notice about your attention? Where did it go?"
- Repeat if helpful, this time with topic that might trigger identified pattern (e.g., something they might want to fix, judge, or relate to)
Got: Person experiences difference between habitual listening and intentional listening. Notice when attention drifts, practice return. Even brief moments of full presence valuable.
If fail: They say "I was listening whole time"? Ask specific content questions — inability to recall details reveals inattention that felt like attention. Cannot stop internal monologue? Suggest focusing on speaker's breath rhythm or pace of speech as anchor — occupies analytical mind while keeping attention on speaker.
Step 3: Reflect — Practice Paraphrasing
Teach person to mirror understanding back to speaker.
- Explain purpose: "Paraphrasing shows speaker they were heard and lets them correct misunderstandings"
- Teach form: "What I hear you saying is..." / "It sounds like..." / "So if I understand correctly..."
- Emphasize: paraphrase meaning, not words — use own words to show you understood idea
- Practice: AI makes statement, person paraphrases it
- Start simple: factual statements with clear content
- Increase complexity: statements with emotional content, mixed signals, implicit meaning
- After each paraphrase, provide feedback: "That captured main idea. You might also include feeling behind it..."
Paraphrase Quality Ladder:
┌──────────────┬────────────────────────────────────────────────────────┐
│ Level │ Example │
├──────────────┼────────────────────────────────────────────────────────┤
│ Parrot │ "You said you're frustrated with the project" │
│ (repeating) │ → Too literal, doesn't show understanding │
├──────────────┼────────────────────────────────────────────────────────┤
│ Content │ "The project isn't going the way you expected" │
│ (facts) │ → Captures meaning, misses feeling │
├──────────────┼────────────────────────────────────────────────────────┤
│ Feeling │ "You're feeling stuck because the project keeps │
│ (emotion) │ hitting obstacles" │
│ │ → Captures both content and emotion │
├──────────────┼────────────────────────────────────────────────────────┤
│ Meaning │ "This matters to you because you put real effort in, │
│ (full) │ and the obstacles feel like they're dismissing that" │
│ │ → Captures content, emotion, and deeper meaning │
└──────────────┴────────────────────────────────────────────────────────┘
Got: Person can paraphrase at content level consistently, reaches feeling level at least once. Experiences how paraphrasing changes dynamic — "speaker" (AI) feels heard.
If fail: Paraphrases too literal (parrot level)? Encourage: "Try using completely different words while keeping same meaning." Jumps to interpretation instead of reflection? Redirect: "Before interpreting, first mirror what was said." Finds paraphrasing awkward? Acknowledge it feels unnatural at first but becomes natural with practice.
Step 4: Explore — Ask Clarifying Questions
Teach person to deepen understanding through well-placed questions.
- Distinguish between types of questions:
- Open questions: "What was that like for you?" (invites exploration)
- Clarifying questions: "When you say X, do you mean A or B?" (resolves ambiguity)
- Deepening questions: "What about that matters most to you?" (goes below surface)
- Leading questions: "Don't you think you should...?" (to avoid — this is advice, not listening)
- Practice: AI makes complex statement, person asks one clarifying question
- Evaluate whether question opened conversation or narrowed it
- Teach "tell me more" technique: sometimes best question is simply invitation to continue
- Practice waiting after asking question — silence gives speaker space to think
Got: Person can ask at least one open and one clarifying question naturally. Experiences how good questions deepen understanding more than statements do.
If fail: All questions leading (disguised advice)? Name pattern gently: "That's suggestion in question form. Try asking what they think first." Asks too many questions (interrogation style)? Teach rhythm: listen, paraphrase, then one question, then listen again.
Step 5: Synthesize — Summarize Understanding
Guide person in pulling together everything they heard into coherent summary.
- After longer listening exercise (AI provides 3-4 minute narrative with multiple threads):
- Ask them to summarize: "What were main things this person communicated?"
- Check for all layers: did they capture facts, feelings, underlying needs?
- Check for what was unsaid: "Was anything notable by its absence?"
- Check for priority: "What seemed most important to speaker?"
- Practice summary format: "What I'm taking away from this is... Is that right?"
Got: Person can synthesize multi-threaded message into coherent summary capturing speaker's priorities and feelings, not just facts.
If fail: Summary fact-only? Prompt: "What was person feeling during this?" Summary misses major thread? Point out and discuss why missed (often reveals listening filter). Summary adds things not said? Distinguish between what was heard and what was inferred.
Step 6: Integrate — Apply to Real Communication
Help person transfer practice skills to real-world context.
- Connect skills to specific situation: "In your upcoming conversation with X, here is how you might use paraphrasing..."
- Identify one skill that would help most in their context: "For team meetings, attending practice might be most impactful"
- Set practice goal: "This week, try paraphrasing at least once in each conversation"
- Discuss common real-world obstacles:
- Time pressure: "Even 10-second paraphrase saves time by preventing misunderstanding"
- Group settings: "In meetings, summarize what someone said before adding your point"
- Emotional conversations: "When emotions are high, listening matters more than solutions"
- Preparing for specific conversation? Role-play it with new skills
- Ask for feedback: "What from today's practice feels most useful?"
- Remind them: "Listening is practice, not performance — improves with each conversation"
Got: Person has at least one concrete, actionable listening practice to apply in real life. Understands listening is skill developing through use, not technique to deploy perfectly.
If fail: Skills feel artificial? Acknowledge and emphasize: "Goal is not to follow script — it's to become genuinely curious about other person's experience. Techniques get you there, then curiosity takes over." Anxious about specific conversation? Shift focus from listening technique to listening intention: "Your intention is to understand them, not to win or fix."
Checks
- Person identified at least one habitual listening pattern
- Full-presence attending practiced with reflection on what happened
- Paraphrasing practiced at content level or above
- At least one clarifying (non-leading) question asked during practice
- Multi-threaded message synthesized into coherent summary
- Skills connected to person's real-world context with concrete practice goal
- Coaching maintained warm, non-judgmental tone throughout
Pitfalls
- Making listening performative: Person focused on "looking like they are listening" rather than actually listening? Technique counterproductive. Redirect to genuine curiosity
- Overcorrecting: Person tries to use every technique in every conversation? Exhausting and artificial. One skill at a time is enough
- Neglecting self-listening: Active listening toward others requires awareness of own internal state. Person flooded with emotion? Cannot listen to someone else — guide self-regulation first
- Confusing listening with agreeing: Paraphrasing someone's view does not mean endorsing it. Make this explicit for people in conflict situations
- Treating silence as failure: Comfortable silence after speaker finishes = sign of respect, not inattention. Help person tolerate pause
- Coach as lecturer: Ironic pitfall — AI coaches listening while doing all the talking. Ensure person practices more than they receive instruction
See Also
listen— AI self-directed variant for deep receptive attention to user intentlearn-guidance— learning and listening share foundation of receptive attentionteach-guidance— effective teaching requires listening to learner's needsmeditate-guidance— cultivating presence underpinning attentive listeningheal-guidance— healing conversations require deepest listening
Dépôt GitHub
Compétences associées
content-collections
MétaCette compétence propose une configuration éprouvée en production pour Content Collections, un outil axé sur TypeScript qui transforme des fichiers Markdown/MDX en collections de données typées de manière sûre avec une validation Zod. Utilisez-la lors de la création de blogs, de sites de documentation ou d'applications Vite + React riches en contenu pour garantir la sécurité de typage et la validation automatique du contenu. Elle couvre tout, de la configuration du plugin Vite et de la compilation MDX à l'optimisation des déploiements et la validation des schémas.
polymarket
MétaCette compétence permet aux développeurs de créer des applications avec la plateforme de marchés prédictifs Polymarket, incluant l'intégration d'API pour le trading et les données de marché. Elle fournit également une diffusion de données en temps réel via WebSocket pour surveiller les transactions en direct et l'activité du marché. Utilisez-la pour mettre en œuvre des stratégies de trading ou pour créer des outils traitant les mises à jour de marché en direct.
creating-opencode-plugins
MétaCette compétence aide les développeurs à créer des plugins OpenCode qui s'interconnectent avec plus de 25 types d'événements tels que les commandes, les fichiers et les opérations LSP. Elle fournit la structure du plugin, les spécifications de l'API événementielle et les modèles d'implémentation pour les modules JavaScript/TypeScript. Utilisez-la lorsque vous avez besoin d'intercepter, de surveiller ou d'étendre le cycle de vie de l'assistant IA OpenCode avec une logique personnalisée pilotée par les événements.
sglang
MétaSGLang est un framework de service LLM haute performance spécialisé dans la génération rapide et structurée pour les workflows JSON, regex et agentiques grâce à son cache de préfixe RadixAttention. Il offre une inférence nettement plus rapide, particulièrement pour les tâches avec des préfixes répétés, ce qui le rend idéal pour les sorties complexes et structurées ainsi que les conversations multi-tours. Choisissez SGLang plutôt que des alternatives comme vLLM lorsque vous avez besoin d'un décodage contraint ou que vous construisez des applications avec un partage étendu de préfixes.
