'feedback-loop' 검색 결과

Design AI feedback loops for continuous improvement. TRIGGERS - Use when user needs help with ai-feedback-loop related tasks.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Design AI feedback loops for continuous improvement. TRIGGERS - Use when user needs help with ai-feedback-loop related tasks.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Guide a scoped coding task through specification, implementation, and review. Set acceptance criteria, verification checks, iteration limits, and approval gates, then correct identified gaps until the requirements pass or a stopping condition is reached.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Build a small feature from specification through verification
• Modify a module against explicit acceptance criteria
• Repeat fixes and checks within an iteration limit

Use when the user asks to "design an early access program", "set up a waitlist and beta stages", or "define beta graduation criteria"; produces a waitlist→concept→alpha→beta→GA stage ladder with per-stage purpose and opt-in semantics, quantified graduation criteria per stage (labeled Estimated), a cohort-gating and invite-throttling plan, tester recruitment with launch-day social-proof prep, a feedback-loop spec where every status change notifies its subscribers, and a referral-loop mechanism spec (invite codes, anti-abuse). Not for waitlist acquisition strategy or the capture-flow spec — use list-growth-designer; not for the canonical stage record — use launch-registry. waitlist/内测阶梯/抢先体验/毕业标准/反馈闭环

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Patterns for AI agents that learn from their own execution, detect failure modes, and improve autonomously. Use when building agents that get better over time, managing auto- memory, or designing self-correcting feedback loops.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Design a wise systems intervention from an existing analysis. Maps proposed actions against Meadows' leverage points, checks for unintended consequences, and generates alternatives.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Measures whether an automation suite builds release confidence via feedback-loop length, suite reliability, release cadence, and production escape rate, and emits a release_confidence verdict. Use when judging suite value, ROI, or pre-release trust; not for writing or healing tests.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Persistent compounding memory for AI agents. 5 default MCP tools: session_start, session_end, remember, recall, check. Full surface: 6 tools with --full (adds check_action); 13 tools with AR_EXTRAS=1 --full. Two-verb model: inhale (session_start) and exhale (session_end). Correction-first memory with decision trail tracking, watch_for warnings, palace rooms with salience scoring, cross-project insight matching, same-day journal merging, ambient recall hooks. Local markdown only. Zero cloud, zero telemetry, Obsidian-compatible. Optional Supabase backend: when configured via `ar setup supabase`, recall() uses pgvector cosine similarity on OpenAI/Voyage embeddings instead of keyword search — same API, semantic understanding. Gracefully degrades to local search if not configured.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Runs a bounded spec-build-review development loop with explicit scope, stop conditions, and human approval gates for risky or ambiguous work.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Persistent compounding memory for AI agents. 5 default MCP tools: session_start, session_end, remember, recall, check. Full surface (18 tools) available with --full flag. Two-verb model: inhale (session_start) and exhale (session_end). Correction-first memory with decision trail tracking, watch_for warnings, palace rooms with salience scoring, cross-project insight matching, same-day journal merging, ambient recall hooks. Local markdown only. Zero cloud, zero telemetry, Obsidian-compatible. Optional Supabase backend: when configured via `ar setup supabase`, recall() uses pgvector cosine similarity on OpenAI/Voyage embeddings instead of keyword search — same API, semantic understanding. Gracefully degrades to local search if not configured.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Establish channels and processes for capturing and processing post-launch feedback during PRD v0.9 Go-to-Market. Triggers on requests to set up feedback systems, capture user input, or when user asks "how do we collect feedback?", "feedback loop", "user research", "post-launch feedback", "customer feedback", "NPS", "voice of customer". Outputs CFD- entries specialized for post-launch feedback capture.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Adds per-skill learnings loops for dated patterns, mistakes, and domain facts. Use when wiring skill memory, consolidation, or drift audits.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Design a wise systems intervention from an existing analysis. Maps proposed actions against Meadows' leverage points, checks for unintended consequences, and generates alternatives.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

OctoClaw is the TypeScript-first policy, delegation, status, and operator layer for OpenClaw. Use it when a turn should be routed through reply/delegate policy, WorkContract-backed delegation, runtime status, IM delivery, or feedback-loop tooling.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Feed actual task results back into agent memory for calibration. Compares predicted vs actual outcomes, records accuracy scores, and tracks estimation quality, prediction quality, and decision quality over time to improve future agent performance.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Feedback loop implementation for continuous CTI improvement. Consumer feedback, analyst retrospectives, source quality tracking.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Identify and simulate Data Poisoning attacks aimed at degrading or skewing an AI model's accuracy. This skill focuses on Adversarial Machine Learning concepts where attackers inject malicious or mislabelled data points into training or fine-tuning datasets (e.g., feedback loops) to bias the AI.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Diagnose when intuitive judgment, agent confidence, or expert routing can be trusted by classifying environment validity, feedback quality, and task-boundary fit. Use for confidence calibration, agent routing, expertise audits, and escalation design. NOT for deterministic implementation tasks, pure syntax debugging, or domains with explicit verifiable answers.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

当用户想要在团队中实施结构化反馈、建立360度评估机制、或现有匿名反馈产出低效结果时触发此技能。帮助设计具名、无评分、与薪酬脱钩的反馈体系。

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Harness-first workflow for evaluating and improving terminal UIs through real interaction. Use this whenever the user wants to review a TUI experience, compare before/after behavior, identify UX friction, validate navigation or filtering flows, inspect visual stability, or turn observed interaction problems into concrete follow-up tests and improvement recommendations. Prefer this skill any time a TUI should be exercised through a reproducible PTY/session harness instead of only reading code.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Runs a bounded spec-build-review development loop with explicit scope, stop conditions, and human approval gates for risky or ambiguous work.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when the user asks to "design an early access program", "set up a waitlist and beta stages", or "define beta graduation criteria"; produces a waitlist→concept→alpha→beta→GA stage ladder with per-stage purpose and opt-in semantics, quantified graduation criteria per stage (labeled Estimated), a cohort-gating and invite-throttling plan, tester recruitment with launch-day social-proof prep, a feedback-loop spec where every status change notifies its subscribers, and a referral-loop mechanism spec (invite codes, anti-abuse). Not for waitlist acquisition strategy or the capture-flow spec — use list-growth-designer; not for the canonical stage record — use launch-registry. waitlist/内测阶梯/抢先体验/毕业标准/反馈闭环

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Diagnose when intuitive judgment, agent confidence, or expert routing can be trusted by classifying environment validity, feedback quality, and task-boundary fit. Use for confidence calibration, agent routing, expertise audits, and escalation design. NOT for deterministic implementation tasks, pure syntax debugging, or domains with explicit verifiable answers.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Diagnose when intuitive judgment, agent confidence, or expert routing can be trusted by classifying environment validity, feedback quality, and task-boundary fit. Use for confidence calibration, agent routing, expertise audits, and escalation design. NOT for deterministic implementation tasks, pure syntax debugging, or domains with explicit verifiable answers.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.