Results for “recallai”

Computes the Recall metric using torchmetrics, including configuration for binary, multiclass, and multilabel tasks.

FREE — God-tier long-context memory for AI agents. Injects 500K-1M clean tokens, auto-summarizes with tone/intent preservation, compresses 14-turn history into 800 tokens.

FREE — God-tier long-context memory for AI agents. Injects 500K-1M clean tokens, auto-summarizes with tone/intent preservation, compresses 14-turn history into 800 tokens.

FREE — God-tier long-context memory for AI agents. Injects 500K-1M clean tokens, auto-summarizes with tone/intent preservation, compresses 14-turn history into 800 tokens.

Pauses mid-conversation to reassess direction, assumptions, and bias, then recommends whether to continue, pivot, or pause.

按 scope 重置 wiki 到干净 scaffold（wiki / raw / log / checkpoints / all）。适用于开发迭代或 setup 失败后的无痛重启。

FREE — God-tier long-context memory for AI agents. Injects 500K-1M clean tokens, auto-summarizes with tone/intent preservation, compresses 14-turn history into 800 tokens.

Use when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, refactoring, or automated editing. Uses GPT-5.2 by default for state-of-the-art software engineering.

Use the status-briefing skill to run `pk-reconcile session-start`, then

Regenerates a specific code layer (schemas, services, routes, hooks, ui) or all layers, then runs the corresponding validation checks.

Mines git history and codebase to reconstruct the development lifecycle, identify sequential and parallel patterns, and produce actionable recommendations for future iterations.

Imported skill faq_database from openai

セッション再開時に最新5件のhandoffを読み込み文脈を復元するスキル。「おはよう」「こんにちは」「こんばんは」「再開」「restart」または /resume-session を呼んだ時にトリガーする。new-session の対（読込側）。

Re-renders a subject or scene from multiple dramatic camera angles while maintaining consistent identity and detail.

Use quando o usuário pede para executar Codex CLI (codex exec, codex resume) ou referencia OpenAI Codex para análise de código, refatoração ou edição automatizada. Usa GPT-5.2 por padrão para engenharia de software de ponta.

Delegate tasks to OpenAI Codex CLI and Google Antigravity CLI from Claude Code with topic-aware sessions.

週次リフレクション（1週の振り返りサマリ）を生成するスキル。直近の完了週の日記から4要素（作業傾向/思考癖/繰り返す課題/CCアドバイス）を生成し、_INDEX気づきTop3はユーザー承認後に反映。ユーザーが「リフレクション」「今週の振り返り」「思考癖まとめて」と言った時、または /reflection を呼んだ時に発動。resume-sessionの検知提案からも起動される。

Resume an interrupted AgenTeam run with verify-first strategy.

补充上下文，用更简单、明确的中文重新解释。

Use when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, refactoring, or automated editing. Uses GPT-5.2 by default for state-of-the-art software engineering.

Use when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, refactoring, or automated editing. Uses GPT-5.2 by default for state-of-the-art software engineering.

OpenAI Codex CLI wrapper — three modes. Code review: independent diff review via codex review with pass/fail gate. Challenge: adversarial mode that tries to break your code. Consult: ask codex anything with session continuity for follow-ups. The "200 IQ autistic developer" second opinion. Use when asked to "codex review", "codex challenge", "ask codex", "second opinion", or "consult codex". (gstack) Voice triggers (speech-to-text aliases): "code x", "code ex", "get another opinion".

Runs a full retrospective and dev cycle analysis, chaining /recall and /new-features to reconstruct what went wrong, extract lessons learned, identify rework patterns, and synthesize feature ideas from the findings.

Provides three modes — code review, adversarial challenge, and consult — for obtaining a second opinion on code.