Results for “recalls”

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.

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

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.

Apple Reminders via remindctl: add, list, complete.

Surface relevant project memory at session start or on demand. Trigger: session start, 'recall', 'remember', 'what do you know', 'context', /recall

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.

Transforms lessons learned into domain-organized memory instructions that persist across VS Code contexts, with global and workspace scopes.

Plan, debug, tune, evaluate, export, or deploy public Nemotron embedding and reranking retrieval recipes using the current checkout.

Save information to persistent memory for cross-session recall. Stores preferences, conventions, decisions, and context.

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

Trigger or resolve a PagerDuty incident for on-call escalation

Save the current diagnosis state to disk for cross-session recall, including conclusions, rejected directions, and next steps.

List, add, edit, complete, or delete Apple Reminders and reminder lists via remindctl.

Extract cached credentials, password hashes, Kerberos tickets, and authentication tokens from memory dumps using Volatility and Mimikatz for forensic investigation.

Execute self-learning system that captures corrections during sessions and syncs them to CLAUDE.md. Use when discussing learnings, corrections, or when the user mentions remembering something. Trigger with phrases like "remember this", "don't forget", "use X not Y", or "actually...".

skill-trigger-reminders

Restores the most recent diagnosis snapshot saved by dbs-save, allowing users to continue a previous diagnostic session.

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

Transforms lessons learned into domain-organized memory instructions (global or workspace). Syntax: `/remember [>domain [scope]] lesson clue` where scope is `global` (default), `user`, `workspace`, or `ws`.

QQBot scheduled reminders. Use only for explicit user requests to create, list, or cancel one-time or recurring QQ reminders; ask for missing time, content, or timezone before scheduling.

Resume an interrupted AgenTeam run with verify-first strategy.

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.