Results for “shorten-rest”

Rewrites the previous response to be simpler and shorter while preserving the substance.

Rewrites the previous response to be shorter and simpler while preserving substance.

Rewrite the previous response more briefly while preserving the substance.

Modifies an existing rough cut by generating a review_patch and re-compiling the timeline, supporting clip shortening, removal, reordering, and audio adjustments.

Rewrite the previous response more briefly while preserving the substance.

Invoke when the agent's conversational replies have gotten too long or wordy and the user wants shorter answers for the rest of the conversation.

Rewrite the previous response more briefly while preserving the substance.

Shorthand-first response compression that cuts ~40% of response tokens while preserving technical precision and exact literals. Use when the user says "steno mode", "shorthand mode", "compressed responses", "token reduction", "brief structured output", or invokes /steno. Supports four compression levels: lite, brief, court, machine. Do not trigger for requests needing polished prose such as onboarding/tutorial content, stakeholder or customer-facing copy, or teaching-focused explanations.

Plan and apply safe, reversible headless-mode changes on Jetson devices to reclaim memory from the GUI and non-essential daemons.

Keep long-running agent work within 5-hour and weekly usage limits by checking usage between waves, pausing near the cap, and resuming only when the window is clear.

Guides building, reviewing, and debugging inbound Apex REST resources with explicit status codes, JSON error shapes, and versioned URL mappings.

Rewrite the previous response more briefly while preserving the substance.

Enables persistent ultra-compressed technical communication; use for explicit brevity or token-reduction requests, except where fragments risk safety or clarity.

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

Facilitate a structured sprint retrospective to surface insights and produce actionable improvements with owners and deadlines.

Quickly refreshes project state when resuming work by reporting git status, recent commits, environment, memory staleness, pending tasks, and red flags.

Optimizes long-running agent sessions with structured context compression, summarization, and durable handoff summaries that preserve decisions, files, risks, and next actions.

Use when content is verbose, repetitive, or padded and needs tightening while preserving meaning

Ultra-compressed communication mode. Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full technical accuracy. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman.

Reduces token usage by ~75% by stripping filler words, articles, and pleasantries while preserving full technical accuracy. Activates on user commands like 'caveman mode' or 'be brief'.

Use when fragmented, dictated, or stream-of-consciousness notes need reorganizing into coherent prose without adding new ideas

Shares memory between agents at the representation level by compacting the orchestrator's KV cache for efficient worker handoff, reducing token costs without summarization or retrieval.

Use when aligning short reads to a reference genome or indexed sequence database. Suitable for mapping FASTQ/FASTA reads in paired-end or single-end mode to produce SAM output.

Runs a relentless interview that sharpens a plan or design and creates docs (ADRs and glossary) along the way. Use when the user wants to stress-test a plan or design, or produce decision records.

Runs a relentless interview that sharpens a plan or design. Use when the user wants to be grilled on an idea, pressure-test a plan, or refine a design through questioning.

Manage and compress conversation context in long sessions. Detect when context is growing large, summarize completed work phases, archive old findings while preserving key decisions. Prevents context degradation.

Ultra-compressed communication mode. Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full technical accuracy. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman.

Tone down overly bold or visually aggressive designs. Reduces intensity while maintaining design quality and impact.

建议在逻辑间隔处手动压缩上下文，以在任务阶段中保留上下文，而非任意的自动压缩。

Script a short-form vertical video with a 2-second hook, tight pacing, and on-screen text cues.

上下文压缩省 Token。对话变长或开新任务时输出/使用 6 块压缩结构，总长 400~800 tokens。必加载。

Token-efficient code review using Tree-sitter AST graphs and MCP. Reduces AI assistant token usage by 6.8–49x by computing blast radius of changes instead of reading entire codebases. Uses SQLite graph database for structural analysis.

Ultra-compressed communication mode. Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full technical accuracy. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman.

Facilitate a structured sprint retrospective — what went well, what didn't, and prioritized action items with owners and deadlines. Use when running a retrospective, reflecting on a sprint, creating action items from team feedback, or learning how to run effective retros.

Optimize context window usage — compact stale data, compress via summarization, preserve active state