Results for “message-distillation”

Lossless LLM-optimized compression of source documents. Use when the user requests to 'distill documents' or 'create a distillate'.

Multi-channel personalized message generation with 3 tiers of personalization

Compress large language models using knowledge distillation from teacher to student models. Use when deploying smaller models with retained performance, transferring GPT-4 capabilities to open-source models, or reducing inference costs. Covers temperature scaling, soft targets, reverse KLD, logit distillation, and MiniLLM training strategies.

Scan skills to extract cross-cutting principles and distill them into rules — append, revise, or create new rule files

Anti-distillation defense for employee Skills. Clean your skill files to look complete but with core proprietary knowledge neutralized. Use when user wants to protect trade secrets, sanitize forced knowledge transfers, or create safe-to-submit skill documents.

Turn a diff or plain description into a conventional-commit message - honest type and scope, a why-focused body, breaking changes flagged, nothing invented.

Compress large language models using knowledge distillation from teacher to student models, covering temperature scaling, soft targets, reverse KLD, logit distillation, and MiniLLM training strategies.

Compress large language models using knowledge distillation from teacher to student models. Use when deploying smaller models with retained performance, transferring GPT-4 capabilities to open-source models, or reducing inference costs. Covers temperature scaling, soft targets, reverse KLD, logit distillation, and MiniLLM training strategies.

Lossless LLM-optimized compression of source documents. Use when the user requests to 'distill documents' or 'create a distillate'.

Imported skill messages from langchain

Scan installed skills to extract cross-cutting principles and distill them into rules files.

Draft, rewrite, or condense emails with target tone, length, and audience; use for cold outreach, replies, status updates, or escalations where clarity and brevity matter.

Strip AI-generated tells from a draft and rewrite it in Heath's personal voice (GTM Juice). Fire whenever the user asks to "humanize", "de-AI", "clean up", "rewrite in my voice", "make this sound like me", "kill the AI tells", or "polish this draft". Also fires as the mandatory final pass inside juice-content-dispatch — every LinkedIn post, newsletter, and video script drafted there must run through this skill before the Notion write. Applies the 29-pattern Wikipedia "Signs of AI writing" catalog (em dashes, significance inflation, promotional language, rule of three, synonym cycling, inline-header lists, sycophantic tone, hyphenated word pairs, persuasive-authority tropes, signposting, etc.), then applies a hardcoded Heath-voice calibration: self-implicating first, failure-derived, plain declaratives over bumper-sticker aphorisms, no bow-tied endings, never Mixmax corporate brand voice. Forked from blader/humanizer (MIT).

Distill any intent input into the SPEC kernel + companions — the canonical, preservation-validated machine contract for downstream work. Use when the user says "create a spec", "distill this into a spec", "validate this spec", "update the spec", or "break this into stories".

Messaging systems fall into three fundamental shapes, and most bad choices come

Email sequences, newsletters, automation, and deliverability strategies. Use when the user requests 'email sequence', 'newsletter', 'drip campaign', 'welcome email', 'lifecycle email', 'cold email', 'email automation', or 'email copywriting'.

Defines market positioning and messaging using April Dunford's methodology, producing a positioning document with competitive landscape, value map, and messaging hierarchy.

Organize email inbox, draft replies, send messages, and verify delivery with evidence-based confirmation.

Draft, rewrite, or condense emails with target tone, length, and audience; use for cold outreach, replies, status updates, or escalations where clarity and brevity matter.

北岛（诗人）认知与表达框架（压缩蒸馏）：冷意象、否定句诗学、流亡与记忆 触发：回答、朦胧诗 等。不伪造诗句

🔮 Divination — Oracle Toolkit for AI Agents

Retrieves live messages from local messaging surfaces, including iMessage and DMs, recovers recent one-time codes, and inspects threads before replying, with evidence of the source checked.

When the user wants to create or optimize an email sequence, drip campaign, automated email flow, or lifecycle email program. Also use when the user mentions "email sequence," "drip campaign," "nurture sequence," "onboarding emails," "welcome sequence," "re-engagement emails," "email automation," "lifecycle emails," "trigger-based emails," "email funnel," "email workflow," "what emails should I send," "welcome series," or "email cadence." Use this for any multi-email automated flow. For cold outreach emails, see cold-email. For in-app onboarding, see onboarding.

When the user wants to create or optimize an email sequence, drip campaign, automated email flow, or lifecycle email program. Also use when the user mentions "email sequence," "drip campaign," "nurture sequence," "onboarding emails," "welcome sequence," "re-engagement emails," "email...

去除或避免文本中的 AI 味。用于用户强制调用本 Skill，或写作/改写时提到“不要有 AI 味”“不要太假”“真情实感”“有人感”，或对已有文本/上一轮输出反馈“太像 AI”“太空泛”“太模板”“太官方”“不像我说的”等场景。

当创作者需要在个人真实表达与市场需求之间找到平衡点时

`task-agent`/`review-agent`: use when broker delivery, ordering, acknowledgement, DLQ, backpressure, or replay changes; skip synchronous retry without message semantics.

Generate unique personalized first lines for hundreds of prospects using company news, LinkedIn activity, and mutual connections. Saves 10+ hours of manual research per campaign. Use when you need personalized outreach at volume.

Retrieves live messages from iMessage, DMs, or other messaging surfaces to read texts, recover one-time codes, or inspect threads before replying.

Design and optimize email sequences, drip campaigns, and lifecycle automations for marketing and product teams.

Push the LLM to reconsider, refine, and improve its recent output. Use when user asks for deeper critique or mentions a known deeper critique method, e.g. socratic, first principles, pre-mortem, red team.

Discord message-tool ops: send/read/edit/delete, react, poll, pin, thread, search, presence, media/components.

Craft messages that are understood, remembered, and drive action using the SUCCESs framework (Simple, Unexpected, Concrete, Credible, Emotional, Stories).

Analyzes why a piece of content resonates with audiences using five classic communication theories, identifies the emotional core and effective stance, and outputs discussion directions for a chatroom.

LinkedIn connection requests and DM sequences adapted to tool stack