跳到正文
cccskills
免费在 GitHub 公开

latent-space-engineering

Shapes agent behavior via instruction framing and style transfer. Use when composing dispatch prompts or writing skill instructions for parallel review agents.

中文简介正在准备中。当前显示原文说明。

实测评分 未实测

查看安装方法

包含的文件(6)

  • SKILL.md3.5 KB
  • modules/competitive-review.md1.7 KB
  • modules/emotional-framing.md2.2 KB
  • modules/know-your-delegate.md3.4 KB
  • modules/named-register-invocation.md4.4 KB
  • modules/style-gene-transfer.md1.6 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Latent Space Engineering

Shape agent behavior by framing instructions for optimal performance. Distinct from context engineering (packing the right information), this skill addresses HOW instructions are framed to put agents in productive mental states.

When To Use

  • Composing agent dispatch prompts
  • Writing skill instructions that guide behavior
  • Dispatching 3+ parallel review agents
  • Generating code or documentation that must match an existing style

When NOT To Use

  • Packing factual context (use context-optimization)
  • Simple single-shot tasks with no behavioral nuance
  • Tasks where instruction tone is irrelevant

Core Techniques

1. Emotional Framing

Replace threat-based prompting with calm, confident instructions. Fear-based prompts cause rushing and corner-cutting.

Load module: modules/emotional-framing.md

2. Style Gene Transfer

Inject exemplar code or prose into context before requesting output. Agents reproduce stylistic attributes from pre-loaded samples.

Load module: modules/style-gene-transfer.md

3. Competitive Review

Frame multi-agent review dispatch with competitive incentives to increase rigor and thoroughness.

Load module: modules/competitive-review.md

4. Named Register Invocation

Name a published standard to pull a whole writing register into output at a cost of one line. Cheaper than exemplar injection and coarser, with a known mid-session decay.

Load module: modules/named-register-invocation.md

Quick Reference

TechniqueWhenModule
Emotional framingAny agent promptemotional-framing
Style gene transferCode/doc generationstyle-gene-transfer
Competitive review3+ parallel reviewerscompetitive-review
Named registerOperator or procedural textnamed-register-invocation

Writing for the Delegate

Framing shapes a delegate's output as much as it shapes a model's prose. Before dispatching, establish what model the delegate runs, what tools it has, and what project context it lacks, then write the prompt as a proposal rather than a procedure.

See modules/know-your-delegate.md.

Exit Criteria

  • When a named register is invoked (for example ASD-STE100), a deterministic check verifies the register held, per modules/named-register-invocation.md
  • Dispatch prompts contain no threat-based language ("you must", "don't fail", "or else"); replaced with calm, confident framing per modules/emotional-framing.md
  • When generating code or docs to match an existing style, at least one exemplar sample is injected into context before the output is requested (style gene transfer applied)
  • When 3+ parallel review agents are dispatched, each agent prompt includes a competitive framing element per modules/competitive-review.md
  • The correct technique module is loaded for the task type; irrelevant modules are not loaded (token efficiency maintained)

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Shapes turns action-first: action leads, steps numbered, state restated. Use for ADHD-friendly output. Do not use to trim tokens; use response-compression.

中文简介正在准备中。当前显示原文说明。

athola/claude-night-market3432026年10月24日 更新

Inverts burden of proof for code additions. Use when reviewing PRs, planning refactors, or running unbloat to challenge every addition's necessity.

中文简介正在准备中。当前显示原文说明。

athola/claude-night-market3432026年10月24日 更新

Tracks per-agent token usage and flags waste in parallel dispatch. Use when evaluating parallel agent efficiency or after a multi-agent run.

中文简介正在准备中。当前显示原文说明。

athola/claude-night-market3432026年10月24日 更新

Coordinates Claude agent teams via filesystem protocol. Use when orchestrating parallel agents with task dependencies. Do not use for single-agent tasks.

中文简介正在准备中。当前显示原文说明。

athola/claude-night-market3432026年10月24日 更新

Evaluates API surface design, consistency, and exemplar alignment. Use when reviewing public API changes or before releasing a new API surface.

中文简介正在准备中。当前显示原文说明。

athola/claude-night-market3432026年10月24日 更新

Selects architecture paradigm via research before scaffolding. Use when architecture is undecided and the choice needs justification and documentation.

中文简介正在准备中。当前显示原文说明。

athola/claude-night-market3432026年10月24日 更新

查看 athola 的全部技能

报告此技能的问题