latent-space-engineering
Shapes agent behavior via instruction framing and style transfer. Use when composing dispatch prompts or writing skill instructions for parallel rev…
它会碰到什么
这一栏是扫描器报的事实,不是结论。命中多不等于有毒(安全工具、规则库、示例脚本本来就会包含危险写法),命中少也不等于干净。它和你手上的凭据、文件、网络有什么关系,需要你自己看。
技能内容
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
| Technique | When | Module |
|-----------|------|--------|
| Emotional framing | Any agent prompt | emotional-framing |
| Style gene transfer | Code/doc generation | style-gene-transfer |
| Competitive review | 3+ parallel reviewers | competitive-review |
| Named register | Operator or procedural text | named-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)
想直接用这个技能?
本站把开放许可(MIT / Apache 等)的技能按仓库打包整理到网盘,点一下转存到你自己的网盘,不用一个个从 GitHub 拉。许可未声明的技能只给原始仓库链接,不打包。
它属于哪个仓库
plugins/imbue/skills/latent-space-engineering/SKILL.md同一个仓库里的其他技能
- claude-code-plugin-reference
- night-market-architecture-contract
- night-market-build-and-env
- night-market-change-control
- night-market-collective-memory
- night-market-completion-integrity-campaign
- night-market-config-catalog
- night-market-debugging-playbook
- night-market-diagnostics-toolkit
- night-market-docs-and-writing
- night-market-failure-archaeology
- night-market-model-and-harness-updates