AGENT SKILL

lateral-thinking

Route creative problems through one of eight structured lateral-thinking methods: random stimulus, provocation, assumption inversion, concept fan, forced analogy, SCAMPER, six hats, or worst possible idea. Use when a user asks for lateral thinking, fresh or non-obvious ideas, a different angle, help escaping predictable brainstorming, challenging a fixed constraint or assumption, widening a stuck solution space, generating variations of an existing idea, or examining a creative decision from multiple perspectives. Apply to product, strategy, naming, copy, workflow, service, and design ideation. Do not use to perform debugging, code review, calculations, factual research, or implementation; redesigning those processes creatively is in scope.

License 许可
MIT
所属仓库
ham-zax/webharness
最近更新
2026-11-15
Stars
★ 0
Forks
0

01 前言 Front Matter

name
lateral-thinking
description
Route creative problems through one of eight structured lateral-thinking methods: random stimulus, provocation, assumption inversion, concept fan, forced analogy, SCAMPER, six hats, or worst possible idea. Use when a user asks for lateral thinking, fresh or non-obvious ideas, a different angle, help escaping predictable brainstorming, challenging a fixed constraint or assumption, widening a stuck solution space, generating variations of an existing idea, or examining a creative decision from multiple perspectives. Apply to product, strategy, naming, copy, workflow, service, and design ideation. Do not use to perform debugging, code review, calculations, factual research, or implementation; redesigning those processes creatively is in scope.

02 资源文件 12

03 SKILL.md 正文

Lateral Thinking

Purpose

Diagnose the shape of a creative block, choose exactly one technique, and run that technique visibly. Preserve failed branches and abandoned attempts instead of making every move look successful.

Core contract

  • Treat the user's concrete creative target as the input.
  • Return a structured ideation session as the output: the technique steps, promising directions, visible dead ends, a meta-pattern, and optional next moves.
  • Use no connector by default. Use external tools only when the user's target independently requires current facts or connected data.
  • Ask at most one focused clarification if the target or symptom is materially unclear.
  • Run exactly one technique per pass. Offer another technique only after finishing the first.
  • Do not push the user to commit. Diverge first; leave convergence to the user unless the chosen technique explicitly includes synthesis.
  • Refuse requests to perform analytical work such as debugging, code review, calculations, or implementation. Creative redesign of an analytical process remains valid.

Route the symptom

Symptom Technique Reference
Ideas all feel similar or predictable Random Stimulus references/random-stimulus.md
A rule or constraint feels unbreakable Provocation references/provocation.md
Requirements hide unquestioned beliefs Assumption Inversion references/inversion.md
The current solution may answer the wrong problem Concept Fan references/concept-fan.md
The solution works but feels derivative Forced Analogy references/analogy.md
One existing idea needs disciplined variations SCAMPER references/scamper.md
A decision is moving too fast or from one angle Six Hats references/six-hats.md
Everything feels timid, safe, or over-optimized Worst Possible Idea references/worst-idea.md

Routing procedure

  1. Diagnose the user's symptom from the table.
  2. If two techniques seem plausible, pick the one matching the user's immediate blockage rather than combining methods.
  3. If the symptom is unclear, ask exactly one concrete question. Prefer questions such as "What feels stuck: the problem framing, a fixed constraint, or the sameness of the ideas?"
  4. Read the selected reference file and follow it inline.
  5. Preserve the technique's honesty mechanics. Show empty operations, dead flips, failed mappings, disqualified ideas, or abandoned stimuli where required.
  6. End with the technique's meta-pattern. Explain what the successes and failures collectively reveal.
  7. Offer a small set of next moves: deepen one direction, repeat the same method with fresh material, switch technique, or stop.

Shared quality rules

Make failure visible

Do not retrofit every prompt into a winner. A credible session contains misses. Keep them visible and state why they failed the technique's own test.

Keep the chain inspectable

Show enough intermediate work for the user to see how a direction emerged. Do not jump from a technique prompt directly to a polished idea if the reference requires a property list, mapping, movement step, assumption flip, or badness mechanism.

Prefer structural novelty

Reject cosmetic renaming as novelty. Favor changes in roles, flows, sequence, incentives, constraints, timing, ownership, or system behavior.

Name the meta-pattern

After the batch, compare both winners and failures. State the structural insight that explains what kept working, what kept dying, or what hidden assumption controls the space.

Bound the batch

Respect each technique's maximum batch size. Depth and honesty matter more than filling every slot.

Technique-specific references

  • references/random-stimulus.md - force-fit unrelated stimuli, with a stimulus pool.
  • references/provocation.md - generate deliberately absurd Po statements and extract movement.
  • references/inversion.md - flip assumptions into plausible opposites and hunt for where they are already true.
  • references/concept-fan.md - climb abstraction, fan alternative concepts, and drop back to concrete implementations.
  • references/analogy.md - map the target to distant structurally similar systems and transplant mechanisms.
  • references/scamper.md - transform one existing idea through seven lenses and retain only operations that bite.
  • references/six-hats.md - examine one decision through six unblended passes.
  • references/worst-idea.md - generate plausible terrible solutions, isolate why they are bad, and invert the mechanisms.
  • references/SOURCE.md - source attribution and adaptation notes.

Source and license

This skill adapts the MIT-licensed danium/lateral-thinking repository. Preserve LICENSE.txt and references/SOURCE.md when redistributing substantial portions of this skill.

04 同仓库更多 Skills

ham-zax
ham-zax/webharness

x-content

Create, rewrite, critique, select formats for, discover opportunities for, and learn from X/Twitter content and X Articles for a technical AI-native developer/builder account. Use when turning ideas, source posts, releases, benchmarks, results, conversations, authenticated For You or creator-watch opportunities, or project evidence into an Original, Quote, Thread, Reply, or Article; reviewing article titles/outlines/visual briefs/launch hooks; improving drafts; choosing additive contributions from live X context; or learning from own-account outcomes. Own content intelligence only; compose with agent-browser for live X state and Growth OS for discovery provenance, approvals, measurement, and publication.

★ 0
ham-zax
ham-zax/webharness

writing-plans

Create detailed implementation plans for multi-step software work before editing code. Use when requirements or a specification must become concrete file-level tasks, interfaces, acceptance criteria, risks, rollout, or explicitly required validation. Default to no test creation, test modification, test execution, TDD, regression-test, or coverage work unless the user, authoritative specification, or mandatory repository policy explicitly requires testing.

★ 0
ham-zax
ham-zax/webharness

systematic-debugging

Root-cause debugging for concrete technical failures including bugs, failing builds or tests, integration issues, performance regressions, and unexpected behavior. Use before proposing or implementing a repair when diagnosis is required. Reproduce the symptom, trace the responsible owner, maintain one leading causal hypothesis, and falsify it with the smallest direct evidence. Compose with Causal Coding for source mutation; testing is opt-in and requires independent authorization.

★ 0
ham-zax
ham-zax/webharness

skill-creator

Guide for creating and updating high-quality skills by translating workflows, conventions, and reusable processes into well-structured skills. Includes context, use case examples and spec for skills. Use this skill whenever a user asks to create, update, edit, improve, package, or troubleshoot a skill, and also for conversational questions about skills in ChatGPT (e.g., "What are skills?", "What can I use skills for?", "What are the best skill use cases for me?", "Where can I find my skills?").

★ 0
ham-zax
ham-zax/webharness

reflexion

Self-refinement, multi-perspective critique, verification, and durable lesson curation adapted from NeoLabHQ Reflexion. Use when the user asks to reflect, self-review, critique, double-check, verify and improve prior work, run a rigorous review, memorize lessons, or says "then reflect" after a coding, analysis, or writing task. Supports repository-aware evidence gathering and works without subagents or Claude hooks.

★ 0
ham-zax
ham-zax/webharness

ponytail

Enforce Ponytail's lazy-senior-developer approach for coding, fixing, refactoring, design, dependency choices, and explicit Ponytail modes such as review, audit, debt, gain, and help. Prefer YAGNI, existing code, standard library, native platform features, existing dependencies, low reader load, and the smallest correct diff. For source mutation, keep Causal Coding authoritative for scope, testing authorization, verification cadence, and stopping. On connected WSL/Linux targets, compose with MCP Harness Router and use `wsl-web-harness` for authoritative repository work.

★ 0