skills/meta/creating-skills/.SKILL.md.swp

b0VIM 9.1<00>M<EFBFBD>h<EFBFBD>`<0E><>jessem4.local~jesse/Documents/GitHub/superpowers/superpowers/.worktrees/amplifier-skills/skills/meta/creating-skills/SKILL.md
3210#"! U
Gad<00>n<00><00>{<00><00>qmlZYML<00>
<00>
8
7
<00><00>76"!<00><00>DC<00>
<00>
<00>
<00>
<00>
n
:
<00>	<00>	r	,	<00><00>o%$<00><00><00><00><00><00>^-<00><00><00><00><00>zyk<00><00><00>}|ed`XJ<00><00><00><00><00><00>K<00><00><00><00><00><00><00><00>xH<00><00><00><00><00><00><00>uFE6<00><00>Bullet list with SYMPTOMS and use cases[Small inline flowchart IF decision non-obvious]## When to UseWhat is this? Core principle in 1-2 sentences.## Overview# Skill Name---dependencies: (optional) Required tools/librarieslanguages: all | [typescript, python] | etcversion: 1.0.0when_to_use: Symptoms and situations when you need this (CSO-critical)description: One-line summary of what this doesname: Human-Readable Name---```markdown## SKILL.md Structure- Everything else- Code patterns (< 50 lines)- Principles and concepts**Keep inline:**2. **Reusable tools** - Scripts, utilities, templates1. **Heavy reference** (100+ lines) - API docs, comprehensive syntax**Separate files for:****Flat namespace** - all skills in one searchable location```    supporting-file.*     # Only if needed    SKILL.md              # Main reference (required)  skill-name/skills/```## Directory StructureAPI docs, syntax guides, tool documentation (office docs)### ReferenceWay of thinking about problems (flatten-with-flags, test-invariants)### PatternConcrete method with steps to follow (condition-based-waiting, root-cause-tracing)### Technique## Skill Types- Project-specific conventions (put in CLAUDE.md)- Standard practices well-documented elsewhere- One-off solutions**Don't create for:**- Others would benefit- Pattern applies broadly (not project-specific)- You'd reference this again across projects- Technique wasn't intuitively obvious to you**Create when:**## When to Create a SkillThe entire skill creation process follows RED-GREEN-REFACTOR.| **Refactor cycle** | Find new rationalizations → plug → re-verify || **Watch it pass** | Verify agent now complies || **Minimal code** | Write skill addressing those specific violations || **Watch it fail** | Document exact rationalizations agent uses || **Write test first** | Run baseline scenario BEFORE writing skill || **Refactor** | Close loopholes while maintaining compliance || **Test passes (GREEN)** | Agent complies with skill present || **Test fails (RED)** | Agent violates rule without skill (baseline) || **Production code** | Skill document (SKILL.md) || **Test case** | Pressure scenario with subagent ||-------------|----------------|| TDD Concept | Skill Creation |## TDD Mapping for Skills**Skills are NOT:** Narratives about how you solved a problem once**Skills are:** Reusable techniques, patterns, tools, reference guidesA **skill** is a reference guide for proven techniques, patterns, or tools. Skills help future Claude instances find and apply effective approaches.## What is a Skill?See skills/testing/test-driven-development for the fundamental RED-GREEN-REFACTOR cycle. This skill adapts TDD to documentation.**Core principle:** If you didn't watch an agent fail without the skill, you don't know if the skill teaches the right thing.You write test cases (pressure scenarios with subagents), watch them fail (baseline behavior), write the skill (documentation), watch tests pass (agents comply), and refactor (close loopholes).**Creating skills IS Test-Driven Development applied to process documentation.**## Overview# Creating Skills---languages: allversion: 4.1.0when_to_use: When you discover a technique, pattern, or tool worth documenting for reuse. When editing existing skills. When asked to modify skill documentation. When you've written a skill and need to verify it works before deploying.description: TDD for process documentation - test with subagents before writing, iterate until bulletproofname: Creating Skills---adB<00>
<00><00><00><00><00><00>-<00><00><00><00>If you follow TDD for code, follow it for skills. It's the same discipline applied to documentation.Same benefits: Better quality, fewer surprises, bulletproof results.Same cycle: RED (baseline) → GREEN (write skill) → REFACTOR (close loopholes).Same Iron Law: No skill without failing test first.**Creating skills IS TDD for process documentation.**## The Bottom Line
-												refactor: split emergent-patterns into focused problem-solving skills

**Restructure:**
- Split detecting-emergent-patterns (216 lines) into 5 focused skills (~60 lines each)
- Move tracing-lineages to skills/research/ (better category fit)
- Create skills/problem-solving/ category

**New problem-solving skills:**
- simplification-cascades: Find one insight that eliminates multiple components
- collision-zone-thinking: Force unrelated concepts together for breakthroughs
- meta-pattern-recognition: Spot patterns in 3+ domains
- inversion-exercise: Flip assumptions to reveal alternatives
- scale-game: Test at extremes to find fundamental limits
- when-stuck: Dispatch skill that maps stuck-symptoms to techniques

**Improvements:**
- Symptom-based when_to_use (what you'd actually think/feel)
- Quick reference tables for rapid scanning
- Pattern-based triggers (not exact phrase matching)
- Cross-references from brainstorming for discoverability

Each skill now: scannable in 30 seconds, applicable immediately, focused on one technique.

											
										
										
											2025-10-10 14:34:51 -07:00
+								b0VIM 9.1<00>M<EFBFBD>h<EFBFBD>`<0E><>jessem4.local~jesse/Documents/GitHub/superpowers/superpowers/.worktrees/amplifier-skills/skills/meta/creating-skills/SKILL.md
3210#"! U
 								Gad<00>n<00><00>{<00><00>qmlZYML<00>
<00>
8
7
<00><00>76"!<00><00>DC<00>
 								<00>
 								<00>
 								<00>
 								<00>
 								n
 								:
 								<00>	<00>	r	,	<00><00>o%$<00><00><00><00><00><00>^-<00><00><00><00><00>zyk<00><00><00>}|ed`XJ<00><00><00><00><00><00>K<00><00><00><00><00><00><00><00>xH<00><00><00><00><00><00><00>uFE6<00><00>Bullet list with SYMPTOMS and use cases[Small inline flowchart IF decision non-obvious]## When to UseWhat is this? Core principle in 1-2 sentences.## Overview# Skill Name---dependencies: (optional) Required tools/librarieslanguages: all | [typescript, python] | etcversion: 1.0.0when_to_use: Symptoms and situations when you need this (CSO-critical)description: One-line summary of what this doesname: Human-Readable Name---```markdown## SKILL.md Structure- Everything else- Code patterns (< 50 lines)- Principles and concepts**Keep inline:**2. **Reusable tools** - Scripts, utilities, templates1. **Heavy reference** (100+ lines) - API docs, comprehensive syntax**Separate files for:****Flat namespace** - all skills in one searchable location```    supporting-file.*     # Only if needed    SKILL.md              # Main reference (required)  skill-name/skills/```## Directory StructureAPI docs, syntax guides, tool documentation (office docs)### ReferenceWay of thinking about problems (flatten-with-flags, test-invariants)### PatternConcrete method with steps to follow (condition-based-waiting, root-cause-tracing)### Technique## Skill Types- Project-specific conventions (put in CLAUDE.md)- Standard practices well-documented elsewhere- One-off solutions**Don't create for:**- Others would benefit- Pattern applies broadly (not project-specific)- You'd reference this again across projects- Technique wasn't intuitively obvious to you**Create when:**## When to Create a SkillThe entire skill creation process follows RED-GREEN-REFACTOR.| **Refactor cycle** | Find new rationalizations → plug → re-verify || **Watch it pass** | Verify agent now complies || **Minimal code** | Write skill addressing those specific violations || **Watch it fail** | Document exact rationalizations agent uses || **Write test first** | Run baseline scenario BEFORE writing skill || **Refactor** | Close loopholes while maintaining compliance || **Test passes (GREEN)** | Agent complies with skill present || **Test fails (RED)** | Agent violates rule without skill (baseline) || **Production code** | Skill document (SKILL.md) || **Test case** | Pressure scenario with subagent ||-------------|----------------|| TDD Concept | Skill Creation |## TDD Mapping for Skills**Skills are NOT:** Narratives about how you solved a problem once**Skills are:** Reusable techniques, patterns, tools, reference guidesA **skill** is a reference guide for proven techniques, patterns, or tools. Skills help future Claude instances find and apply effective approaches.## What is a Skill?See skills/testing/test-driven-development for the fundamental RED-GREEN-REFACTOR cycle. This skill adapts TDD to documentation.**Core principle:** If you didn't watch an agent fail without the skill, you don't know if the skill teaches the right thing.You write test cases (pressure scenarios with subagents), watch them fail (baseline behavior), write the skill (documentation), watch tests pass (agents comply), and refactor (close loopholes).**Creating skills IS Test-Driven Development applied to process documentation.**## Overview# Creating Skills---languages: allversion: 4.1.0when_to_use: When you discover a technique, pattern, or tool worth documenting for reuse. When editing existing skills. When asked to modify skill documentation. When you've written a skill and need to verify it works before deploying.description: TDD for process documentation - test with subagents before writing, iterate until bulletproofname: Creating Skills---adB<00>
 								<00><00><00><00><00><00>-<00><00><00><00>If you follow TDD for code, follow it for skills. It's the same discipline applied to documentation.Same benefits: Better quality, fewer surprises, bulletproof results.Same cycle: RED (baseline) → GREEN (write skill) → REFACTOR (close loopholes).Same Iron Law: No skill without failing test first.**Creating skills IS TDD for process documentation.**## The Bottom Line