antigravity-claudekit/skills/ck-sequential-thinking/SKILL.md

name, description

name	description
ck-sequential-thinking	Apply step-by-step analysis for complex problems with revision capability. Use for multi-step reasoning, hypothesis verification, adaptive planning, problem decomposition, course correction, debugging with unclear scope.

ck-sequential-thinking

Structured problem-solving via manageable, reflective thought sequences with dynamic adjustment capability.

When to Use

• Complex problem decomposition where scope is unclear
• Adaptive planning with revision capability
• Analysis needing course correction mid-process
• Problems with unclear or emerging scope
• Multi-step solutions requiring context maintenance across steps
• Hypothesis-driven investigation or debugging

Don't Use When

• Problem is straightforward with a clear, direct solution
• Quick lookup or simple retrieval task
• Single-step action with no branching needed

Core Process

1. Start with Loose Estimate

Thought 1/5: [Initial analysis]

Adjust total dynamically as understanding evolves.

2. Structure Each Thought

• Build on previous context explicitly
• Address one aspect per thought
• State assumptions, uncertainties, realizations
• Signal what next thought should address

3. Apply Dynamic Adjustment

• Expand: More complexity discovered → increase total count
• Contract: Simpler than expected → decrease total count
• Revise: New insight invalidates previous → mark revision
• Branch: Multiple approaches → explore alternatives

4. Use Revision When Needed

Thought 5/8 [REVISION of Thought 2]: [Corrected understanding]
- Original: [What was stated]
- Why revised: [New insight]
- Impact: [What changes]

5. Branch for Alternatives

Thought 4/7 [BRANCH A from Thought 2]: [Approach A]
Thought 4/7 [BRANCH B from Thought 2]: [Approach B]

Compare explicitly, converge with decision rationale.

6. Generate & Verify Hypotheses

Thought 6/9 [HYPOTHESIS]: [Proposed solution]
Thought 7/9 [VERIFICATION]: [Test results]

Iterate until hypothesis verified.

7. Complete Only When Ready

Mark final: Thought N/N [FINAL]

Complete when:

• Solution verified
• All critical aspects addressed
• Confidence achieved
• No outstanding uncertainties

Application Modes

Explicit: Use visible thought markers when complexity warrants visible reasoning or user requests a breakdown.

Implicit: Apply methodology internally for routine problem-solving where thinking aids accuracy without cluttering the response.

Integration

ck-sequential-thinking is called by other skills:

• ck-debug uses it for complex root cause tracing
• ck-fix uses it for deep complexity assessments
• ck-web-testing uses it for analyzing test failure patterns