second-claude-code

Do/Produce phase -- apply strategic frameworks such as SWOT, RICE, OKR, and Lean Canvas

Batch parallel execution -- decompose large tasks into independent units and run concurrently

Plan/Gather phase -- collect knowledge into PARA-classified storage

Plan/Gather phase -- find and install new skills beyond the core 8

Maintainer loop -- benchmark and evolve prompt assets inside isolated branches

PDCA cycle -- orchestrate Plan→Do→Check→Act with quality gates

Act/Refine phase -- iterative improvement until quality target met

Plan/Gather phase -- deep autonomous research on any topic

Check/Verify phase -- multi-perspective review with consensus gate

Observe and synthesize a persistent user identity profile (SOUL.md)

Do/Produce phase -- build and run PDCA pipelines

Do/Produce phase -- newsletter, article, shorts, report, social

Find specific shared concepts between new items and existing knowledge

Adversarial review that attacks the weakest points. Use when you want stress-testing before publishing or presenting. Examples: "Attack this proposal", "What would a skeptic say about this?", "Find the holes in this argument".

Data analysis and pattern recognition. Use after research collection to synthesize findings into structured insights. Examples: "Analyze these research findings", "Find patterns in this data", "Identify contradictions across these sources".

Execute pipeline steps sequentially with state persistence

Score skill candidates using weighted criteria

Content editing and quality improvement. Use when content exists and needs refinement based on feedback. Examples: "Improve the flow of this article", "Apply these review notes", "Tighten the argument in section 3".

Web search and data collection. Use when you need to gather information on a topic from multiple sources before analysis or writing. Examples: "Research competitor pricing", "Find recent stats on AI adoption", "Collect expert opinions on remote work trends".

Tone and audience-fit review. Use when content must preserve a specific voice or match a target audience consistently. Examples: "Check whether this sounds like our newsletter voice", "Review tone consistency in this article".

Execute a single pipeline step by reading input and writing output

Inspect skill candidates by reading their README and SKILL.md

Strategic framework application. Use when you need structured strategic analysis using established frameworks. Examples: "SWOT analysis of our product", "Porter's Five Forces for the market", "Jobs-to-be-Done analysis for our users".

Search external sources for skills and packages

User soul observer and synthesizer — captures behavioral patterns across sessions, resolves contradictions as conditional rules, proposes soul evolution with evidence. Examples: "Synthesize my soul from observations", "What does my session history reveal about me?", "Propose an update to my SOUL.md based on this session".

Fact and source verification. Use before publishing any content that contains statistics, quotes, dates, or factual claims. Examples: "Verify the stats in this article", "Check all claims in this report", "Are these numbers accurate?".

Long-form content creation. Use when you need polished written output based on research and analysis. Examples: "Write a newsletter about AI trends", "Draft a market analysis report", "Create a thought leadership article on remote work".

Structure and readability review. Use when a draft or code review needs a focused pass on flow, organization, and formatting. Examples: "Check the structure of this report", "Review whether this code review is organized clearly".

Deep logic and structure review. Use for thorough quality review of documents before publication or delivery. Examples: "Review this report for logical gaps", "Check if the argument holds up", "Find structural weaknesses in this article".

Use when applying strategic frameworks such as SWOT, RICE, OKR, or GTM

Use when decomposing large tasks into independent parallel units

Use when collecting URLs, notes, files, or excerpts into structured PARA knowledge

Use when the current skills cannot handle a task and new skills are needed

Use when benchmarking and evolving prompt assets through a fixed-suite optimization loop

Use when running a PDCA cycle across research, production, review, and refinement

Use when iteratively improving a draft until it meets a review target

Use when researching a topic through iterative web exploration and synthesis

Use when reviewing content, strategy, or code with parallel specialized reviewers

Use when observing user patterns and synthesizing a persistent identity profile

Use when translating content between English and Korean with formatting preservation

Use when chaining multiple /scc commands into a reusable workflow

Use when producing newsletters, articles, reports, shorts, or social content

8 hooks across 8 events