Agent skills for Claude Desktop

Expert prompt engineering for creating effective prompts for Claude, GPT, and other LLMs.

Designs and optimizes structured prompts, few-shot examples, and system instructions for reliable LLM workflows.

Transforms user prompts into optimized prompts using frameworks (RTF, RISEN, Chain of Thought, RODES, Chain of Density, RACE, RISE, STAR…

Use when enhancing or optimizing input prompts — transform vague prompts into precision instructions with RSCIT, hallucination guards, and…

Design a learning sequence teaching prompt quality — comparing vague vs. refined prompts to show why specificity and context transform AI…

Activates when the user asks about AI prompts, needs prompt templates, wants to search for prompts, or mentions prompts.chat.

WHEN refining or structuring prompts; NOT executing tasks; outputs XML-tagged instructions with roles, tasks, constraints, and examples.

Prompt the user with pointed questions to extract what is in his head about a project — remaining work, what is being avoided, what really…

Analyze a draft prompt, critique it, match it to ECC ecosystem components, and output a complete optimized prompt the user can paste and…

Analyzes AI interaction history to evaluate technical proficiency, prompting patterns, and AI dependency across various coding assistants.

Use when Codex should work as a coding-agent-native proof planning and review workflow: transform a candidate theorem, proof sketch…

Validates entire engineering proof chain.

Analyze and restructure mathematical proofs for clarity and completeness

Proofreading skill for the Book of Challenges manuscript.

Edits the structure, line of argumentation, organization, shortening, redundancies, contradictions and reading guidance of publishing…

Generate PandaDoc proposals from client information or sales call transcripts.

Orchestrate proposal creation by gathering deal context, validating inputs, invoking proposal-writer skill, and ensuring quality output.

Generates professional Korean B2B sales proposals and RFP responses using industry-standard structures and compliance checks.

PROPOSE-ONLY — mine this host's recent Claude Code transcripts for work that keeps recurring and keeps returning bulk into context, rank…

Architect PROSE-compliant agent primitives for AI-native development.

Capture friction as methodology notes. Three modes — explicit description, contextual (review recent corrections), session mining (scan…