Parse Markdown feature proposals into structured data with completeness scores.
npx skills add https://github.com/JuniYadi/claude-code --skill feature-parser
Please help me install this Agent Skill. Skill: feature-parser Source: https://github.com/JuniYadi/claude-code/tree/main/super-dev/skills/feature-parser Command: npx skills add https://github.com/JuniYadi/claude-code --skill feature-parser
Feature proposals are often free-form and inconsistent, making automated analysis and decision-making harder.
Use this skill to parse a Markdown feature proposal by providing the proposal as input. The parsed output includes the title, overview, goals, requirements, constraints, success criteria, related context, and a computed completeness score suitable for downstream tooling.
High-intent search queries and answers about installing and using this skill.
You parse Markdown feature proposals by analyzing standard template sections to extract title, overview, goals, requirements, constraints, and success criteria into a machine-readable structured representation.
Structured data extraction from Markdown proposals pulls title, overview, goals, requirements, and constraints into a reproducible schema, generating keyword extraction and a computed completeness score for automated indexing.
Yes, you can extract keywords and related context from Markdown proposals. The parser analyzes standard template sections to output a reproducible schema including computed completeness scores and extracted keywords.
Yes, feature parsing supports completeness scoring by evaluating the extracted title, goals, requirements, and success criteria from Markdown proposals to compute a score suitable for downstream judge agents.
The best way to index Markdown feature proposals is to parse them into a structured, machine-readable representation with a reproducible schema, making the extracted goals and requirements suitable for codebase-analyzer agents.
Parsing Markdown proposals without a standard template limits the extraction of goals, requirements, and constraints, as the parser relies on standard template sections to generate a structured representation and completeness score.
soeirooCreate structured design briefs with problem statements, audience, constraints, and success criteria.
pelchersParse academic PDFs, DOCX, Markdown, HTML, and web pages into structured JSON metadata and outlines.
agentclashConfigure LLM-as-judge scoring with rubric, assertion, reference, and n-wise ranking modes.
arisngGenerate standardized markdown issue documents with YAML frontmatter and templates.
