All skills
oaustegard avatar

/featuring

@a8e6362

Generate hierarchical _FEATURES.md files that describe what a codebase DOES from a user/consumer perspective, anchored to source symbols via tree-sitting. Supports large complex codebases through feature-driven decomposition into sub-feature files. Uses a multi-pass synthesis: orientation → detail → overview rewrite. Use when someone says "what does this do", "document features", "feature inventory", "_FEATURES.md", or needs to understand a codebase's purpose before modifying it. Complements tree-sitting (structural) with semantic (why/what-for) layer.

Use this Skill: https://skilld.dev/gh/oaustegard/claude-skills/featuring

This session only. Nothing lands on disk.

README.md

≈306 tokens on demand. Your agent reads this file only when SKILL.md points to it.

featuring

Generate hierarchical _FEATURES.md files that describe what a codebase does from a user/consumer perspective, anchored to source symbols via tree-sitting.

Features

  • Top-down feature documentation — organized by capability, not by file or directory structure
  • Hierarchical decomposition — complex capability areas get their own sub-feature files with progressive disclosure
  • Multi-pass synthesis — orientation scan, detailed extraction, then overview rewrite (written last, not first)
  • Symbol anchoring — every feature references key symbols via file#symbol notation
  • Drift detection — check.py validates all symbol references against the live codebase, catching renames, deletions, and uncovered new APIs
  • CI-ready — check script returns exit codes suitable for GitHub Actions or pre-commit hooks

Dependency

Requires the tree-sitting skill for AST-based code scanning.

Relationship to Other Skills

  • tree-sitting provides the structural inventory (what symbols exist)
  • featuring adds the semantic layer (why they exist, what they accomplish together)
  • generating-lattice offers stricter bidirectional traceability when needed

Source: SKILL.md on GitHub

No alerts14d3 checks · Risk SAFE
  • Gen Agent Trust Hub14d

    The skill is safe for its intended purpose but contains a potential indirect prompt injection surface as it processes external source code and documentation.

  • Socket14d

    No alerts

  • Snyk14d

    Risk: LOW · No issues

Signed by skilld at a8e6362. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated last month
metadata
{
  "version": "0.4.0"
}

README badge

README badge for oaustegard/claude-skills/featuring