dhanesh

Extracts a reusable code pattern from the current repo and authors a portable, validated Agent Skill. Use when you want to capture a logging setup, CI/CD pipeline, observability stack, async messaging pattern, frontend component library, feature-flag middleware, or any other repeatable engineering pattern so it can be replayed across other repos. Produces: a standard-conformant SKILL.md, parameterized code templates in assets/templates/, a PARAMETERS.md documenting every placeholder, then runs validate-skill.sh, scan-leaks.sh, and dry-run-replay.sh as a tiered quality gate. Output is ready to publish via references/publishing.md.

Regression fixture for dry-run-replay header-skip drift.

A clean skill containing a git commit SHA, a UUID, and an embedded base64 image asset — none of which are secrets and none must trip the scanner.

Sets up structured logging for a service using a configurable log level and service name. Produces a logger.config file ready for ingestion by your logging pipeline. Works with any service that reads configuration from a flat config file.

A skill that accidentally contains an AWS access key — should be caught by the scanner.

A skill containing bare base64 secrets ending in equals-sign padding, which must not evade the entropy detector.

A clean skill with no secrets or sensitive identifiers. Uses only normal configuration values and parameterized placeholders.

A skill with compound credential keys like SECRET_KEY and CLIENT_SECRET that must be matched by the generic-credential detector.

Backward reasoning from desired outcome. Derives required conditions by asking 'What must be TRUE?'

Verify ALL artifacts against ALL constraints. Produces a verification matrix showing coverage and gaps

Light mode: 3-phase workflow for simple changes. Use instead of full workflow for bug fixes, small features, or quick iterations.

Generate parallel execution plan from constraint network. Identifies waves, critical path, and bidirectional dependencies

Initialize a constraint manifold for a feature. Creates .manifold/<feature>.json + .manifold/<feature>.md

Interview-driven constraint discovery across 5 categories (business, technical, UX, security, operational)

Surface and resolve constraint conflicts (trade-offs). Identifies direct conflicts, resource tensions, and competing requirements

Generate ALL artifact types from the constraint manifold in one coordinated run - code, tests, docs, runbooks, alerts

Autonomous codebase improvement loop inspired by Karpathy's autoresearch. Iteratively improves code quality, test coverage, performance, and architecture using multi-metric evaluation with diminishing returns detection. USE WHEN user wants to iteratively improve a codebase, run autonomous code improvement, or apply the autoresearch pattern.

Autonomous codebase improvement loop inspired by Karpathy's autoresearch. USE WHEN user wants to iteratively improve a codebase, run autonomous code improvement, or apply the autoresearch pattern. Individual commands use /autoresearch directly.

This skill should be ALWAYS ACTIVE during software development. It automatically enforces the 10 Engineering Commandments when the user is writing code, planning features, creating specifications, designing architecture, or reviewing code. Auto-activates on keywords like "implement", "build", "create", "refactor", "design", "architecture", "component", "service", "endpoint", or "module".

This skill should be used when the user runs "/commandments", asks to "evaluate the codebase against engineering commandments", "assess engineering maturity", "run a commandments assessment", "check codebase maturity levels", "how mature is this codebase", "engineering best practices audit", "code quality assessment against commandments", or "generate a commandments report". It evaluates the current repository against 10 Engineering Commandments using a 5-level maturity model and generates a detailed report with evidence-backed assessments and stack-specific actionable improvements.