assist-software

12 mods across 1 repository, 2 stars between them.

assist-software/claude-code-repository

Plugin Claude Code

Audit, author, fix, and initialise LLM prompts in any codebase against a shared best-practices rubric. Architecture-aware: understands where prompts belong in layered/clean architectures. Creates a persistent docs/prompt-engineering/ workspace per project.

2 2mo ago A tokens not measured

context-gatherer

03

assist-software/claude-code-repository

Agent

Reads a codebase's READMEs, feature docs, configuration, and surrounding business logic to build a concise project-context brief used when authoring new prompts. Read-only.

2 2mo ago A 40 tokens

project-scanner

04

assist-software/claude-code-repository

Agent

Scans a codebase for LLM usage, extracts prompt inventory and project conventions in a single pass. Used by /prompt-init to populate OVERVIEW.md and rules/project-conventions.md. Read-only.

2 2mo ago A 45 tokens

prompt-discovery

05

assist-software/claude-code-repository

Agent

Sweeps a codebase (any language) to locate every LLM prompt and prompt template, returning a structured inventory with a confidence score per hit. Use as the first stage of an audit. Read-only.

2 2mo ago A 46 tokens

prompt-reviewer

06

assist-software/claude-code-repository

Agent

Reviews one prompt (or a small batch) against the prompt-best-practices rubric and returns findings with severities and concrete suggested diffs. Runs in an isolated context so many reviews can run in parallel. Read-only — never edits files.

2 2mo ago A 53 tokens

prompt-writer

07

assist-software/claude-code-repository

Agent

Authors new, best-practice prompt templates for a feature using a project-context brief and the prompt-best-practices rubric. Proposes the prompt, its placement in the architecture, call parameters, and a starter eval — as diffs for approval.

2 2mo ago A 54 tokens

prompt-audit

08

assist-software/claude-code-repository

Command

Discover and review LLM prompts in this codebase against the best-practices rubric. Reports findings and proposed diffs in the terminal — never edits without approval.

2 2mo ago A 33 tokens

prompt-author

09

assist-software/claude-code-repository

Command

Author new best-practice prompt(s) for a feature by reading the codebase context, then propose them (with correct architecture placement, call params, and a starter eval) for approval.

2 2mo ago A 38 tokens

prompt-init

11

assist-software/claude-code-repository

Command

Initialise the prompt-engineering workspace for this project. Creates docs/prompt-engineering/ with a rules folder, a features folder, and an OVERVIEW of any existing LLM prompts. Run once per project; safe to re-run.

2 2mo ago C 48 tokens

assist-software/claude-code-repository

Skill Claude CodeCodex

The single source of truth for prompt-engineering best practices used by this suite. Provides a named, severity-graded rubric for reviewing prompts and a set of guidelines for authoring new ones, including where prompts belong in layered/clean architectures. Read this whenever auditing, authoring, or fixing an LLM…

2 2mo ago A 69 tokens