ReddRadar
Agent skill
docs-review
Review all project documentation against the current codebase and fix inaccuracies. Only modifies documentation files.
Install this agent skill to your Project
npx add-skill https://github.com/njbrake/agent-of-empires/tree/main/.claude/skills/docs-review
SKILL.md
Documentation Review
Review all project documentation for accuracy against the current codebase. Fix any outdated, incorrect, or missing information.
Scope
Documentation files to review:
README.mdCLAUDE.md- All files in
docs/(guides, CLI reference, installation, quick start, etc.) - Any other
.mdfiles at the repository root
Source code to cross-reference:
- CLI command definitions in
src/cli/(clap structs, subcommands, flags, arguments) - Configuration structs in
src/session/(config fields, defaults, validation) - Supported agents and detection logic in
src/process/ - TUI key bindings and navigation in
src/tui/ - Docker/sandbox configuration in
src/docker/ - Git worktree operations in
src/git/ - Feature flags and capabilities throughout
src/
Instructions
-
Read every documentation file listed above.
-
For each documentation file, cross-reference its claims against the actual source code:
- CLI flags and arguments: compare against clap definitions in
src/cli/ - Configuration options: compare against config structs in
src/session/ - Supported agents: compare against agent detection in
src/process/ - Key bindings: compare against input handling in
src/tui/ - Installation steps: verify scripts in
scripts/match documented commands - Feature descriptions: verify features exist and work as documented
- CLI flags and arguments: compare against clap definitions in
-
For each discrepancy found:
- Fix the documentation to match the source code (never the reverse)
- Keep the fix minimal and precise
- Preserve the existing writing style and tone of the document
-
Do NOT modify any non-documentation files. Never edit
.rs,.toml,.yml,.yaml,.sh,.js,.json, or any other source/config files. -
After reviewing all files, provide a summary of what was changed and why. If no changes were needed, report that all documentation is accurate.
What to look for
- CLI commands, flags, or arguments that have been added, removed, or renamed
- Configuration options that have changed defaults, names, or behavior
- Features described in docs that no longer exist
- Features in the code that are not documented
- Incorrect file paths or directory references
- Outdated installation instructions or version requirements
- Key bindings that have changed
- Supported agent lists that are out of date
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
njbrake/agent-of-empires
aoe
Manage AI coding agent sessions via Agent of Empires (aoe)
davila7/claude-code-templates
verl-rl-training
Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.
davila7/claude-code-templates
openrlhf-training
High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.
davila7/claude-code-templates
gguf-quantization
GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.
davila7/claude-code-templates
Claude Code Guide
Master guide for using Claude Code effectively. Includes configuration templates, prompting strategies "Thinking" keywords, debugging techniques, and best practices for interacting with the agent.
davila7/claude-code-templates
qdrant-vector-search
High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance.
Didn't find tool you were looking for?