skills/readme-review/SKILL.md
Review the project README to understand what it does and suggest a recommended next step. Use when starting work on an unfamiliar project.
npx skillsauth add sofer/.agents readme-reviewInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Quickly orient yourself in a new project by reviewing the README and suggesting what to do next.
Write a concise summary covering:
Keep the summary brief and focused on essentials.
Based on the project context and README content, suggest ONE recommended next action. Consider:
For new/unfamiliar projects:
/intent to clarify goalsFor projects with clear direction:
For projects lacking documentation:
/requirements to document what exists## Project summary
[Brief summary of what the project does]
**Tech stack:** [languages, frameworks, tools]
**Status:** [development stage or activity level]
## Recommended next step
[One clear recommendation with rationale]
To proceed: [specific command or skill to invoke, if applicable]
/intent, /requirements, /orchestrate) when they fittools
Check whether Claude and Codex have equivalent access to shared agent resources, skills, hooks, plugins, MCP servers, permissions, startup behaviour, and provider-specific adapter config. Use when comparing agent environments, debugging missing capabilities after restart, or deciding whether to symlink a resource or configure a runtime.
testing
Record substantive skill use in an append-only local log. Use after choosing or invoking a non-system skill for real work, when a skill is inspected but not used, or when a skill fails to apply. Do not use for routine system skills or incidental file reads.
testing
Turn a vague or underspecified request into a self-contained problem statement. Use when the user has a rough idea, when a request would fail if handed directly to an agent, or before non-trivial work that needs shared understanding.
data-ai
Append a one-line learning to ~/.agents/learning-log.md. Use when the user types /learning, or when something genuinely worth remembering surfaced during work and the user confirms it should be captured.