Repository
cashew-labs/libretto agent skills
- skills
- 21
- GitHub stars
- 904
GitHub description: “The AI toolkit for building reliable browser automations”
- Stars
- 904 (71 forks)
- Licence
- MIT
- Last push
- Aug 2026
- Created
- Mar 2026
- Homepage
- libretto.sh
- automation
- browser
- claude-code
- codex
- rpa
Install all skills
npx skills add cashew-labs/librettoAdd --skill <name> for a single skill and -a <agent> to choose the agent (see the agent guides).
Skills in cashew-labs/libretto, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Lays out a minimal, iteration-first approach to writing system prompts for LLM agents, with model-specific notes for Claude, GPT, Gemini, and Codex. | cashew-labs/ | 904 | — | ~570 | Automated safety check: Pass | MIT | 1 mo ago |
| 2 | Works through the review comments on a pull request one by one: fetches the threads, makes the fixes, runs type-check, build and lint, pushes, and resolves the threads. | cashew-labs/ | 904 | — | ~532 | Automated safety check: Pass | MIT | 1 mo ago |
| 3 | Design rules for command-line tools: subcommand-scoped help, actionable success output, debuggable failures, stable output, meaningful exit codes and a --json mode. | cashew-labs/ | 904 | — | ~781 | Automated safety check: Pass | MIT | 1 mo ago |
| 4 | Drives desktop Electron apps already installed on your machine, such as Slack, Discord or VS Code, by relaunching them with a debugging port and using the Libretto CLI. | cashew-labs/ | 904 | — | ~967 | Automated safety check: Pass | MIT | 1 mo ago |
| 5 | Resolves Git merge, rebase and cherry-pick conflicts by reading the PRs behind each side, keeping both intents and asking you when they truly clash. | cashew-labs/ | 904 | — | ~1.1k | Automated safety check: Pass | MIT | 1 mo ago |
| 6 | Researches the codebase and relevant docs, asks clarifying questions, then writes a spec sheet in specs/ for a significant feature or complex fix. | cashew-labs/ | 904 | — | ~2.4k | Automated safety check: Pass | MIT | 1 mo ago |
| 7 | Turns the current session's code changes into a Markdown walkthrough shown in a native Glimpse window, with highlighted code, rendered diffs and review feedback. | cashew-labs/ | 904 | — | ~1.5k | Automated safety check: Pass | MIT | 1 mo ago |
| 8 | 8.Push Commit and push changes, creating or updating a PR as needed. | cashew-labs/ | 904 | — | ~1.1k | Automated safety check: Pass | MIT | 1 mo ago |
| 9 | Stage ALL changes in the repository (not just session changes), commit, and push. | cashew-labs/ | 904 | — | ~1.1k | Automated safety check: Pass | MIT | 1 mo ago |
| 10 | Create a code-based implementation spec in the specs/ directory for a significant feature, fix, or refactor. | cashew-labs/ | 904 | — | ~1.9k | Automated safety check: Warn | MIT | 1 mo ago |
| 11 | 11.Spec Review Review a spec for under-specified areas, bugs, and adherence to the spec requirements in this skill. | cashew-labs/ | 904 | — | ~1.2k | Automated safety check: Pass | MIT | 1 mo ago |
| 12 | Write and edit test files that model real user flows. An agent skill from cashew-labs/libretto. | cashew-labs/ | 904 | — | ~535 | Automated safety check: Pass | MIT | 1 mo ago |
| 13 | Get nicely formatted output of the last review comments on a PR. | cashew-labs/ | 904 | — | ~562 | Automated safety check: Pass | MIT | 1 mo ago |
| 14 | Implement a single phase of a spec. An agent skill from cashew-labs/libretto. | cashew-labs/ | 904 | — | ~752 | Automated safety check: Pass | MIT | 1 mo ago |
| 15 | 15.Libretto Browser automation CLI for building, maintaining, and running browser automation workflows by inspecting live pages and prototyping interactions. | cashew-labs/ | 904 | — | ~5.4k | Automated safety check: Pass | MIT | 1 mo ago |
| 16 | Read-only Libretto workflow for diagnosing live browser state without clicks, typing, navigation, or mutation requests. | cashew-labs/ | 904 | — | ~1.1k | Automated safety check: Pass | MIT | 1 mo ago |
| 17 | 17.Review Expert code review specializing in simplicity and correctness. | cashew-labs/ | 904 | — | ~1.4k | Automated safety check: Pass | MIT | 1 mo ago |
| 18 | 18.Summarize Summarize a spec or current changes into a format suitable for sharing on Slack. | cashew-labs/ | 904 | — | ~233 | Automated safety check: Pass | MIT | 1 mo ago |
| 19 | 19.Errore errore is Go-style error handling for TypeScript: return errors instead of throwing them. | cashew-labs/ | 904 | — | ~6.9k | Automated safety check: Pass | MIT | 1 mo ago |
| 20 | Guide for writing effective technical documentation, specs, and markdown files. | cashew-labs/ | 904 | — | ~245 | Automated safety check: Pass | MIT | 1 mo ago |
| 21 | 21.Update Docs Update AGENTS.md files based on session learnings about a topic. | cashew-labs/ | 904 | — | ~278 | Automated safety check: Pass | MIT | 1 mo ago |
Questions, answered from the data.
What is the best skill in cashew-labs/libretto?
System Prompt Writing Guide from cashew-labs/libretto ranks first of the 21 skills in cashew-labs/libretto listed here, with the highest score: its repository has 904 GitHub stars, its SKILL.md loads about 570 tokens and it passes the automated safety check with no findings. Next come Address PR Review Comments and CLI Development.
Are the skills in cashew-labs/libretto official?
None yet. All 21 skills in cashew-labs/libretto listed here come from community repositories; a skill counts as official when the product's own GitHub organization publishes it.
How do I install all skills from cashew-labs/libretto?
Run npx skills add cashew-labs/libretto in your project: the open-source skills CLI installs the repository's skills into your coding agent's skills folder. To install a single skill, open its page here for the exact command.
How are these skills ranked?
By Skill Navigator score, which combines the GitHub stars of the skill's repository (shared across that repo's skills and discounted for large collections), how many other GitHub owners carry a copy of the skill, and automated SKILL.md quality checks, minus penalties for safety-check warnings and for each further skill from the same repository. Skills that fail the safety check are not listed.