New: 97,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Implement Spec

by cashew-labs in cashew-labs/libretto

Implement a single phase of a spec. An agent skill from cashew-labs/libretto.

MITAuto-check passedTesting & QA

Install Implement Spec

skills CLI
$ npx skills add cashew-labs/libretto --skill implement-spec -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install cashew-labs/libretto implement-spec --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/cashew-labs/libretto.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/implement-spec .claude/skills/implement-spec && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
implement-spec
GitHub stars
904
Token cost
~752 tokens
SKILL.md length
460 words
Files
1
Skills in repo
21
Repo updated
First seen
Licence
MIT

At a glance

Implement a single phase of a spec. An agent skill from cashew-labs/libretto.

  • Works in 10 steps: Read and understand the spec → Read all important files → Implement the phase → …
  • Given a spec file and a phase number to implement
  • SKILL.md covers 1. Read and understand the spec, 2. Read all important files, 3. Implement the phase and 4. Verify goals, plus 6 more sections
  • Calls pnpm

What it does

Implement Spec is an agent skill from cashew-labs/libretto. Implement a single phase of a spec. Use when given a spec file and a phase number to implement.

Its SKILL.md is about 750 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Testing & QA. It works with pnpm. The repository describes itself as: The AI toolkit for building reliable browser automations. The licence is MIT.

When your agent uses it

  • Given a spec file and a phase number to implement

Example prompts

  • “/implement-spec”

Workflow steps

10 steps, taken from the step headings in SKILL.md.

  1. Read and understand the spec
  2. Read all important files
  3. Implement the phase
  4. Verify goals
  5. Mark tasks complete
  6. Do not commit
  7. Handle user feedback
  8. Update the spec before committing
  9. Future work
  10. Handoff

What it can do on your machine

Read from SKILL.md and the folder at commit 41ab782. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • pnpm

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use pnpm, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Implement Spec loads about 752 tokens when it runs. Until then it costs about 28 tokens; SKILL.md has 460 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~28
When it runs · the whole SKILL.md, loaded when a task matches
~752

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from cashew-labs/libretto at commit 41ab782, republished under its MIT licence (© cashew-labs). 460 words, ~752 tokens.

Download SKILL.mdSave it as .claude/skills/implement-spec/SKILL.md (or your agent's skills folder).
name
implement-spec
description
Implement a single phase of a spec. Use when given a spec file and a phase number to implement.

Implement the specified phase of the given spec file.

Ultrathink. Follow these steps:

1. Read and understand the spec

Read the entire spec file. Understand the problem overview, solution overview, goals, and non-goals. Pay close attention to the phase you've been asked to implement.

2. Read all important files

Read every file listed in the "Important files/docs/websites for implementation" section of the spec. Also read any external documentation links. Do not start writing code until you thoroughly understand the existing codebase and how your changes fit in.

3. Implement the phase

Work through every task item in the phase, including all success criteria (tests, typechecks, lint checks). A phase is not complete until every task item is done, including running any verification steps.

Run pnpm run typecheck, pnpm test, and pnpm run lint after implementation to catch issues.

4. Verify goals

Check the spec's Goals section. If the phase you just implemented should complete any of those goals, explicitly verify them through integration tests or manual testing of the Electron app using Playwright (see AGENTS.md for Playwright instructions). Do not consider the phase done until achieved goals are verified end-to-end.

5. Mark tasks complete

Mark all completed task items in the spec as done (- [x]) before presenting to the user.

6. Do not commit

When you're done, do not stage or commit your changes. Present the completed work to the user for manual review. The user may request changes.

7. Handle user feedback

If the user asks for changes, implement them. Iterate until the user is satisfied.

Show full SKILL.md (203 more words)Show less

8. Update the spec before committing

Once the user approves and asks you to commit:

  1. Update the spec to reflect what was actually implemented. If the implementation deviated from what was originally specced (e.g. the user asked for a different approach), overwrite the phase content in the spec to match what was done. The spec should always reflect the current state of the codebase, not the original plan.
  2. Check downstream phases. If your spec changes affect later phases, ask the user whether you should update those phases too.
  3. Then commit both the implementation and the updated spec together.

9. Future work

If during implementation you identify work that is not blocking but would be valuable later (big features, refactors, cleanup), propose adding it to a "Future work" section in the spec, placed above the "Important files" section. Confirm with the user before adding.

If the work is blocking (the app is broken without it), it should be done as part of the current spec — either in this phase or added to a subsequent phase.

10. Handoff

When the user asks you to hand off to the next phase, include in the handoff summary a note to load the implement-spec skill.

© cashew-labs, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/implement-spec of cashew-labs/libretto.

Open the folder on GitHubat commit 41ab782

Compare with similar skills

Implement Spec next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Implement Spec compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Implement Spec this skillcashew-labs/libretto904—~752Automated safety check: PassMIT
DeerFlow Smoke Testbytedance/deer-flow83k—~2.5kAutomated safety check: NotesMIT
OpenWork Desktop CDP Driverdifferent-ai/openwork24k—~465Automated safety check: PassCustom licence
E2Egronxb/hot-updater1.8k—~1.6kAutomated safety check: PassCustom licence
Cloud Agents Starterscalar/scalar16k—~1.4kAutomated safety check: PassMIT
Desktop Dual Repo TestEynzof/Hermes-CN-Desktop1.7k—~1.8kAutomated safety check: PassCustom licence

Similar skills

  • DeerFlow Smoke Test

    bytedance/deer-flow

    Walks through an end-to-end smoke test of a DeerFlow deployment: pull the latest code, deploy with Docker or locally, verify services, run health checks and write a report.

    83k GitHub stars~2.5k tokensUpdated today
    Testing & QAAuto-check: notes

  • OpenWork Desktop CDP Driver

    different-ai/openwork

    Drives a running OpenWork desktop window over CDP from the shell to evaluate JS, take screenshots, start sessions and send prompts for hand checks.

    24k GitHub stars~465 tokensUpdated today
    Testing & QAAuto-check passed

  • E2E

    gronxb/hot-updater

    Run end-to-end OTA verification for examples/v0.85.0 with agent-device.

    1.8k GitHub stars~1.6k tokensUpdated today
    Testing & QAAuto-check passed

  • Cloud Agents Starter

    scalar/scalar

    Minimal starter runbook for cloud agents to install dependencies, run packages, execute tests, and troubleshoot the Scalar monorepo quickly.

    16k GitHub stars~1.4k tokensUpdated today
    Testing & QAAuto-check passed

  • Desktop Dual Repo Test

    Eynzof/Hermes-CN-Desktop

    A skill your agent uses when starting or verifying Hermes Agent CN Desktop with the latest Hermes-CN-Desktop and Hermes-CN-Core branches — dev smoke test (pnpm tauri:dev), packaged beta/release…

    1.7k GitHub stars~1.8k tokensUpdated 16 days ago
    Testing & QAAuto-check passed

  • Local CI

    module-federation/core

    Run this repository's local CI parity commands and pnpm run ci:local jobs.

    2.7k GitHub stars~914 tokensUpdated today
    Testing & QAAuto-check passed

More from cashew-labs/libretto

All 21 skills in this repo

  • System Prompt Writing Guide

    cashew-labs/libretto

    Lays out a minimal, iteration-first approach to writing system prompts for LLM agents, with model-specific notes for Claude, GPT, Gemini, and Codex.

    904 GitHub stars~570 tokensUpdated 1 mo ago
    Auto-check passed

  • Address PR Review Comments

    cashew-labs/libretto

    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.

    904 GitHub stars~532 tokensUpdated 1 mo ago
    Auto-check passed

  • CLI Development

    cashew-labs/libretto

    Design rules for command-line tools: subcommand-scoped help, actionable success output, debuggable failures, stable output, meaningful exit codes and a --json mode.

    904 GitHub stars~781 tokensUpdated 1 mo ago
    Auto-check passed

  • External Electron App Automation

    cashew-labs/libretto

    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.

    904 GitHub stars~967 tokensUpdated 1 mo ago
    Auto-check passed

  • Merge Conflict Resolver

    cashew-labs/libretto

    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.

    904 GitHub stars~1.1k tokensUpdated 1 mo ago
    Auto-check passed

  • Feature Spec Generator

    cashew-labs/libretto

    Researches the codebase and relevant docs, asks clarifying questions, then writes a spec sheet in specs/ for a significant feature or complex fix.

    904 GitHub stars~2.4k tokensUpdated 1 mo ago
    Auto-check passed

Works with

Categories

Questions about Implement Spec

What does Implement Spec do?

Implement a single phase of a spec. An agent skill from cashew-labs/libretto. Implement Spec is an agent skill from cashew-labs/libretto. Implement a single phase of a spec.

When should I use Implement Spec?

Implement Spec fits situations like: given a spec file and a phase number to implement.

How do I install Implement Spec in Claude Code?

Run `npx skills add cashew-labs/libretto --skill implement-spec -a claude-code`. Or copy the skill folder (.agents/skills/implement-spec in cashew-labs/libretto) into .claude/skills/implement-spec in your project. Claude Code loads it when a task matches its description.

How do I install Implement Spec in Codex?

Run `npx skills add cashew-labs/libretto --skill implement-spec -a codex`. Or copy the skill folder (.agents/skills/implement-spec in cashew-labs/libretto) into .agents/skills/implement-spec in your project. Codex loads it when a task matches its description.

Can I use Implement Spec in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add cashew-labs/libretto --skill implement-spec -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/implement-spec, .gemini/skills/implement-spec, .github/skills/implement-spec and .opencode/skills/implement-spec in your project.

What does Implement Spec need to run?

Going by SKILL.md and its folder, Implement Spec needs the command-line tools its instructions call (pnpm).

Does Implement Spec access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Implement Spec safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Implement Spec use?

Implement Spec is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Implement Spec use?

About 752 tokens (SKILL.md is roughly 3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Implement Spec?

Skills that share tags, products or a category with Implement Spec: DeerFlow Smoke Test (bytedance/deer-flow, 83k stars), OpenWork Desktop CDP Driver (different-ai/openwork, 24k stars), E2E (gronxb/hot-updater, 1.8k stars) and Cloud Agents Starter (scalar/scalar, 16k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Implement Spec?

cashew-labs (a GitHub organization) maintains it in cashew-labs/libretto, which has 904 GitHub stars. The repository holds 21 skills in this directory. The repository was last updated on August 21, 2026.

Source: cashew-labs/libretto on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.