New: 98,000+ 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

by nvuillam in nvuillam/github-dependents-info

Phase 3 of the SDLC pipeline (also usable standalone). An agent skill from nvuillam/github-dependents-info.

MITAuto-check passedTesting & QA

Install Implement

skills CLI
$ npx skills add nvuillam/github-dependents-info --skill implement -a claude-code

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

GitHub CLI
$ gh skill install nvuillam/github-dependents-info implement --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/nvuillam/github-dependents-info.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/implement .claude/skills/implement && 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
GitHub stars
162
Token cost
~999 tokens
SKILL.md length
510 words
Files
1
Skills in repo
4
Repo updated
First seen
Licence
MIT

At a glance

Phase 3 of the SDLC pipeline (also usable standalone). An agent skill from nvuillam/github-dependents-info.

  • Works in 2 steps: A /design output present in the recent… → The user's /implement arguments — treat…
  • The user invokes /implement after a /design in conversation context
  • SKILL.md covers Pre-flight, How to work, Code conventions (enforced) and Things not to touch unless…, plus 2 more sections
  • Calls poetry and make

What it does

Implement is an agent skill from nvuillam/github-dependents-info. Phase 3 of the SDLC pipeline (also usable standalone). Use when the user invokes /implement after a /design in conversation context, OR with a direct task description. Executes the change list, editing source files. Reads design context from the conversation — not from disk. Does NOT run the full test suite (that is /test's job), but does sanity-check imports and syntax.

Its SKILL.md is about 1000 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, covering Test generation. It works with GitHub. The repository describes itself as: Collect information about dependencies between a github repo and other repositories. Results available in JSON, markdown and badge. The licence is MIT.

When your agent uses it

  • The user invokes /implement after a /design in conversation context
  • With a direct task description

Example prompts

  • “/implement”

Requirements

  • Python 3
  • Docker

Workflow steps

2 steps, taken from the first numbered list in SKILL.md.

  1. A /design output present in the recent conversation — use its Change list verbatim.
  2. The user's /implement arguments — treat them as the task. Do a brief in-head plan, confirm with the user if non-trivial, then proceed.

What it can do on your machine

Read from SKILL.md and the folder at commit 74aece1. 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:

    • poetry
    • make

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

  • Network

    No URLs in SKILL.md.

    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 loads about 999 tokens when it runs. Until then it costs about 96 tokens; SKILL.md has 510 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~96
When it runs · the whole SKILL.md, loaded when a task matches
~999

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 nvuillam/github-dependents-info at commit 74aece1, republished under its MIT licence (© nvuillam). 510 words, ~999 tokens.

Download SKILL.mdSave it as .claude/skills/implement/SKILL.md (or your agent's skills folder).
name
implement
description
Phase 3 of the SDLC pipeline (also usable standalone). Use when the user invokes /implement after a /design in conversation context, OR with a direct task description. Executes the change list, editing source files. Reads design context from the conversation — not from disk. Does NOT run the full test suite (that is /test's job), but does sanity-check imports and syntax.

implement — SDLC phase 3 (standalone-capable)

You are in the implementation phase. Your job is to execute concrete code changes.

This skill can run after /design OR standalone (e.g. user says /implement add a --since flag without prior phases). Input source, in priority order:

  1. A /design output present in the recent conversation — use its Change list verbatim.
  2. The user's /implement arguments — treat them as the task. Do a brief in-head plan, confirm with the user if non-trivial, then proceed.

Pre-flight

  1. Look for a recent /design Change list in the conversation. If absent and the user's instructions are non-trivial (more than one file, or unclear scope), ask the user whether they want you to do a quick design-in-head first or just execute. For simple/explicit tasks, just execute.
  2. Read CLAUDE.md for conventions if you haven't already in this session.

How to work

  • For multi-step changes, use TaskCreate to mirror the change list as trackable tasks. Mark each in_progress when you start it and completed immediately when done — do not batch. For single-edit tasks, skip TaskCreate.
  • Edit with Edit (preferred) or Write (only for new files). Read the file first if you have not already in this session.
  • After each non-trivial edit to gh_dependents_info.py or __main__.py, run poetry run python -c "import github_dependents_info; from github_dependents_info.__main__ import app" to catch import/syntax errors early.
  • If the plan specified test additions, write the test stubs/files in this phase — but do not run them. /test (or the user) runs them.

Code conventions (enforced)

  • Black, line length 120. Don't hand-format; let make codestyle reflow.
  • isort sections: FUTURE → TYPING → STDLIB → THIRDPARTY → FIRSTPARTY → LOCALFOLDER.
  • Python ≥ 3.10 syntax is fine (X | None, PEP 604 unions).
  • Default to no comments. Only add a comment when the why is non-obvious.
  • Don't refactor beyond the requested change. If you spot adjacent cleanup, note it as a follow-up in your end-of-phase summary, do not do it.
  • Keep the CLI thin: behavior belongs on the GithubDependentsInfo class.
  • Forward new CLI options with env-var fallbacks only when explicitly set (the if X is not None: gh_options[...] = X pattern in __main__.py).
  • Mirror new user-facing CLI flags into action.yml inputs AND the shell set -- "$@" ... branches.
Show full SKILL.md (153 more words)Show less

Things not to touch unless explicitly requested

  • The badge marker strings <!-- gh-dependents-info-used-by-start --> and <!-- gh-dependents-info-used-by-end -->.
  • The packages_<repo>.csv / dependents_<name>.csv filename patterns under csv_directory — downstream users may script against them.
  • The pinned image: docker://nvuillam/github-dependents-info:vX.Y.Z in action.yml — that moves at release time, not feature work.
  • requirements.txt directly — it's regenerated from poetry.lock by make install.

When you hit a problem

  • Failing pre-commit hook on commit: fix the underlying issue, never --no-verify.
  • An edit breaks an unrelated test: stop and surface it. Do not blindly "fix" it.
  • A dependency needs adding: use poetry add <pkg> (or instruct the user), do not hand-edit pyproject.toml's dependency list.

Output

When all changes are done:

  1. Summarize what changed in 2-3 sentences (one paragraph, no headers).
  2. List any follow-ups you noticed but did not do.
  3. End with a single line suggesting the next step, e.g. Run /test to verify, or review the diff above. — do not assume the user will continue.

© nvuillam, 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 .claude/skills/implement of nvuillam/github-dependents-info.

Open the folder on GitHubat commit 74aece1

Compare with similar skills

Implement 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 compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Implement this skillnvuillam/github-dependents-info162—~999Automated safety check: PassMIT
Explore Feature E2E Testcomet-ml/opik22k—~3.4kAutomated safety check: PassApache-2.0
Kane CLI Browser TestingLambdaTest/kane-cli247—~8.4kAutomated safety check: PassApache-2.0
Megatron GB200 One-Node Test OnboardingNVIDIA/Megatron-LM18k—~1.3kAutomated safety check: PassApache-2.0
Endgamemicrosoft/copilot-for-eclipse126—~1.4kAutomated safety check: PassMIT
MAUI UI Test Writerdotnet/maui23k—~3kAutomated safety check: PassMIT

Similar skills

  • Explore Feature E2E Test

    comet-ml/opik

    Turns a code change into one committed, passing Playwright end-to-end spec by resolving the change scope and handing authoring to a companion skill.

    22k GitHub stars~3.4k tokensUpdated today
    Testing & QAAuto-check passed

  • Kane CLI Browser Testing

    LambdaTest/kane-cli

    Drives a real browser through the kane-cli tool and designs requirement-linked test suites from a PRD or a plain description, with mobile and cloud-grid runs.

    247 GitHub stars~8.4k tokensUpdated 2 days ago
    Testing & QAAuto-check passed

  • Megatron GB200 One-Node Test Onboarding

    NVIDIA/Megatron-LM

    Official

    Creates one-node GitHub merge-request variants of existing two-node GB200 functional tests in Megatron-LM, adjusting parallelism settings to fit four GPUs.

    18k GitHub stars~1.3k tokensUpdated today
    Testing & QAAuto-check passed

  • Endgame

    microsoft/copilot-for-eclipse

    Official

    Orchestrate endgame verification for a GitHub milestone issue.

    126 GitHub stars~1.4k tokensUpdated 7 days ago
    Testing & QAAuto-check passed

  • MAUI UI Test Writer

    dotnet/maui

    Official

    Writes UI tests that reproduce a GitHub issue in .NET MAUI and keeps iterating until the tests actually fail, proving they catch the bug.

    23k GitHub stars~3k tokensUpdated today
    Testing & QAAuto-check passed

  • MAUI XAML Unit Test Writer

    dotnet/maui

    Official

    Writes a paired .xaml and .xaml.cs unit test for a .NET MAUI issue that is about XAML behavior itself, such as parsing, XamlC output or generated code.

    23k GitHub stars~742 tokensUpdated today
    Testing & QAAuto-check passed

More from nvuillam/github-dependents-info

  • Analyze

    nvuillam/github-dependents-info

    Phase 1 of the SDLC pipeline (also usable standalone). An agent skill from nvuillam/github-dependents-info.

    162 GitHub stars~879 tokensUpdated today
    Auto-check passed

  • Design

    nvuillam/github-dependents-info

    Phase 2 of the SDLC pipeline (also usable standalone). An agent skill from nvuillam/github-dependents-info.

    162 GitHub stars~1k tokensUpdated today
    Auto-check passed

  • Megalinter Setup

    nvuillam/github-dependents-info

    Install or upgrade MegaLinter on a repository. An agent skill from nvuillam/github-dependents-info.

    162 GitHub stars~3.9k tokensUpdated today
    Auto-check: notes

Works with

Categories

Questions about Implement

What does Implement do?

Phase 3 of the SDLC pipeline (also usable standalone). An agent skill from nvuillam/github-dependents-info. Implement is an agent skill from nvuillam/github-dependents-info. Phase 3 of the SDLC pipeline (also usable standalone).

When should I use Implement?

Implement fits situations like: the user invokes /implement after a /design in conversation context; with a direct task description.

How do I install Implement in Claude Code?

Run `npx skills add nvuillam/github-dependents-info --skill implement -a claude-code`. Or copy the skill folder (.claude/skills/implement in nvuillam/github-dependents-info) into .claude/skills/implement in your project. Claude Code loads it when a task matches its description.

How do I install Implement in Codex?

Run `npx skills add nvuillam/github-dependents-info --skill implement -a codex`. Or copy the skill folder (.claude/skills/implement in nvuillam/github-dependents-info) into .agents/skills/implement in your project. Codex loads it when a task matches its description.

Can I use Implement 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 nvuillam/github-dependents-info --skill implement -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, .gemini/skills/implement, .github/skills/implement and .opencode/skills/implement in your project.

What does Implement need to run?

Going by SKILL.md and its folder, Implement needs the command-line tools its instructions call (poetry and make). Our summary lists: Python 3; Docker.

Does Implement 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 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 use?

Implement 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 use?

About 999 tokens (SKILL.md is roughly 4k 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?

Skills that share tags, products or a category with Implement: Explore Feature E2E Test (comet-ml/opik, 22k stars), Kane CLI Browser Testing (LambdaTest/kane-cli, 247 stars), Megatron GB200 One-Node Test Onboarding (NVIDIA/Megatron-LM, 18k stars) and Endgame (microsoft/copilot-for-eclipse, 126 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Implement?

nvuillam (a GitHub user) maintains it in nvuillam/github-dependents-info, which has 162 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on October 7, 2026.

Source: nvuillam/github-dependents-info on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.