Executing Plans Inline
obra/superpowers
Has the agent carry out an implementation plan itself, task by task in the current session, keeping a ledger, proving each step with a test and ending with one whole-branch review.
Phase 2 of the SDLC pipeline (also usable standalone). An agent skill from nvuillam/github-dependents-info.
Install Design
$ npx skills add nvuillam/github-dependents-info --skill design -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install nvuillam/github-dependents-info design --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/nvuillam/github-dependents-info.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/design .claude/skills/design && rm -rf skills-srcUse ~/.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/
Install the "design" agent skill from https://github.com/nvuillam/github-dependents-info/tree/main/.claude/skills/design into .claude/skills/design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "design", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/nvuillam/github-dependents-info/tree/main/.claude/skills/designType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add nvuillam/github-dependents-info --skill design -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install nvuillam/github-dependents-info design --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/nvuillam/github-dependents-info.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/design .agents/skills/design && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "design" agent skill from https://github.com/nvuillam/github-dependents-info/tree/main/.claude/skills/design into .agents/skills/design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "design", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add nvuillam/github-dependents-info --skill design -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install nvuillam/github-dependents-info design --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/nvuillam/github-dependents-info.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/design .cursor/skills/design && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "design" agent skill from https://github.com/nvuillam/github-dependents-info/tree/main/.claude/skills/design into .cursor/skills/design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "design", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/nvuillam/github-dependents-info.git --path .claude/skills/design--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add nvuillam/github-dependents-info --skill design -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install nvuillam/github-dependents-info design --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/nvuillam/github-dependents-info.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/design .gemini/skills/design && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "design" agent skill from https://github.com/nvuillam/github-dependents-info/tree/main/.claude/skills/design into .gemini/skills/design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "design", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install nvuillam/github-dependents-info designInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add nvuillam/github-dependents-info --skill design -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/nvuillam/github-dependents-info.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/design .github/skills/design && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "design" agent skill from https://github.com/nvuillam/github-dependents-info/tree/main/.claude/skills/design into .github/skills/design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "design", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add nvuillam/github-dependents-info --skill design -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install nvuillam/github-dependents-info design --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/nvuillam/github-dependents-info.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/design .opencode/skills/design && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "design" agent skill from https://github.com/nvuillam/github-dependents-info/tree/main/.claude/skills/design into .opencode/skills/design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "design", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
design- GitHub stars
- 163
- Token cost
- ~1k tokens
- SKILL.md length
- 389 words
- Files
- 1
- Skills in repo
- 4
- Repo updated
- First seen
- Licence
- MIT
At a glance
Phase 2 of the SDLC pipeline (also usable standalone). An agent skill from nvuillam/github-dependents-info.
- Works in 3 steps: Check the conversation for a recent… → Read CLAUDE.md for architecture and… → If there are unresolved open questions…
- The user invokes /design with either a prior /analyze in conversation context OR a direct problem description
- SKILL.md covers Pre-flight, What to produce, Design principles for this… and Rules
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Design is an agent skill from nvuillam/github-dependents-info. Phase 2 of the SDLC pipeline (also usable standalone). Use when the user invokes /design with either a prior /analyze in conversation context OR a direct problem description. Produces an implementation plan inline in the conversation. Do NOT write production code in this phase. Do NOT save the design to disk unless the user explicitly asks.
Its SKILL.md is about 1k 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 Agent Workflows, covering Planning. 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 /design with either a prior /analyze in conversation context OR a direct problem description
- Tasks that involve Planning
Example prompts
- “/design”
Workflow steps
3 steps, taken from the first numbered list in SKILL.md.
- Check the conversation for a recent /analyze output. If present, use it as input. If not, treat the user's /design arguments as the…
- Read CLAUDE.md for architecture and conventions.
- If there are unresolved open questions (from a prior analysis or the user's prompt), ask the user to resolve them before proposing a…
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
No scripts in the folder and no shell commands in SKILL.md.
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
Design loads about 1k tokens when it runs. Until then it costs about 87 tokens; SKILL.md has 389 words of instructions outside code blocks.
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). 389 words, ~1,045 tokens.
Download SKILL.mdSave it as
.claude/skills/design/SKILL.md (or your agent's skills folder).- name
- design
- description
- Phase 2 of the SDLC pipeline (also usable standalone). Use when the user invokes /design with either a prior /analyze in conversation context OR a direct problem description. Produces an implementation plan inline in the conversation. Do NOT write production code in this phase. Do NOT save the design to disk unless the user explicitly asks.
design — SDLC phase 2 (standalone-capable)
You are in the design phase. Your job is to turn a problem (either an /analyze output already in the conversation, or a fresh description from the user) into a concrete, ordered plan that /implement (or the user) can execute mechanically.
This skill can run after /analyze OR standalone. If the user invokes /design with their own description and no prior analysis, do a quick mental analysis first — but still output a design, not an analysis.
Pre-flight
- Check the conversation for a recent
/analyzeoutput. If present, use it as input. If not, treat the user's/designarguments as the problem statement. - Read
CLAUDE.mdfor architecture and conventions. - If there are unresolved open questions (from a prior analysis or the user's prompt), ask the user to resolve them before proposing a design. Don't guess on non-trivial trade-offs.
What to produce
Output the design inline as your response, in the conversation. Do NOT write it to a file unless the user explicitly asks ("save the design", "put it in a doc", etc.). The implementation phase reads from conversation context.
Structure:
# Design: <one-line solution statement>
## Approach
<3-6 sentences describing the chosen approach and why it fits the constraints.>
## Alternatives considered
<For each rejected alternative: one sentence on what it was, one sentence on why. Skip the section if the choice was obvious.>
## Change list
<Ordered, numbered list of concrete edits. Each item names a file, the function/region to touch, and the change. Example:
1. `github_dependents_info/gh_dependents_info.py:920` — extend `fetch_all_package_pages` signature with `since: datetime | None = None`; thread it through to `fetch_page`.
2. `github_dependents_info/__main__.py:80` — add `--since` Typer option, parse to datetime, forward via `gh_options`.
3. `action.yml` — add matching `since` input and shell branch that appends `--since=...`.
>
## Public-API impact
<Anything affecting downstream users: new/changed CLI flags, env vars, JSON schema, badge marker behavior, action.yml inputs. State "None" when applicable.>
## Test plan
<Specific tests to add or update. For each: which file, what it asserts, whether it needs network.>
## Risks & rollback
<What could break. How to revert.>Skip sections that are genuinely empty — don't pad with "N/A".
Show full SKILL.md (193 more words)Show less
Design principles for this codebase
- Keep logic in
GithubDependentsInfo. New behavior goes on the class, not in__main__.py. CLI is a thin shim. - CLI options with env-var fallbacks are only forwarded to the constructor when explicitly set by the user — see
__main__.pyllm_*handling. Preserve that pattern. action.ymlmirrors the CLI. New user-facing CLI flags need aninputs:entry and aset -- "$@" ...shell branch.- CSV-resume compatibility. If a change alters what's stored mid-crawl, decide whether old
csv_directorycontents are invalidated or migrated, and say so. - Don't change badge marker strings (
<!-- gh-dependents-info-used-by-start -->/...-end -->). - Doctests run by default (
addopts = ["--doctest-modules"]). New>>>examples become tests.
Rules
- No code edits. Design-only phase.
- No files written. Output stays in conversation unless the user explicitly asks to persist it.
- Be specific about file paths and line numbers in the change list so
/implement(or a human) doesn't have to re-discover them. - If the available analysis turns out to be wrong, say so and recommend re-running
/analyzerather than designing on a bad foundation. - End with a single line suggesting the next step, e.g.
Run /implement to execute, or refine the design 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/design of nvuillam/github-dependents-info.
Open the folder on GitHubat commit 74aece1
Compare with similar skills
Design 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Design this skillnvuillam/github-dependents-info | 163 | — | ~1k | Automated safety check: Pass | MIT | |
| Executing Plans Inlineobra/superpowers | 297k | 2 repos | ~5.1k | Automated safety check: Pass | MIT | |
| Interview Meaddyosmani/agent-skills | 103k | 6 repos | ~3.8k | Automated safety check: Pass | MIT | |
| OpenSpec Guided OnboardingFission-AI/OpenSpec | 71k | 1 repos | ~4.5k | Automated safety check: Pass | MIT | |
| Writing Plansgeeksblabla/stateofdev.ma | 163 | 57 repos | ~661 | Automated safety check: Pass | None | |
| Subagent Driven DevelopmentAsvarox/allkaraoke | 261 | 37 repos | ~1.2k | Automated safety check: Pass | None |
Similar skills
Interview Me
addyosmani/agent-skills
Asks one question at a time, each with a best guess attached, until the agent is about 95 percent sure what you really want, before any plan, spec or code.
OpenSpec Guided Onboarding
Fission-AI/OpenSpec
Walks you through a complete OpenSpec workflow cycle with narration while doing real work in your codebase.
Writing Plans
geeksblabla/stateofdev.ma
A skill your agent uses when design is complete and you need detailed implementation tasks for engineers with zero codebase context - creates comprehensive implementation plans with exact file…
Subagent Driven Development
Asvarox/allkaraoke
A skill your agent uses when executing implementation plans with independent tasks in the current session
Planning With Files
jd-opensource/JoySafeter
Implements Manus-style file-based planning for complex tasks.
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.
Megalinter Setup
nvuillam/github-dependents-info
Install or upgrade MegaLinter on a repository. An agent skill from nvuillam/github-dependents-info.
Implement
nvuillam/github-dependents-info
Phase 3 of the SDLC pipeline (also usable standalone). An agent skill from nvuillam/github-dependents-info.
Related
Categories
Questions about Design
What does Design do?
Phase 2 of the SDLC pipeline (also usable standalone). An agent skill from nvuillam/github-dependents-info. Design is an agent skill from nvuillam/github-dependents-info. Phase 2 of the SDLC pipeline (also usable standalone).
When should I use Design?
Design fits situations like: the user invokes /design with either a prior /analyze in conversation context OR a direct problem description; tasks that involve Planning.
How do I install Design in Claude Code?
Run `npx skills add nvuillam/github-dependents-info --skill design -a claude-code`. Or copy the skill folder (.claude/skills/design in nvuillam/github-dependents-info) into .claude/skills/design in your project. Claude Code loads it when a task matches its description.
How do I install Design in Codex?
Run `npx skills add nvuillam/github-dependents-info --skill design -a codex`. Or copy the skill folder (.claude/skills/design in nvuillam/github-dependents-info) into .agents/skills/design in your project. Codex loads it when a task matches its description.
Can I use Design 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 design -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/design, .gemini/skills/design, .github/skills/design and .opencode/skills/design in your project.
What does Design need to run?
SKILL.md names no scripts, command-line tools or credentials: Design is instructions for the agent only.
Does Design 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 Design 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 Design use?
Design 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 Design use?
About 1k tokens (SKILL.md is roughly 4.2k 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 Design?
Skills that share tags, products or a category with Design: Executing Plans Inline (obra/superpowers, 297k stars), Interview Me (addyosmani/agent-skills, 103k stars), OpenSpec Guided Onboarding (Fission-AI/OpenSpec, 71k stars) and Writing Plans (geeksblabla/stateofdev.ma, 163 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Design?
nvuillam (a GitHub user) maintains it in nvuillam/github-dependents-info, which has 163 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on October 9, 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.