Agent skill

Save Idea

by davidondrej in davidondrej/skills

Save ideas, observations, content topics, projects, and convictions in the ideas repo.

MITAuto-check passedDevelopment

Install Save Idea

skills CLI
$ npx skills add davidondrej/skills --skill save-idea -a claude-code

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

GitHub CLI
$ gh skill install davidondrej/skills save-idea --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/davidondrej/skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/thinking-and-docs/save-idea .claude/skills/save-idea && 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
save-idea
GitHub stars
4.1k
Token cost
~1.2k tokens
SKILL.md length
601 words
Files
1
Skills in repo
51
Repo updated
First seen
Licence
MIT

At a glance

Save ideas, observations, content topics, projects, and convictions in the ideas repo.

  • Works in 5 steps: Capture and Route → Read and Number → Append with Source → …
  • The user asks to capture an idea
  • SKILL.md covers 1. Capture and Route, 2. Read and Number, 3. Append with Source and 4. Commit and Push, plus 2 more sections
  • Calls git and just

What it does

Save Idea is an agent skill from davidondrej/skills. Save ideas, observations, content topics, projects, and convictions in the ideas repo. Use when the user asks to capture an idea or insight. Adds to idea backlogs, not reminders or tasks.

Its SKILL.md is about 1.2k 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 Development. The repository describes itself as: access to david ondrej's personal agent skills. The licence is MIT.

When your agent uses it

  • The user asks to capture an idea

Example prompts

  • “/save-idea”

Workflow steps

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

  1. Capture and Route
  2. Read and Number
  3. Append with Source
  4. Commit and Push
  5. Confirm

What it can do on your machine

Read from SKILL.md and the folder at commit 7874889. 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:

    • git
    • just

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

  • Network

    No URLs in SKILL.md. Its commands use git, 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

Save Idea loads about 1.2k tokens when it runs. Until then it costs about 49 tokens; SKILL.md has 601 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~49
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k

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 davidondrej/skills at commit 7874889, republished under its MIT licence (© davidondrej). 601 words, ~1,235 tokens.

Download SKILL.mdSave it as .claude/skills/save-idea/SKILL.md (or your agent's skills folder).
name
save-idea
description
Save ideas, observations, content topics, projects, and convictions in the ideas repo. Use when the user asks to capture an idea or insight. Adds to idea backlogs, not reminders or tasks.

save-idea

Capture the entry in the ideas repo, commit, push, and confirm. All paths below are relative to that repo.

1. Capture and Route

Everything after /save-idea is the entry. Multiple ideas get one entry each. Preserve the user's wording verbatim, except startup ideas and convictions, which may be tightened without changing the user's meaning or voice.

Use and strip an explicit prefix. Otherwise choose by the definitions below; ask one short question only if ambiguous.

  • video: → VIDEO-IDEAS.md: a concept for a full video.
  • topic: → TOPICS.md: podcast/content topics, guests, or discussion questions.
  • observation: → OBSERVATIONS.md: personal insights, hypotheses, or assumptions to test, without requiring content intent.
  • marketing: → MARKETING-IDEAS.md: getting an existing product in front of people.
  • startup: → STARTUP-IDEAS.md: a business/product idea or technical insight that could become a startup.
  • mini: → mini-projects.md: a small technical or cool project, not a startup candidate.
  • article: → ARTICLE-IDEAS.md: a topic for the user's daily public articles.
  • No prefix for convictions: use CONVICTIONS.md only for beliefs the user states as certain about AI-era building, startups, the AI industry, or agentic coding.

Tentative beliefs belong in observations. An observation is not a topic merely because it could be discussed on a podcast.

2. Read and Number

Read the target file. Use its last entry number + 1; never reuse gaps, renumber, reorder, or edit existing entries.

  • Video numbering continues from the old Google Doc; do not restart it.
  • Startup numbering follows the last idea in the STARTUP IDEAS list. Ignore the separate discarded-ideas numbering.
  • Other files start at 1 and have independent numbering.

If missing, create TOPICS.md or MARKETING-IDEAS.md with a one-line purpose header; OBSERVATIONS.md with # OBSERVATIONS and Insights, hypotheses, and assumptions to test.; or mini-projects.md with # MINI PROJECTS and > Just cool shit we wanna build — small projects we think would be cool. Then append entry 1.

Show full SKILL.md (303 more words)Show less

3. Append with Source

Source format: <repo>, <agent and chat/session>, <YYYY-MM-DD>.

  • Repo: where the skill was invoked, from git rev-parse --show-toplevel, or cwd outside a repo. Use a ~/... path.
  • Chat/session: agent name plus title or session ID if available; otherwise just the agent name.
  • Date: today. Preserve any extra links or notes the user supplied.

Videos, topics, observations, marketing, and articles: append verbatim at the bottom, with real tabs before source and context lines:

text
N. Idea exactly as the user said it
	source: <repo>, <agent and chat/session>, <date>
	any extra links or notes the user gave

Startups, convictions, and mini projects: indent all source and context lines with four spaces; use - source: and a blank line between entries:

text
N. Title — one-line explanation.
    - source: <repo>, <agent and chat/session>, <date>
  • Startups: read startup/AGENTS.md. Tighten the entry while keeping the user's voice. Insert after the last numbered idea, before the trailing ---- separator and discarded-ideas note. Preserve the root STARTUP-IDEAS.md symlink to startup/STARTUP-IDEAS.md.
  • Convictions: append N. Punchy conviction — one-line why., tightened but faithful to the user's wording.
  • Mini projects: append N. Idea exactly as the user said it; do not rewrite or add an explanation.

4. Commit and Push

Commit and push captures only when the user has authorized it. This applies only to the listed backlog files, including the startup symlink's target, not other repo changes.

Run Git yourself using git -C; do not change cwd or delegate this step:

bash
git -C <ideas-repo> pull --rebase --autostash <remote> <branch>
# Stage only this capture's files; example:
git -C <ideas-repo> add OBSERVATIONS.md
git -C <ideas-repo> commit -m "Add observation 1 on local agents"
git -C <ideas-repo> push <remote> <branch>
  • Stage only the captured idea files; never git add -A. For the startup symlink, stage startup/STARTUP-IDEAS.md. Keep unrelated staged changes or edits out of the commit.
  • Commit message: Add <entry type> <number> on <short description>. List numbers for multiple entries.
  • If any Git step fails, report the exact error and stop. Never force-push.

5. Confirm

Report the exact saved entry text, number, file, and successful push.

Protected Locations

  • Never write or push to the legacy startup repo. Startup support material belongs in the startup support directory.
  • Never write to the discarded-ideas file; only the user moves ideas there.

© davidondrej, 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 skills/thinking-and-docs/save-idea of davidondrej/skills.

Open the folder on GitHubat commit 7874889

Compare with similar skills

Save Idea 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.

Save Idea compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Save Idea this skilldavidondrej/skills4.1k—~1.2kAutomated safety check: PassMIT
Vercel Composition Patternssupabase/supabase111k58 repos~726Automated safety check: PassMIT
Finishing a Development Branchobra/superpowers297k5 repos~1.9kAutomated safety check: PassMIT
Typescript Advanced Typesrolling-scopes/rsschool-app10k25 repos~4.2kAutomated safety check: PassMPL-2.0
PR Babysitteropeninterpreter/openinterpreter69k3 repos~4.2kAutomated safety check: PassApache-2.0
Code Review ChecklistshareAI-lab/learn-claude-code78k5 repos~1.1kAutomated safety check: PassMIT

Similar skills

  • Official

    React composition patterns that scale. An agent skill from supabase/supabase.

    111k GitHub starsUsed in 58 repos~726 tokens
    DevelopmentAuto-check passed
  • Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree.

    297k GitHub starsUsed in 5 repos~1.9k tokens
    DevelopmentAuto-check passed
  • Typescript Advanced Types

    rolling-scopes/rsschool-app

    Master TypeScript's advanced type system including generics, conditional types, mapped types, template literals, and utility types for building type-safe applications.

    10k GitHub starsUsed in 25 repos~4.2k tokens
    DevelopmentAuto-check passed
  • PR Babysitter

    openinterpreter/openinterpreter

    Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.

    69k GitHub starsUsed in 3 repos~4.2k tokens
    DevelopmentAuto-check passed
  • Code Review Checklist

    shareAI-lab/learn-claude-code

    Reviews code against a five-part checklist covering security, correctness, performance, maintainability and testing, and reports findings in a fixed format.

    78k GitHub starsUsed in 5 repos~1.1k tokens
    DevelopmentAuto-check passed
  • Greploop

    onyx-dot-app/onyx

    Iteratively improves a PR (GitHub), MR (GitLab), or shelved changelist (Perforce) until Greptile gives it a 5/5 confidence score with zero unresolved comments.

    32k GitHub starsUsed in 4 repos~3.3k tokens
    DevelopmentAuto-check passed

More from davidondrej/skills

All 51 skills in this repo
  • Nagent

    davidondrej/skills

    Launch a new bb worker thread with the right project, model, worktree, and task brief.

    4.1k GitHub stars~1.7k tokensUpdated yesterday
    Auto-check: notes
  • Browser Harness

    davidondrej/skills

    Direct browser control via CDP. An agent skill from davidondrej/skills.

    4.1k GitHub starsUsed in 2 repos~3k tokens
    Auto-check passed
  • Persistent Localhost

    davidondrej/skills

    Manage persistent dev servers, APIs, and other local processes on a port using macOS LaunchAgents.

    4.1k GitHub stars~618 tokensUpdated yesterday
    Auto-check passed
  • Reset Cursor Acp

    davidondrej/skills

    Reset a stuck Cursor ACP thread in <chat-system and reload its configuration.

    4.1k GitHub stars~728 tokensUpdated yesterday
    Auto-check passed
  • Anti Sleep

    davidondrej/skills

    Keep a Mac awake for a set duration or while a process runs.

    4.1k GitHub stars~640 tokensUpdated yesterday
    Auto-check: warnings
  • Bb CLI

    davidondrej/skills

    Use this when controlling bb. An agent skill from davidondrej/skills.

    4.1k GitHub stars~823 tokensUpdated yesterday
    Auto-check passed

Categories

Questions about Save Idea

What does Save Idea do?

Save ideas, observations, content topics, projects, and convictions in the ideas repo. Save Idea is an agent skill from davidondrej/skills. Save ideas, observations, content topics, projects, and convictions in the ideas repo.

When should I use Save Idea?

Save Idea fits situations like: the user asks to capture an idea.

How do I install Save Idea in Claude Code?

Run `npx skills add davidondrej/skills --skill save-idea -a claude-code`. Or copy the skill folder (skills/thinking-and-docs/save-idea in davidondrej/skills) into .claude/skills/save-idea in your project. Claude Code loads it when a task matches its description.

How do I install Save Idea in Codex?

Run `npx skills add davidondrej/skills --skill save-idea -a codex`. Or copy the skill folder (skills/thinking-and-docs/save-idea in davidondrej/skills) into .agents/skills/save-idea in your project. Codex loads it when a task matches its description.

Can I use Save Idea 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 davidondrej/skills --skill save-idea -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/save-idea, .gemini/skills/save-idea, .github/skills/save-idea and .opencode/skills/save-idea in your project.

What does Save Idea need to run?

Going by SKILL.md and its folder, Save Idea needs the command-line tools its instructions call (git and just).

Does Save Idea access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Save Idea 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 Save Idea use?

Save Idea 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 Save Idea use?

About 1.2k tokens (SKILL.md is roughly 4.9k 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 Save Idea?

Skills that share tags, products or a category with Save Idea: Vercel Composition Patterns (supabase/supabase, 111k stars), Finishing a Development Branch (obra/superpowers, 297k stars), Typescript Advanced Types (rolling-scopes/rsschool-app, 10k stars) and PR Babysitter (openinterpreter/openinterpreter, 69k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Save Idea?

davidondrej (a GitHub user) maintains it in davidondrej/skills, which has 4,112 GitHub stars. The repository holds 51 skills in this directory. The repository was last updated on October 8, 2026.

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