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

Grounded Idea Generation

by EveryInc in EveryInc/compound-engineering-plugin

Generates and critiques a wide field of repo-grounded improvement ideas, then hands the survivors off for brainstorming.

MITAuto-check passedAgent Workflows

Install Grounded Idea Generation

skills CLI
$ npx skills add EveryInc/compound-engineering-plugin --skill ce-ideate -a claude-code

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

GitHub CLI
$ gh skill install EveryInc/compound-engineering-plugin ce-ideate --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/EveryInc/compound-engineering-plugin.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/ce-ideate .claude/skills/ce-ideate && 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
ce-ideate
GitHub stars
25k
Token cost
~1.8k tokens
SKILL.md length
976 words
Files
18 (incl. references)
Skills in repo
37
Repo updated
First seen
Licence
MIT

At a glance

Generates and critiques a wide field of repo-grounded improvement ideas, then hands the survivors off for brainstorming.

  • Works in 4 steps: Resume and Scope → Mode-Aware Grounding → 5: Topic-Surface Decomposition → …
  • Wanting a wide set of improvement ideas before picking a direction
  • SKILL.md covers Boundaries, Artifact Root, Phase 0: Resume and Scope and Phase 1: Mode-Aware Grounding, plus 2 more sections
  • Calls git and go

What it does

Which ideas are worth exploring is the question answered here, as a step before deciding what a chosen idea should mean or how it gets built. The full set of candidate ideas is generated before any of them is critiqued, a weak one is rejected with an explicit reason rather than quietly ranked out, and every idea is grounded in the actual repository instead of giving generic advice detached from the code.

The output is a ranked ideation artifact written to a project folder, with every surviving idea explained and the user left holding a menu of next steps; it stops short of producing requirements, plans, or code, sending you to a separate brainstorming skill for whichever idea you want to act on.

When your agent uses it

  • Wanting a wide set of improvement ideas before picking a direction
  • Needing ideas grounded in the actual codebase, not generic advice
  • Deciding which of several possible directions is worth pursuing further

Example prompts

  • “Generate improvement ideas for our onboarding flow, grounded in the repo.”
  • “What are some surprising directions for the search feature nobody's raised?”
  • “Give me a ranked list of ideas for reducing support tickets.”

Workflow steps

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

  1. Resume and Scope
  2. Mode-Aware Grounding
  3. 5: Topic-Surface Decomposition
  4. Divergent Ideation

What it can do on your machine

Read from SKILL.md and the folder at commit 67035e9. 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
    • go

    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

Grounded Idea Generation loads about 1.8k tokens when it runs, and up to ~58k if it reads all its reference files. Until then it costs about 64 tokens; SKILL.md has 976 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~64
When it runs · the whole SKILL.md, loaded when a task matches
~1.8k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~58k

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 EveryInc/compound-engineering-plugin at commit 67035e9, republished under its MIT licence (© EveryInc). 976 words, ~1,779 tokens.

Download SKILL.mdSave it as .claude/skills/ce-ideate/SKILL.md (or your agent's skills folder). This skill also uses 17 other files; get the full folder from GitHub.
name
ce-ideate
description
Generate and evaluate grounded ideas. Use when the user wants ideas, improvements, or surprising directions before choosing one to develop. Not for refining an idea they already have (ce-brainstorm) or judging one already on the table (ce-pov).
argument-hint
[feature, focus area, or constraint] [output:md]

Generate Improvement Ideas

The current year is 2026 — use it when dating documents and checking recent artifacts.

ce-ideate runs before ce-brainstorm. This skill answers "which ideas are worth exploring?" ce-brainstorm then answers what one chosen idea should mean. ce-plan answers how it gets built.

Done: a ranked ideation artifact is written to <root>/ideation/ when that root is present, else to a CE temp path. Every idea generated has been critiqued, and the survivors are explained. The user is left holding the next-steps menu. No requirements, plans, or code.

Boundaries

  1. Ground before ideating. No advice detached from the repo.
  2. Generate many, critique all, explain survivors only. Generate the full candidate list before critiquing any of it. Rejection is explicit and carries a reason; this is not optimistic ranking.
  3. Send the user to brainstorming for action. Never skip from ideation output to planning.
  4. Never dispatch on an unidentified subject. Ask instead, through the host's blocking question tool already in the current tool list (match by capability, not by a host-specific name). Presence in the current tool list is proof the tool exists; never call a user-facing question tool to discover whether it exists. If a matching tool is listed but unloaded, use the host's tool-discovery primitive to load that capability — do not search for another host's tool name. Where no such tool is in the list, offer numbered options on the user-visible surface. Never skip a question silently. Keep "Surprise me" a real option, alongside a Cancel that exits cleanly. Do not ask about solution direction, constraints, audience, tone, or success criteria; ce-brainstorm asks those. If it takes more than 3 questions, ideation is the wrong workflow.
  5. Never print the internal taxonomy label. The labels repo-grounded, elsewhere-software, and elsewhere-non-software only decide which agents to dispatch. Describe the mode to the user in the topic's own words.
  6. Warn and proceed when grounding fails.
  7. Show the user the cost line before dispatching.

The focus hint is any optional context this run was invoked with, from the user or from a calling skill. The rest of this skill calls it {focus_hint}.

Artifact Root

Artifacts go under <root>/ideation/, and learnings are read from <root>/solutions/. Resolve <root> only when you are about to compose one of those paths, and never before the mode is classified — an elsewhere or no-repo run writes to a temp directory and never needs it. Pass a subagent the resolved path, not the config.

<!-- ce-docs-root:start -->

Resolve the CE artifact root <root> before composing any artifact path.

  • Read docs_root from <repo-root>/.compound-engineering/config.yaml only (<repo-root> = git rev-parse --show-toplevel). Do not read it from config.local.yaml. Unset -> <root> is docs, exactly as before.
  • Validate a set value: a repo-relative directory whose real, symlink-resolved path stays inside the repo and is neither the repo root nor under .git/. Otherwise stop with an error naming docs_root and the value -- never fall back to docs.
  • Use <root> as the sole artifact location: create it if absent, compose each path as <root>/<subdir> with this skill's own subdirectory, and never also read docs.
<!-- ce-docs-root:end -->
Show full SKILL.md (472 more words)Show less

Phase 0: Resume and Scope

Both reads this phase names are required, even when the subject, mode, and format look clear. Those two references define the resume check, the format decision, and the scope classification. Nothing here is resolved before reading them.

Output mode is exclusive. A run produces HTML (.html) or markdown (.md), never both. Precedence runs from a request in this prompt, through a stated user preference and config (ideate_output:), down to the html default; a headless run resolves the format the same way, with no pipeline override.

Read references/output-mode.md whenever a format is resolved. The read is required. It defines each step of the decision, and the 30-day recent-work check that decides whether this run updates an existing doc instead of writing a new one.

<!-- ce-config-layers:start -->

Resolve ordinary CE yaml keys from the two repo files.

  • Read <repo-root>/.compound-engineering/config.local.yaml, then config.yaml (<repo-root> = git rev-parse --show-toplevel). Missing files are skipped. Gitignore does not change resolution.
  • Win with the first active (non-commented) value. For scalars, empty is unset; an invalid value continues to the next layer, then the skill default. For lists and maps, a present key — including an empty list or map — replaces the whole key.
  • Do not use this rule for docs_root — that key is config.yaml only.
<!-- ce-config-layers:end -->

Non-software routing. A topic that is not about software runs elsewhere-mode grounding rather than the repo scan. It then follows references/universal-ideation.md in place of Phase 2's frames and the Phase 5 menu. The deliverable is still written automatically.

The Phase 0 checks. references/scope-gates.md defines every Phase 0 check, plus what changes in surprise-me and tactical runs. Ask when the subject is not identifiable. go deep beats a tactical signal.

Phase 1: Mode-Aware Grounding

Read references/grounding.md before dispatching any grounding agent. The read is required. That reference defines every dispatch in this phase, including the routing test that runs before either dispatch block. Grounding runs in parallel, in the foreground.

Scratch lives beneath the effective user's private CE root: /tmp/compound-engineering-<uid> when that is usable, else the validated $TMPDIR fallback, and never .context/. Generate one 8-hex <run-id> and reuse it for the cache and for every checkpoint.

Phase 1.5: Topic-Surface Decomposition

Before frames are dispatched, decompose the topic into 3-5 orthogonal axes — what aspects of the subject to think about. Read references/decomposition.md. Surprise-me mode is the only case that skips this phase. That file's own criteria decide whether a subject is too small to split, so make that judgment after the read. Append the axis list, or the skip reason, to the grounding summary under Topic axes. Evidence scouts are repo-mode only.

Phase 2: Divergent Ideation

Read references/divergent-ideation.md before building any dispatch prompt. The fleet, the frames, and the generation rules live only there. When its merge, synthesis, and axis-coverage steps are complete, continue with references/post-ideation-workflow.md, which it names as the next required read.

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

Files

SKILL.md and 17 other files (references) in skills/ce-ideate of EveryInc/compound-engineering-plugin.

  • SKILL.md
  • references/agents/issue-intelligence-analyst.md
  • references/agents/learnings-researcher.md
  • references/agents/slack-researcher.md
  • references/agents/web-researcher.md
  • references/decomposition.md
  • references/divergent-ideation.md
  • references/grounding.md
  • references/html-rendering.md
  • references/ideation-sections.md
  • references/issue-intelligence.md
  • references/markdown-rendering.md
  • references/output-mode.md
  • references/post-ideation-workflow.md
  • references/scope-gates.md
  • references/universal-ideation.md
  • references/user-research-artifacts.md
  • references/web-research-cache.md

Open the folder on GitHubat commit 67035e9

Compare with similar skills

Grounded Idea Generation 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.

Grounded Idea Generation compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Grounded Idea Generation this skillEveryInc/compound-engineering-plugin25k—~1.8kAutomated safety check: PassMIT
Feature BrainstormVeryGoodOpenSource/vgv-wingspan109—~1.8kAutomated safety check: PassMIT
LLM Councilgcpdev/llm-council-skill4611 repos~1kAutomated safety check: NotesMIT
Brainstorming Before BuildingjnMetaCode/superpowers-zh8.3k—~1.8kAutomated safety check: PassMIT
Planmhmzdev/the-holy-quran-app889—~957Automated safety check: PassMIT
Design Reviewxwtro0tk1t-cloud/harness265—~1.6kAutomated safety check: PassNone

Similar skills

  • Feature Brainstorm

    VeryGoodOpenSource/vgv-wingspan

    Clarifies what to build before how, by asking one question at a time about a feature idea and then handing the result on to planning.

    109 GitHub stars~1.8k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • LLM Council

    gcpdev/llm-council-skill

    Multi-LLM collaborative brainstorming and planning. An agent skill from gcpdev/llm-council-skill.

    461 GitHub starsUsed in 1 repo~1k tokens
    Agent WorkflowsAuto-check: notes

  • Brainstorming Before Building

    jnMetaCode/superpowers-zh

    Turns a rough idea into an approved design before any code is written, sorting the request into spike, bounded or architectural and enforcing an approval gate.

    8.3k GitHub stars~1.8k tokensUpdated 3 days ago
    Agent WorkflowsAuto-check passed

  • Plan

    mhmzdev/the-holy-quran-app

    Turn an idea or brainstorm into an actionable execution plan for The Holy Qur'an app with phases, file changes, and machine-checkable success criteria.

    889 GitHub stars~957 tokensUpdated 28 days ago
    Agent WorkflowsAuto-check passed

  • Design Review

    xwtro0tk1t-cloud/harness

    Dispatch an independent challenger agent to adversarially review a spec or implementation plan against the actual codebase.

    265 GitHub stars~1.6k tokensUpdated 5 mo ago
    Agent WorkflowsAuto-check passed

  • Brainstorming

    ed3dai/ed3d-plugins

    A skill your agent uses when creating or developing anything, before writing code or implementation plans - refines rough ideas into fully-formed designs through structured Socratic questioning…

    250 GitHub starsUsed in 1 repo~4.3k tokens
    Agent WorkflowsAuto-check passed

More from EveryInc/compound-engineering-plugin

All 37 skills in this repo

  • Compound Learning Writer

    EveryInc/compound-engineering-plugin

    Records one solved and verified problem as a durable learning in the repository, but only when the reasoning is not already clear from the final code, tests or docs.

    25k GitHub stars~2k tokensUpdated today
    Auto-check passed

  • Compound Learnings Refresh

    EveryInc/compound-engineering-plugin

    Audits a repo's stored learnings against the current codebase, fixes stale, overlapping or superseded docs and reports on every document.

    25k GitHub stars~2k tokensUpdated today
    Auto-check passed

  • Compound Engineering Prototype

    EveryInc/compound-engineering-plugin

    Builds a throwaway prototype at just the fidelity needed to settle a specific how-it-should-work-or-feel question, before committing to an approach other work will treat as fixed.

    25k GitHub stars~1.9k tokensUpdated today
    Auto-check passed

  • Compound Engineering Setup

    EveryInc/compound-engineering-plugin

    Checks Compound Engineering plugin health and repo-local config, or scaffolds a Compound Pack when you ask for one by id.

    25k GitHub stars~2k tokensUpdated today
    Auto-check passed

  • PR Babysitter

    EveryInc/compound-engineering-plugin

    Watches an open GitHub pull request over time, routing review comments and CI failures to other skills until the PR is ready to merge.

    25k GitHub stars~2k tokensUpdated today
    Auto-check passed

  • CE Brainstorm

    EveryInc/compound-engineering-plugin

    Turns a vague or ambitious feature idea into a requirements-only plan through dialogue with you, sized to the work, before any code is written.

    25k GitHub stars~1.9k tokensUpdated today
    Auto-check passed

Categories

Questions about Grounded Idea Generation

What does Grounded Idea Generation do?

Generates and critiques a wide field of repo-grounded improvement ideas, then hands the survivors off for brainstorming. Which ideas are worth exploring is the question answered here, as a step before deciding what a chosen idea should mean or how it gets built. The full set of candidate ideas is generated before any of them is critiqued, a weak one is rejected with an explicit reason rather than quietly ranked out, and every idea is grounded in the actual repository instead of giving generic advice detached from the code.

When should I use Grounded Idea Generation?

Grounded Idea Generation fits situations like: wanting a wide set of improvement ideas before picking a direction; needing ideas grounded in the actual codebase, not generic advice; deciding which of several possible directions is worth pursuing further.

How do I install Grounded Idea Generation in Claude Code?

Run `npx skills add EveryInc/compound-engineering-plugin --skill ce-ideate -a claude-code`. Or copy the skill folder (skills/ce-ideate in EveryInc/compound-engineering-plugin) into .claude/skills/ce-ideate in your project. Claude Code loads it when a task matches its description.

How do I install Grounded Idea Generation in Codex?

Run `npx skills add EveryInc/compound-engineering-plugin --skill ce-ideate -a codex`. Or copy the skill folder (skills/ce-ideate in EveryInc/compound-engineering-plugin) into .agents/skills/ce-ideate in your project. Codex loads it when a task matches its description.

Can I use Grounded Idea Generation 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 EveryInc/compound-engineering-plugin --skill ce-ideate -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ce-ideate, .gemini/skills/ce-ideate, .github/skills/ce-ideate and .opencode/skills/ce-ideate in your project.

What does Grounded Idea Generation need to run?

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

Does Grounded Idea Generation 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 Grounded Idea Generation 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 Grounded Idea Generation use?

Grounded Idea Generation 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 Grounded Idea Generation use?

About 1.8k tokens (SKILL.md is roughly 7.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 56k tokens, read only when the agent opens those files.

What are the alternatives to Grounded Idea Generation?

Skills that share tags, products or a category with Grounded Idea Generation: Feature Brainstorm (VeryGoodOpenSource/vgv-wingspan, 109 stars), LLM Council (gcpdev/llm-council-skill, 461 stars), Brainstorming Before Building (jnMetaCode/superpowers-zh, 8.3k stars) and Plan (mhmzdev/the-holy-quran-app, 889 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Grounded Idea Generation?

EveryInc (a GitHub organization) maintains it in EveryInc/compound-engineering-plugin, which has 25,424 GitHub stars. The repository holds 37 skills in this directory. The repository was last updated on October 8, 2026.

Source: EveryInc/compound-engineering-plugin on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.