Inception — facilitate shaping a project's founding concept Agent Skill

Runs a full, persistent process that turns an unformed project concept into a durable founding footing.

Context cost
1.6k tokensestimated from the bundle, loaded when it triggers
Bundle
1 file · 6.3 kBtext throughout, nothing executable
Licence
not declarednone named by its author
Last change
—no release on file
Servers it uses
Noneruns standalone

What it does

Runs a full, persistent process that turns an unformed project concept into a durable founding footing. Develops the problem, purpose, users, possibilities, foundational decisions, rejected alternatives, and first actions across facilitated phases maintained in a thinking graph, then produces a long-lived PRD.

What this skill changes about the agent has not been set out here as a list. Its SKILL.md, shown below, says it in the author’s own words.

productivity

The skill itself

A skill is instructions the model reads, so you can see what you are getting: below is the start of its SKILL.md. The front matter loads with every session, the body loads when the skill triggers, and the whole file comes with the install.

SKILL.md6.3 kB · preview
--- name: inception allowed-tools: Read, Write, Edit, Glob, AskUserQuestion, Bash metadata: description-role: documentation ---
14# Inception — facilitate shaping a project's founding concept
15
16You are a thinking partner for the messy start of a project. The user has a rough idea; your job is to help them externalize and advance it through dialogue until it stands on a solid footing — a clear purpose, recorded decisions, and concrete first actions. This is the orchestrator: it owns the graph, estimates the phase, and delegates the per-phase work.
17
18> Load inception-base first — it defines the thinking-graph model, the storage layout, the scripts/inception.sh CLI, and the rule that all elicitation goes through discuss-toolkit-dig. Everything below assumes that model.
19
20> Scope guard: this shapes the concept; it does not track project progress or execute the actions. When the footing is solid, inception-finalize promotes the concrete actions to tracker Issues; execution begins there through the selected provider's start skill. Don't let the graph become a task tracker.
21
22## Start gate — confirm before starting an unrequested session
23
24A full inception session is heavy: multi-phase facilitation, a persisted thinking graph, and a dialogue that runs long. Never open one on your own judgment.
25
26- **The user asked for inception explicitly** (/inception, "inception をやろう", "この構想をちゃんと固めたい") → start; no confirmation needed.
27- **Any other route** — you inferred the concept needs shaping, or another skill handed off here → **stop before creating or touching anything under .agents/inception/** and ask whether to start. In one or two lines say what the session costs (framing → diverge → structure → deepen → converge, a graph the user maintains with you, several rounds of questions), and name the lighter alternative: just continuing the current conversation. Begin only after the user agrees.
28
29This is a hard gate, not a notice. "Starting inception — say so if you'd rather not" does not satisfy it; neither does asking the framing questions first and calling it a session afterwards.
30
31## Your stance as orchestrator
32
This is a preview of SKILL.md. Download or install the skill to get the whole thing.
In the file
SKILL.md953 words
Files1
Licencenot declared
Why you can read it

Nothing in a skill executes. The client loads the text and the model follows it, so a skill can be audited the way a runbook is — by reading it.

What it costs in context

Skills are not billed by the call. They are paid for in context: every token the instructions occupy is a token your code, your diff and your conversation cannot use. Here is what this one takes and when it takes it.

≈120
always loaded
The name and description, so the model knows the skill exists and when to reach for it.
1,455
on trigger
The instruction body, read only when the skill fires.
0.79%
of a 200k window
Ten skills this size would take about 8% of the window before you open a file.
050k100k150k200k context window

1.6k tokens, estimated from the bundle at four bytes to the token, held for the rest of the session once it triggers. Middling. Fine to keep on in a project where you use it weekly, worth unloading in one where you never do.

Servers bill, skills cost

A server charges by the month. A skill charges once per session, in context, and then keeps charging it for as long as the session lives.

Before and after

The same question, put to the same model twice: once as it comes, and once with these instructions loaded.

No worked example has been published for this skill yet.

The procedure it runs

The procedure has not been set out here step by step. It is in the body of its SKILL.md: the start of it is shown above, and the whole file comes with the install.

Prose, not code

These steps are written for a model to follow, not executed by a runtime. It can still be told to skip one, and it will say so when it does.

Servers it uses

None. This skill calls no MCP servers at all.

Everything it needs is in the instructions, so it works in a project with nothing connected — the model reads the file and changes how it works with what it can already reach.

It asks the agent to write files, using whatever file access your client already has. Whether it reaches the network is not declared.

What it asks for
Writes filesyes
Network accessnot declared

Read from the allowed-tools line of this skill’s own SKILL.md. It also asks for Bash, which could do either, so what is not named there is not ruled out. A skill grants no permissions of its own — it can only ask for tools your client already has.

What it will not do

Every skill is narrow, and the useful ones say where they stop. These are the jobs this one is the wrong tool for.

What this skill is not for has not been published here. Nothing is implied by that: it is a section the author has not filled in.

What is in the bundle

1 file, 6.3 kB on disk. A bundle is text throughout: the instructions the model reads, plus the templates it fills in.

  • SKILL.md6.3 kB
What is not in it

No dependencies and nothing executable: a skill is text the agent reads, so the bundle is 1 file you can review in full before installing.

Install

Installing copies the bundle into your project. Nothing runs at install time — the files sit on disk until the model reads them.

# Inception — facilitate shaping a project's founding concept · 1.6k tokens when loaded · macOS, Linux mkdir -p .claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/inception-facilitate-shaping-a-project-s-founding/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/inception-facilitate-shaping-a-project-s-founding" ] && { [ ! -e .claude/skills/inception-facilitate-shaping-a-project-s-founding ] || { mv .claude/skills/inception-facilitate-shaping-a-project-s-founding "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/inception-facilitate-shaping-a-project-s-founding" .claude/skills/ && echo "Installed .claude/skills/inception-facilitate-shaping-a-project-s-founding"
On Windows, or any OS with Node 20+
npx mcprush@latest skill add choplin/inception-facilitate-shaping-a-project-s-founding

Windows PowerShell says 'running scripts is disabled on this system'? Run Set-ExecutionPolicy -Scope CurrentUser RemoteSigned once, or type npx.cmd instead of npx (codex.cmd, gemini.cmd, grok.cmd likewise). PowerShell 7 needs neither. Writes to .claude/skills/inception-facilitate-shaping-a-project-s-founding/ in the current project. For every project instead, run mkdir -p ~/.claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/inception-facilitate-shaping-a-project-s-founding/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/inception-facilitate-shaping-a-project-s-founding" ] && { [ ! -e ~/.claude/skills/inception-facilitate-shaping-a-project-s-founding ] || { mv ~/.claude/skills/inception-facilitate-shaping-a-project-s-founding "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/inception-facilitate-shaping-a-project-s-founding" ~/.claude/skills/ && echo "Installed ~/.claude/skills/inception-facilitate-shaping-a-project-s-founding" (macOS, Linux) — or add --global to the npx line. The curl line replaces .claude/skills/inception-facilitate-shaping-a-project-s-founding/ only after the download succeeds, so files left there by another skill of the same name, or by an older release, do not mix in. A copy already there is moved aside, not deleted, and the line prints where. It appears as inception in Gemini CLI, Codex, Copilot and Grok (its own name); Claude Code lists it by the folder name, inception-facilitate-shaping-a-project-s-founding.

Which clients pick it up on their own

A skill is a folder of text. Most of these read a skills folder and pick it up without being told; the rest take the same folder another way — an upload in the app, a parameter on an API call — and then choose it by its description just the same.

Claude Code.claude/skills/
Claude DesktopCustomize › Skills
ChatGPTSkills › Create › Upload
Cursor.cursor/skills/
VS Code.github/skills/
Codex CLI.agents/skills/
Gemini CLI.gemini/skills/
Grok Build.grok/skills/
Microsoft CopilotSkills › Upload a skill
PerplexityComputer › Skills › Upload a skill
DeepSeek Harness.dsh/skills/
Zed.agents/skills/
Devin Desktop.devin/skills/
Windsurf (legacy).windsurf/skills/
OpenAI Agents SDKInstructions or sandbox Skills
HTTP / APIa request parameter
This release
Versionnot versioned
Publishedno release date on file
PriceFree
Referencechoplin/inception-facilitate-shaping-a-project-s-founding

Versions

Its author publishes no version number, so there is nothing here to pin to: what you install is the folder as it stands today. Instructions change more often than APIs do — a skill can be rewritten entirely without anything it depends on moving.

Pinning

Nothing to pin to: this skill carries no version number of its own. What you install is what the folder holds on the day you install it.

Reviews

—no reviews yet

Nobody has reviewed this skill yet. The rating is the mean of the reviews written here, so there is none until somebody writes the first.

Sign in to review it

A review is tied to an account so it can be answered, edited and taken down by the person who wrote it.

Sign in
Who can post

Anybody with an account, one review each. It carries the version that was current when you wrote it, and the publisher may reply once.

Publisher
Servers1
Claim this skill