Skip to content
Agentmart
Submit a tool

ai-skills-bootstrap-project

Orchestrate the initial project bootstrap by sequencing repository, instruction-layer, framework, CI, and documentation setup in dependency order.

Skill by fabian-barney

IndexedApache-2.0★ 1
Write a review

Chalk Labs

Need help deploying ai-skills-bootstrap-project?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/fabian-barney-ai-skills-bootstrap-project

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Orchestrate the initial project bootstrap by sequencing repository, instruction-layer, framework, CI, and documentation setup in dependency order.

Use cases: devops

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/ai-skills-bootstrap-project

What's inside

Skill name
ai-skills-bootstrap-project
Description
Orchestrate the initial project bootstrap by sequencing repository, instruction-layer, framework, CI, and documentation setup in dependency order.
License
Apache-2.0
Instructions
141 lines in SKILL.md · view on GitHub

Files (2)

  • SKILL.md
  • bootstrap-surface-status.md · references/

SKILL.md (first lines)

<!-- markdownlint-disable MD025 -->

# Purpose

Run a clean project bootstrap sequence so the new project starts with a
repository home, downstream instruction wiring, framework baseline, CI, and
documentation that fit together.

# When to Use

- use when a new project must be bootstrapped end to end rather than through a
  single setup concern
- use when repository, ai-instructions, framework, CI, and documentation work
  must be sequenced safely
- use when later setup choices depend on earlier bootstrap outputs
- use `references/bootstrap-surface-status.md` when the composed bootstrap
  result must distinguish full completion from partial completion with named
  gaps

# Inputs

- the project goal, team, hosting constraints, and delivery expectations
- repository, framework, runtime, CI, and documentation preferences or
  constraints
- whether version-selection decisions for dependencies or support policy are
  already explicit
- which bootstrap surfaces are in or out of scope for the current project
- known blockers or partial-delivery expectations for any bootstrap surface
- `references/bootstrap-surface-status.md`

# Workflow

## Composed Skills

This is a composite skill. It orchestrates these children in dependency order:

- skill `ai-skills-bootstrap-repository`
- skill `ai-skills-bootstrap-ai-instructions`
- skill `ai-skills-bootstrap-framework-setup`
- skill `ai-skills-bootstrap-ci-pipeline`
- skill `ai-skills-bootstrap-documentation`

## Bootstrap Sequence

1. Confirm the project really needs a multi-surface bootstrap rather than a
   single leaf setup task.
2. Before running child skills, classify each bootstrap surface as in scope or
   `out-of-scope`. Use `out-of-scope` only for intentionally excluded
   surfaces. If an in-scope surface is intentionally not run, its final status
   must be `skipped` with an explicit reason. Then track final child results
   using only `completed`, `blocked`, `skipped`, or `out-of-scope` according
   to `references/bootstrap-surface-status.md`.
3. If `repository` is in scope and should run, apply skill `ai-skills-bootstrap-repository`
   to establish the hosted project home and repository-level policy decisions.
   If it is in scope but intentionally not run, do not run the child and
   record the surface in the next step with status `skipped`. Otherwise, do
   not run the child and record the surface in the next step with status
   `out-of-scope`.
4. Record the repository child result using the required per-surface fields
   from `references/bootstrap-surface-status.md`, including the final status,
   the child skill used, the handoff output or explicit `none`, and the
   blocker, skip reason, out-of-scope rationale, or named gap when the status
   is not `completed`.
5. If `ai-instructions` is in scope and should run, apply skill `ai-skills-bootstrap-ai-instructions`
   so the downstream instruction layer is wired before project-specific
   implementation patterns spread. If it is in scope but intentionally not
   run, do not run the child and record the surface in the next step with
   status `skipped`. Otherwise, do not run the child and record the surface in
   the next step with status `out-of-scope`.
6. Record the ai-instructions child result using the same required
   per-surface fields, including the handoff output or explicit `none`, plus
   the blocker, skip reason, out-of-scope rationale, or named gap when the
   status is not `completed`.
7. If `framework` is in scope and should run, apply skill `ai-skills-bootstrap-framework-setup`
   to establish the working framework, runtime, and toolchain baseline. If it
   is in scope but intentionally not run, do not run the child and record the
   surface in the next step with status `skipped`. Otherwise, do not run the
   child and record the surface in the next step with status `out-of-scope`.
8. Record the framework child result using the same required per-surface
   fields, including the handoff output or explicit `none`, plus the blocker,
   skip reason, out-of-scope rationale, or named gap when the status is not
   `completed`.
9. If `ci` is in scope and should run, apply skill `ai-skills-bootstrap-ci-pipeline`
   so the project baseline is checked continuously. If it is in scope but
   intentionally not run, do not run the child and record the surface in the
   next step with status `skipped`. Otherwise, do not run the child and record
   the surface in the next step with status `out-of-scope`.
10. Record the CI child result using the same required per-surface fields,
    including the handoff output or explicit `none`, plus the blocker, skip
    reason, out-of-scope rationale, or named gap when the status is not
    `completed`.
11. If `documentation` is in scope and should run, apply skill `ai-skills-bootstrap-documentation`
    last so the initial docs reflect the actual repository, framework, and CI
    decisions already made. If it is in scope but intentionally not run, do
    not run the child and record the surface in the next step with status
    `skipped`. Otherwise, do not run the child and record the surface in the
    next step with status `out-of-scope`.
12. Record the documentation child result using the same required
    per-surface fields, including the handoff output or explicit `none`, plus
    the blocker, skip reason, out-of-scope rationale, or named gap when the
    status is not `completed`.
13. Distinguish a full bootstrap from a partial bootstrap. Full bootstrap
    means every in-scope child finished as `completed` and every excluded
    surface is explicitly `out-of-scope`; partial bootstrap means one or more
    in-scope children are `blocked` or `skipped`, and each gap must be named
    explicitly.

# Outputs

- an ordered project-bootstrap decision record
- all in-scope bootstrap surfaces delegated to the correct child skills
- a per-surface status record using only `completed`, `blocked`, `skipped`, or
  `out-of-scope`
- explicit surface handoff outputs and named remaining gaps when the bootstrap is
  partial
- a coherent starting project baseline across repository, instructions,
  framework, CI, and documentation

# Guardrails

From fabian-barney/ai-skills, Apache-2.0.

More from fabian-barney/ai-skills

Signals

Stars
1
Forks
0
Open issues
2
Last commit (this folder)
May 21, 2026 (5 months ago)
Last release
Jun 2, 2026 (5 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
Apache-2.0
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from fabian-barney

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get ai-skills-bootstrap-project running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying ai-skills-bootstrap-project?

CallGet help
Cite this page

ai-skills-bootstrap-project. Agent Mart. https://agentmart.dev/skills/fabian-barney-ai-skills-bootstrap-project (last updated 2026-10-24)