Skip to content
Agentmart
Submit a tool

ai-skills-bootstrap-ai-instructions

Bootstrap the downstream ai-instructions layer for a repository by following the authoritative upstream setup source instead of copying or reinventing it…

Skill by fabian-barney

IndexedApache-2.0★ 1
Write a review

Chalk Labs

Need help deploying ai-skills-bootstrap-ai-instructions?

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-ai-instructions

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

Bootstrap the downstream ai-instructions layer for a repository by following the authoritative upstream setup source instead of copying or reinventing it locally.

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-ai-instructions

What's inside

Skill name
ai-skills-bootstrap-ai-instructions
Description
Bootstrap the downstream ai-instructions layer for a repository by following the authoritative upstream setup source instead of copying or reinventing it locally.
License
Apache-2.0
Instructions
86 lines in SKILL.md · view on GitHub

Files (2)

  • SKILL.md
  • upstream-ai-instructions.md · references/

SKILL.md (first lines)

<!-- markdownlint-disable MD025 -->

# Purpose

Wire the downstream `ai-instructions` layer into a repository while keeping the
authoritative setup flow in the upstream `ai-instructions` repository and the
project-specific context in the local repository.

# When to Use

- use when a repository should gain its initial `ai-instructions` layer during
  project bootstrap
- use when the project needs local AI entrypoints, extension hooks, or wiring
  to shared skills and agents
- use when the repository should stay project-owned without copying canonical
  `ai-skills` behavior into local instruction files
- use `references/upstream-ai-instructions.md` for the authoritative upstream
  repository URL and the setup-source contract

# Inputs

- the repository context and the AI surfaces the project wants to enable
- the upstream `ai-instructions` repository at
  `https://github.com/fabian-barney/ai-instructions`
- any setup instructions actually present in that upstream repository
- the shared skills, agents, or default workflows the repository should point
  at
- any local extension points, policies, or project-specific notes that belong
  in the downstream layer
- constraints on target assistants or environments that consume the
  instruction layer
- `references/upstream-ai-instructions.md`

# Workflow

1. Confirm the repository should install a downstream `ai-instructions` layer
   rather than embedding shared behavior directly into local files.
2. Treat `https://github.com/fabian-barney/ai-instructions` as the
   authoritative upstream source for `ai-instructions` bootstrap and setup.
3. Inspect the upstream repository for the setup instructions required to
   install or initialize the downstream layer.
4. If the upstream setup instructions are missing, incomplete, or ambiguous,
   stop blocked and report the upstream documentation gap explicitly instead of
   inventing local replacement steps.
5. When upstream setup instructions are present, follow them as the source of
   truth for establishing the downstream layer.
6. After the upstream setup is in place, identify the minimal local instruction
   surfaces the project actually needs.
7. Point the local layer at shared `ai-skills` or agent behavior instead of
   copying those instructions into the repository.
8. Add only the project-owned notes, extensions, and context that belong
   locally.
9. Record how the downstream layer should evolve when the project adds new
   shared skills or local constraints.

# Outputs

- a downstream `ai-instructions` baseline when authoritative upstream setup
  instructions exist
- an explicit blocked result when the upstream repository does not provide
  usable setup instructions
- explicit links between local instruction surfaces and shared catalog
  behavior
- a clear separation between shared and project-owned AI context

# Guardrails

- do not treat any local reconstruction as a substitute for the upstream
  `ai-instructions` setup source
- do not copy canonical skill behavior into downstream instruction files when a
  shared skill should remain the source of truth
- do not broaden this skill into full project bootstrap orchestration
- do not assume one assistant or tool consumes the downstream layer unless the
  project requires it
- do not leave repository-specific extensions undocumented

# Exit Checks

- the authoritative upstream repository URL is explicit
- the workflow either followed upstream setup instructions or reported the
  missing-instructions blocker explicitly
- shared behavior remains centralized in `ai-skills` rather than copied
- local instruction content is limited to project-owned context and extensions
- the intended consumers or target surfaces are explicit enough for follow-up
  work

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

Signals

Stars
1
Forks
0
Open issues
2
Last commit (this folder)
May 17, 2026 (6 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

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-ai-instructions 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-ai-instructions?

CallGet help
Cite this page

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