AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Agents Md Bootstrap

skill-narek-khachikyan-skillranger-frontend-agents-md-bootstrap · by Narek-Khachikyan

Create or improve frontend AGENTS.md guidance with project commands, architecture notes, coding conventions, validation steps, and agent safety boundaries.

No reviews yet
0 installs
0 views
view→install

Install

$ agentstack add skill-narek-khachikyan-skillranger-frontend-agents-md-bootstrap

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-narek-khachikyan-skillranger-frontend-agents-md-bootstrap)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
today

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Agents Md Bootstrap? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Frontend AGENTS.md Bootstrap

Use this skill when creating or improving repo-local AGENTS.md guidance for a frontend project so coding agents understand commands, architecture, conventions, validation steps, and safety boundaries. Do not use it for generic README writing, public product documentation, or agent rules that conflict with the repository's actual scripts and structure.

Decision Rules

  • Ground every instruction in files that exist in the repository.
  • Prefer concise, durable guidance over long policy text that will drift quickly.
  • Include commands only when they are discoverable from project config or documentation.
  • Keep agent safety boundaries explicit: do not invent secrets, deployment actions, or destructive maintenance rituals.

Workflow

  1. Inspect package scripts, test config, build config, framework files, folder structure, and existing docs.
  2. Identify the project stack, source layout, common commands, test strategy, style conventions, and generated artifacts to avoid editing.
  3. Draft guidance sections for overview, setup assumptions, commands, coding conventions, validation, and agent-specific cautions.
  4. Add repo-specific notes only when supported by evidence from files or existing docs.
  5. Keep the document short enough that an agent can use it as active context.
  6. Flag any missing information the maintainer should confirm instead of guessing.

References

  • No packaged references are required for this MVP skill.
  • When available in the project, inspect package.json, README files, framework config, test config, CI workflow, and existing agent or editor rules.

Validation

  • Every command in the output should match a real script, config, or documented workflow.
  • The guidance should avoid credentials, private deployment steps, and machine-specific absolute paths.
  • If the project already has AGENTS.md, proposed edits should preserve valid existing conventions and remove only stale or contradictory text with evidence.

Output Contract

  • Provide the proposed AGENTS.md structure or patch summary.
  • Cite the project files that justify commands and conventions.
  • List validation commands run or recommended.
  • Call out assumptions, missing maintainer decisions, and any safety-sensitive guidance.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.