AgentStack
SKILL verified MIT Self-run

Project Discovery

skill-ntaffzii-skill-agents-project-discovery · by ntaffzii

Explore and summarize an unfamiliar or existing project before planning, editing, onboarding, architecture review, migration, stack choice, or implementation. Use when the user asks to understand a repo, inspect architecture, map a codebase, discover project conventions, or prepare a project overview.

No reviews yet
0 installs
18 views
0.0% view→install

Install

$ agentstack add skill-ntaffzii-skill-agents-project-discovery

✓ 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.

Are you the author of Project Discovery? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Project Discovery

Build a practical understanding of a project before proposing or making changes.

Workflow

  1. Identify the goal
  • Determine whether the user needs an overview, architecture summary, stack analysis, risk assessment, implementation plan, migration direction, or onboarding notes.
  1. Inspect high-signal files
  • Read README.md, project instructions, package manifests, lockfiles, docs, architecture notes, CI config, test config, and main entry points.
  • Prefer actual files over guesses.
  1. Map the system
  • Identify core modules, data flow, user-facing surfaces, external services, build commands, test commands, deployment hints, and local conventions.
  • Note areas that need follow-up inspection instead of pretending certainty.
  1. Assess readiness
  • Call out missing docs, unclear ownership, brittle tests, risky dependencies, weak validation, or hidden configuration.
  • Keep recommendations incremental.
  1. Report
  • Respond in the user's language.
  • Link to files when possible.
  • End with a practical next step.

Output Format

# Project Discovery

## What This Project Does

## Stack

## Important Files

## Architecture Notes

## Development Workflow

## Risks And Unknowns

## Recommended Next Steps

Rules

  • Do not propose broad rewrites before understanding local patterns.
  • Distinguish verified facts from assumptions.
  • Keep the report useful for the next action, not encyclopedic.

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.