advise-project-approach

advise-project-approach is an agent skill for project planning, course correction, and review. Its portable SKILL.md can be loaded by Codex, Claude Code, pi, Hermes, and other Agent Skills-compatible harnesses.

Portability is a design contract, not proof of identical behavior in every host. See the host evidence matrix.

Before recommending a stack, architecture, vendor, refactor, or shipping plan, it checks:

• your actual constraints
• comparable real-world projects
• tradeoffs and failure conditions
• cost and lock-in realities
• when the recommendation becomes wrong

Use It When

• you have a rough project idea and need a build plan
• your repo is getting messy and you need course correction
• you are choosing between stacks or vendors
• you want a review before shipping
• you want the agent to explain what not to build yet

One-Line Install

npx skills@latest add AaravKashyap12/advise-project-approach --skill advise-project-approach

This uses the open skills installer to fetch the repo from GitHub and install only this skill. It requires Node.js/npm. Review installed skills before use; skills run with your agent's normal permissions.

Source of Truth

The runtime skill spec lives in skills/advise-project-approach/SKILL.md. That file is the source of truth for the workflow agents actually run.

Everything else in this repo exists to package, explain, test, or distribute that skill.

What's New in v0.7.2

v0.7.2 addresses concrete failures found by independent audits, adversarial package tests, and repeated model evaluations.

• Adds no-clobber and recovery checks for advice that changes user data, plus stronger concurrency-test guidance.
• Keeps private project details out of public research queries and stops research after an inconclusive follow-up.
• Clarifies project-stage routing, accepted intake unknowns, safety prerequisites, and requested answer limits.
• Hardens YAML/metadata, archive integrity, release consistency, and failed-build handling, with permanent regression tests.
• Preserves failures, mixed baseline comparisons, and post-fix evidence in a dedicated audit report.

See the full changelog for earlier versions.

Where This Fits

Use recent-signal tools to discover what changed.

Use advise-project-approach to decide what to build, change, defer, or avoid.

The skill is not trying to be a general search engine. It is a project-judgment workflow for turning evidence into engineering decisions.

Try These Prompts

"What's the best way to build a self-hosted bookmark manager?"
"Research comparable projects before I start this."
"I'm halfway through building a Node/Express API. Is my approach right?"
"Review my finished project at github.com/owner/repo."
"Should I use Postgres or SQLite for this?"
"What stack should I use given I know Python and want to self-host?"
"Should I use Supabase/Firebase/Neon/Vercel, or will pricing hurt later?"

What It Does

Drop it into your agent and it will:

• Pre-build: Research your stack, find comparable real projects, compare architecture options, and hand you a build plan before you commit to anything you will regret in month three.
• Mid-build: Inspect your repo, identify what is actually wrong, not just what is fashionable to fix, and give you a prioritized list of changes ordered by impact.
• Post-build: Review your finished project against mature comparables, call out the gaps, and tell you what to harden before you ship.

It does the research loop a good engineer would do manually: understand the goal, inspect the evidence, study credible comparables, evaluate the tradeoffs, and recommend the highest-leverage path.

No vibes. Evidence first.

Works Across Agent Harnesses

The workflow is self-contained in its runtime skill file:

skills/advise-project-approach/SKILL.md

From a local clone, install the same skill folder into the location your harness scans:

cp -r skills/advise-project-approach <your-agent-skill-directory>/

Pi documents recursive discovery of directories containing SKILL.md and permits freeform additional files. See pi's skill documentation.

The packaged .skill archive, .claude-plugin/plugin.json, and agents/openai.yaml are additive compatibility layers for installers and host UIs. They do not change the portable SKILL.md workflow, and harnesses that do not use them can ignore them.

Other Install Methods

To inspect the available skill before installing:

npx skills@latest add AaravKashyap12/advise-project-approach --list

Manual Download

Download the packaged skill:

dist/advise-project-approach.skill

Or install from the GitHub release:

Download the v0.7.2 release asset

Skill UI

1. Download dist/advise-project-approach.skill.
2. Open your agent's skill settings.
3. Upload the .skill file.
4. Start a new conversation.

Plugin Metadata

This repo also includes .claude-plugin/plugin.json for plugin-aware installers that can read skill collections from GitHub repositories.

Demo

You: I want to build a self-hosted bookmark manager. Solo dev, Python background, want tags and full-text search.

Agent, with skill: researches linkding, Linkwarden, LinkAce, official framework docs, and relevant search/storage options.

## Project Approach: Self-Hosted Bookmark Manager

### TL;DR
Go with Django + SQLite FTS5 or Postgres full-text search, depending on your hosting target and expected scale. Keep the main UI server-rendered with HTMX, Turbo, or light JavaScript unless the UI needs true SPA complexity. This matches your Python skills, keeps deployment simple, and is backed by nearby real projects like linkding.

### Comparable Projects
1. linkding - github.com/sissbruecker/linkding; Django, DRF, Huey, Turbo/Lit, Docker, optional Postgres; nearest domain match; limits: current details must be verified at review time.
2. Linkwarden - github.com/linkwarden/linkwarden; heavier collaborative bookmark manager; useful contrast for when archiving/collaboration matter more than simplicity.
3. LinkAce - linkace.org; mature self-hosted bookmark manager in a different stack; useful for feature comparison, less useful for implementation fit.

The demo avoids hard-coded star counts and "latest" dates because those decay. The skill requires the agent to verify those values at review time.

See more examples:

• [Illustrative contrasts with generic advice, not measured A/B tests](./examples/ab-comparisons.md