Is the Foundational Review skill free?

Yes. The skill itself is free from mikeprasad/aria-knowledge. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Foundational Review SkillProof Score?

8.0/10 — installs cleanly 4/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 4/5.

How do I install Foundational Review?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Foundational Review with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Foundational Review

Pre-decision review: verdict, premises and an irreversibility inventory

by mikeprasad · mikeprasad/aria-knowledge

Works with setup

Install — copy the command Download source ↗

Test report

Verdict: Works with setup
Score: 8.0/10
Tested: Jul 25, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Jul 30, 2026 · ebb3dba

⚠ This skill is no longer available upstream. Our re-check on Aug 10, 2026 couldn't find it any more (repo unreachable/deleted). The test below is what we measured on Jul 25, 2026 and we're leaving it up as a record — but there is nothing left to install, so we've removed the command.

Gated a 'tag v1.0 and freeze the public API of a small CLI' decision both ways: the baseline gave sensible pros/cons prose, while the skill forced a fixed-vocabulary verdict, a premises table with 'if it changes' consequences, and an irreversibility inventory that surfaced exactly what gets expensive after the freeze -- a lens the baseline missed. The core artifact clearly beats ad-hoc, but the friction is real: Step 5 invokes /prospect, the pairing check invokes /readiness-audit, and Step 7 invokes /extract -- all sibling aria skills absent in a standalone install, and the chain-doc load path uses ${CLAUDE_PLUGIN_ROOT} which is unset outside the plugin. The co-located foundational-review-chain.md installs correctly next to SKILL.md.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 4/5
Triggers reliably 5/5
Output vs. baseline 7/10
Docs & honesty 4/5

What Foundational Review does

Runs a decision-anchored review of a project before an irreversible step (a v1.0 freeze, schema/spec tag, API or repo public-flip, or major re-scope), producing a fixed-vocabulary verdict resting on a named premises table, A-F review sections, an irreversibility inventory, and cold-executable specs/plans. Triggers on '/foundational-review', 'review this at the foundations', or 'is this the right thing built the right way'. Refuses to run without a named irreversible decision and redirects instead.

How to install Foundational Review

Nothing to install: the source repository no longer has this skill. If the author brings it back, our daily re-check will pick it up and the command will reappear here.

Commands — how to trigger Foundational Review

/foundational-review Pre-decision review: verdict, premises and an irreversibility inventory

It also activates on plain-language prompts like these:

Run a foundational review before we tag v1.0 and freeze the API
Is this the right thing built the right way before we go public?
Review this at the foundations before the schema freeze

Frequently asked questions

Is the Foundational Review skill free?: Yes. The skill itself is free from mikeprasad/aria-knowledge. SkillProof publishes the install command and an independent test verdict at no cost.
Does Foundational Review work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 25, 2026. Verdict: Works with setup. Gated a 'tag v1.0 and freeze the public API of a small CLI' decision both ways: the baseline gave sensible pros/cons prose, while the skill forced a fixed-vocabulary verdict, a premises table with 'if it changes' consequences, and an irreversibility inventory that surfaced exactly what gets expensive after the freeze -- a lens the baseline missed. The core artifact clearly beats ad-hoc, but the friction is real: Step 5 invokes /prospect, the pairing check invokes /readiness-audit, and Step 7 invokes /extract -- all sibling aria skills absent in a standalone install, and the chain-doc load path uses ${CLAUDE_PLUGIN_ROOT} which is unset outside the plugin. The co-located foundational-review-chain.md installs correctly next to SKILL.md.
What is the Foundational Review SkillProof Score?: 8.0/10 — installs cleanly 4/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 4/5.
How do I install Foundational Review?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Foundational Review with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.