Is the Analysis Pipeline (Greenfield) skill free?

Yes. The skill itself is free from prime-radiant-inc/greenfield. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Analysis Pipeline (Greenfield) SkillProof Score?

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

How do I install Analysis Pipeline (Greenfield)?

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 Analysis Pipeline (Greenfield) 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.

Analysis Pipeline (Greenfield)

Reverse-engineer code into clean-room behavioral specs with provenance

by prime-radiant-inc · prime-radiant-inc/greenfield

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 8.0/10
Tested: Jul 18, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Jul 30, 2026 · ea02964

⚠ 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 18, 2026 and we're leaving it up as a record — but there is nothing left to install, so we've removed the command.

Ran the methodology on a real function (a tool-output classifier from the memvid SDK) against a no-skill baseline. The baseline narrated implementation - it named the function, said it 'lowercases' and 'switches' - while the skill-guided spec stripped those source identifiers, made the load-bearing 'content signal beats originating tool' precedence rule explicit, added source/confidence provenance annotations, and produced Given/When/Then test vectors including the override edge case the baseline buried. For clean-room reimplementation that is a concrete, defensible improvement. Caveat: the skill-dir copy is methodology text only; the /analyze and /sanitize commands and 20+ sub-skills that run the full gated pipeline live elsewhere in the plugin, so end-to-end orchestration was not exercised.

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

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

What Analysis Pipeline (Greenfield) does

Master methodology for reverse engineering: analyze a codebase, binary, or runtime and emit implementation-agnostic behavioral specs where every claim carries a provenance citation and confidence level, plus Given/When/Then test vectors. Triggers on reverse-engineering a product into specs or building clean-room documentation. Orchestrates a 7-layer gated pipeline over many source types.

How to install Analysis Pipeline (Greenfield)

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 Analysis Pipeline (Greenfield)

/analysis-pipeline Reverse-engineer code into clean-room behavioral specs with provenance

It also activates on plain-language prompts like these:

Reverse engineer this binary into a clean-room behavioral spec.
I need implementation-agnostic specs with provenance for this codebase.
Analyze this function's behavior and give me Given/When/Then test vectors.

Frequently asked questions

Is the Analysis Pipeline (Greenfield) skill free?: Yes. The skill itself is free from prime-radiant-inc/greenfield. SkillProof publishes the install command and an independent test verdict at no cost.
Does Analysis Pipeline (Greenfield) work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 18, 2026. Verdict: Tested · Works. Ran the methodology on a real function (a tool-output classifier from the memvid SDK) against a no-skill baseline. The baseline narrated implementation - it named the function, said it 'lowercases' and 'switches' - while the skill-guided spec stripped those source identifiers, made the load-bearing 'content signal beats originating tool' precedence rule explicit, added source/confidence provenance annotations, and produced Given/When/Then test vectors including the override edge case the baseline buried. For clean-room reimplementation that is a concrete, defensible improvement. Caveat: the skill-dir copy is methodology text only; the /analyze and /sanitize commands and 20+ sub-skills that run the full gated pipeline live elsewhere in the plugin, so end-to-end orchestration was not exercised.
What is the Analysis Pipeline (Greenfield) SkillProof Score?: 8.0/10 — installs cleanly 5/5, triggers reliably 4/5, output vs. baseline 7/10, docs & honesty 4/5.
How do I install Analysis Pipeline (Greenfield)?: 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 Analysis Pipeline (Greenfield) 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.