Is the Intended vs Implemented skill free?

Yes. The skill itself is free from phuryn/pm-skills. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Intended vs Implemented SkillProof Score?

7.2/10 — installs cleanly 5/5, triggers reliably 4/5, output vs. baseline 5/10, docs & honesty 4/5.

How do I install Intended vs Implemented?

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 Intended vs Implemented 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.

Intended vs Implemented

Finds gaps between documented intent and actual code, like undocumented access-control drift.

by phuryn · phuryn/pm-skills

Works with setup

Install — copy the command Download source ↗

Test report

Verdict: Works with setup
Score: 7.2/10
Tested: Jul 11, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · fd52d02

Installed verbatim (git clone + cp) with zero surgery — single-file SKILL.md, strict-YAML frontmatter, no missing deps or API keys. Tested on a Flask access-control audit where docs (permissions.md) diverge from routes.py; the skill correctly found both critical gaps (unguarded DELETE and admin-only private-notes leak) and confirmed the one correctly-enforced rule. A/B: the base arm (no skill) caught the identical two gaps and the same correct case with no false positives, so on this task the skill added no measurable lift over baseline.

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 5/10
Docs & honesty 4/5

What Intended vs Implemented does

The method for finding the gap between what a system is supposed to do and what the code actually does — the class of bug generic scanners miss because they have no model of intent. Defines what counts as documented intent, what counts as implementation evidence, which mismatches matter, and how to avoid hand-wavy findings. Use when auditing AI-built code, reviewing access control against…

How to install Intended vs Implemented

git clone https://github.com/phuryn/pm-skills
cd pm-skills
mkdir -p ~/.claude/skills
cp -r pm-ai-shipping/skills/intended-vs-implemented ~/.claude/skills/intended-vs-implemented

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Intended vs Implemented

/intended-vs-implemented Finds gaps between documented intent and actual code, like undocumented access-control drift.

It also activates on plain-language prompts like these:

Check if this code matches its own documentation
Audit access control against the documented permissions
Find where the implementation diverges from the spec

Frequently asked questions

Is the Intended vs Implemented skill free?: Yes. The skill itself is free from phuryn/pm-skills. SkillProof publishes the install command and an independent test verdict at no cost.
Does Intended vs Implemented work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 11, 2026. Verdict: Works with setup. Installed verbatim (git clone + cp) with zero surgery — single-file SKILL.md, strict-YAML frontmatter, no missing deps or API keys. Tested on a Flask access-control audit where docs (permissions.md) diverge from routes.py; the skill correctly found both critical gaps (unguarded DELETE and admin-only private-notes leak) and confirmed the one correctly-enforced rule. A/B: the base arm (no skill) caught the identical two gaps and the same correct case with no false positives, so on this task the skill added no measurable lift over baseline.
What is the Intended vs Implemented SkillProof Score?: 7.2/10 — installs cleanly 5/5, triggers reliably 4/5, output vs. baseline 5/10, docs & honesty 4/5.
How do I install Intended vs Implemented?: 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 Intended vs Implemented 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.