Is the P7 Advisor skill free?

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

What is the P7 Advisor SkillProof Score?

9.2/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 5/5.

How do I install P7 Advisor?

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 P7 Advisor 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.

P7 Advisor

Assesses engineer capability and promotion readiness against a first-tier tech P7 rubric

by chujianyun · chujianyun/skills

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 9.2/10
Tested: Jul 21, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 5bb216f

Fetched SKILL.md raw; frontmatter parses via PyYAML with name + a 351-char description. Body references no scripts or files (self-contained prompt), and the only aux file agents/openai.yaml returned HTTP 200; security scan found no curl|sh, base64, or exfiltration text. For output I fed one input ("Am I ready for P7?" with a vague payment-system self-description) to a baseline answer and a skill-following answer, both written to files. Baseline concluded "you're on a good track" and gave generic advice; the skill version returned "Not ready yet", scored each core signal and marked 5 of 7 "unknown" instead of inflating, downgraded "fixed bugs" to P6/P6+ execution, and rewrote a weak bullet into quantified P7 phrasing plus 2-4 week actions — a concrete, honest improvement.

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

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 8/10
Docs & honesty 5/5

What P7 Advisor does

A prompt-only Claude skill that evaluates an engineer's work evidence against a defined "first-tier tech company P7" capability model, returning a graded readiness verdict (Ready / Near ready / Not ready yet), flagged evidence gaps, and short-cycle growth actions. Triggers when the user asks for P7-level assessment, promotion readiness, capability-gap analysis, resume or project review, or interview prep. It scores only from stated evidence, marks missing dimensions as unknown rather than inventing, and rewrites weak resume bullets into quantified P7 phrasing.

How to install P7 Advisor

git clone --depth 1 https://github.com/chujianyun/skills.git /tmp/p7-advisor-src
mkdir -p ~/.claude/skills
cp -R /tmp/p7-advisor-src/skills/p7-advisor ~/.claude/skills/p7-advisor
# Pure prompt skill — no dependencies, scripts, API keys, or external tools.
# SKILL.md lands at ~/.claude/skills/p7-advisor/SKILL.md
# Also ships agents/openai.yaml (Codex/OpenAI agent manifest), not needed for Claude Code.

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

Commands — how to trigger P7 Advisor

/p7-advisor Assesses engineer capability and promotion readiness against a first-tier tech P7 rubric

It also activates on plain-language prompts like these:

Assess my promotion readiness for P7
Review my resume against P7 expectations
Prepare me for a P7 interview

Frequently asked questions

Is the P7 Advisor skill free?: Yes. The skill itself is free from chujianyun/skills. SkillProof publishes the install command and an independent test verdict at no cost.
Does P7 Advisor work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 21, 2026. Verdict: Tested · Works. Fetched SKILL.md raw; frontmatter parses via PyYAML with name + a 351-char description. Body references no scripts or files (self-contained prompt), and the only aux file agents/openai.yaml returned HTTP 200; security scan found no curl|sh, base64, or exfiltration text. For output I fed one input ("Am I ready for P7?" with a vague payment-system self-description) to a baseline answer and a skill-following answer, both written to files. Baseline concluded "you're on a good track" and gave generic advice; the skill version returned "Not ready yet", scored each core signal and marked 5 of 7 "unknown" instead of inflating, downgraded "fixed bugs" to P6/P6+ execution, and rewrote a weak bullet into quantified P7 phrasing plus 2-4 week actions — a concrete, honest improvement.
What is the P7 Advisor SkillProof Score?: 9.2/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 5/5.
How do I install P7 Advisor?: 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 P7 Advisor 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.