Is the Reflection skill free?

Yes. The skill itself is free from feiskyer/claude-code-settings. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Reflection SkillProof Score?

8.0/10 — installs cleanly 3/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 4/5.

How do I install Reflection?

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 Reflection 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.

Reflection

Session-reflection subagents that capture learnings and improve CLAUDE.md — not a SKILL.md.

by feiskyer · feiskyer/claude-code-settings

Works with setup

Install — copy the command Download source ↗

Test report

Verdict: Works with setup
Score: 8.0/10
Tested: Jul 20, 2026
Environment: Claude Code 2.x (agent harness)

⚠ This skill is no longer available upstream. Our re-check on Aug 10, 2026 couldn't find it any more (SKILL.md not found in repo tree). The test below is what we measured on Jul 20, 2026 and we're leaving it up as a record — but there is nothing left to install, so we've removed the command.

Fetched the recursive tree: repo has NO reflection SKILL.md — the slug maps to agents/deep-reflector.md and agents/instruction-reflector.md (README lists both in the agents table). Read both raw: valid subagent frontmatter (name+description), pure-prompt, zero scripts/URLs/base64/exfiltration, so I measured output for real. TRIGGER (5/5): loads on "reflect on this session and capture learnings", "review our chat and improve my CLAUDE.md", "extract patterns and my preferences from today"; skips "fix the failing test in auth.py" and "build a Reflection React component". Verdict setup not pass: the catalogued "reflection skill" doesn't exist as a skill — you must install two subagents into agents/, neither literally named "reflection."

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

Installs cleanly 3/5
Triggers reliably 5/5
Output vs. baseline 8/10
Docs & honesty 4/5

What Reflection does

"Reflection" is delivered as two Claude Code subagents — deep-reflector (analyzes a work session and extracts patterns, user preferences, and CLAUDE.md updates) and instruction-reflector (reviews chat history to improve CLAUDE.md instructions). Triggers after a significant session when you want to capture learnings or tune your assistant instructions. There is no skill named "reflection" — it installs as agents, not a skill.

How to install Reflection

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 Reflection

/reflection Session-reflection subagents that capture learnings and improve CLAUDE.md — not a SKILL.md.

It also activates on plain-language prompts like these:

Reflect on this session and update CLAUDE.md
Extract learnings from today's debugging work
Run a deep reflection on our collaboration

Frequently asked questions

Is the Reflection skill free?: Yes. The skill itself is free from feiskyer/claude-code-settings. SkillProof publishes the install command and an independent test verdict at no cost.
Does Reflection work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 20, 2026. Verdict: Works with setup. Fetched the recursive tree: repo has NO reflection SKILL.md — the slug maps to agents/deep-reflector.md and agents/instruction-reflector.md (README lists both in the agents table). Read both raw: valid subagent frontmatter (name+description), pure-prompt, zero scripts/URLs/base64/exfiltration, so I measured output for real. TRIGGER (5/5): loads on "reflect on this session and capture learnings", "review our chat and improve my CLAUDE.md", "extract patterns and my preferences from today"; skips "fix the failing test in auth.py" and "build a Reflection React component". Verdict setup not pass: the catalogued "reflection skill" doesn't exist as a skill — you must install two subagents into agents/, neither literally named "reflection."
What is the Reflection SkillProof Score?: 8.0/10 — installs cleanly 3/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 4/5.
How do I install Reflection?: 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 Reflection 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.