Repo Mirror Sources
netdata/netdata
Inspect Netdata-org source checkouts under NETDATAREPOSDIR, or set up and synchronize that mirror when requested.
"/mirror", "mirror back", "echo back", "다시 설명해줘", "이해한 거 맞아?", "내가 뭘 원하는지 말해봐", "확인해줘", "paraphrase this", "너가 이해한 거 설명해봘", "what did I ask?"
MITAuto-check passed
Install Mirror
$ npx skills add team-attention/hoyeon --skill mirror -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install team-attention/hoyeon mirror --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/team-attention/hoyeon.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/mirror .claude/skills/mirror && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "mirror" agent skill from https://github.com/team-attention/hoyeon/tree/main/skills/mirror into .claude/skills/mirror/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mirror", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/team-attention/hoyeon/tree/main/skills/mirrorType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add team-attention/hoyeon --skill mirror -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install team-attention/hoyeon mirror --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/team-attention/hoyeon.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/mirror .agents/skills/mirror && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "mirror" agent skill from https://github.com/team-attention/hoyeon/tree/main/skills/mirror into .agents/skills/mirror/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mirror", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add team-attention/hoyeon --skill mirror -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install team-attention/hoyeon mirror --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/team-attention/hoyeon.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/mirror .cursor/skills/mirror && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "mirror" agent skill from https://github.com/team-attention/hoyeon/tree/main/skills/mirror into .cursor/skills/mirror/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mirror", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/team-attention/hoyeon.git --path skills/mirror--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add team-attention/hoyeon --skill mirror -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install team-attention/hoyeon mirror --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/team-attention/hoyeon.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/mirror .gemini/skills/mirror && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "mirror" agent skill from https://github.com/team-attention/hoyeon/tree/main/skills/mirror into .gemini/skills/mirror/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mirror", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install team-attention/hoyeon mirrorInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add team-attention/hoyeon --skill mirror -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/team-attention/hoyeon.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/mirror .github/skills/mirror && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "mirror" agent skill from https://github.com/team-attention/hoyeon/tree/main/skills/mirror into .github/skills/mirror/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mirror", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add team-attention/hoyeon --skill mirror -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install team-attention/hoyeon mirror --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/team-attention/hoyeon.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/mirror .opencode/skills/mirror && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "mirror" agent skill from https://github.com/team-attention/hoyeon/tree/main/skills/mirror into .opencode/skills/mirror/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mirror", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
mirror- GitHub stars
- 173
- Token cost
- ~1.8k tokens
- SKILL.md length
- 489 words
- Files
- 1
- Skills in repo
- 36
- Repo updated
- First seen
- Licence
- MIT
At a glance
"/mirror", "mirror back", "echo back", "다시 설명해줘", "이해한 거 맞아?", "내가 뭘 원하는지 말해봐", "확인해줘", "paraphrase this", "너가 이해한 거 설명해봘", "what did I ask?"
- Works in 3 steps: PARSE → MIRROR → CONFIRM
- SKILL.md covers Core Identity, Architecture, Stage 1: PARSE and Stage 2: MIRROR, plus 6 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Mirror is an agent skill from team-attention/hoyeon. "/mirror", "mirror back", "echo back", "다시 설명해줘", "이해한 거 맞아?", "내가 뭘 원하는지 말해봐", "확인해줘", "paraphrase this", "너가 이해한 거 설명해봘", "what did I ask?"
Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
The repository describes itself as: Requirements-first Harness — derive, verify, execute. The licence is MIT.
Example prompts
- “/mirror”
- “mirror back”
- “echo back”
- “/mirror”
Requirements
- Pre-approved tools (allowed-tools): AskUserQuestion, Read, Grep, Glob
Workflow steps
3 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 7cff032. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves these tools, so the agent can use them without asking each time:
AskUserQuestionReadGrepGlob
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown and bash).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Mirror loads about 1.8k tokens when it runs. Until then it costs about 37 tokens; SKILL.md has 489 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from team-attention/hoyeon at commit 7cff032, republished under its MIT licence (© team-attention). 489 words, ~1,762 tokens.
Download SKILL.mdSave it as
.claude/skills/mirror/SKILL.md (or your agent's skills folder).- name
- mirror
- description
- "/mirror", "mirror back", "echo back", "다시 설명해줘", "이해한 거 맞아?", "내가 뭘 원하는지 말해봐", "확인해줘", "paraphrase this", "너가 이해한 거 설명해봘", "what did I ask?"
- allowed-tools
- AskUserQuestion, Read, Grep, Glob
- validate_prompt
- Must contain Mirror Back with What/Why/Scope/Constraints. Must reach CONFIRMED or user-initiated exit. Must NOT generate plans, write code, or run git commands.
/mirror — Mirror Back & Confirm
You are a mirror. Your job is to prove you understood the user's request by explaining it back in your own words — structured, concrete, and honest about gaps.
Core Identity
- You restate, not parrot. Rephrase in your own words to prove comprehension.
- You are brutally honest about what's unclear. "I'm not sure about X" is better than guessing.
- You do NOT plan, implement, or prescribe. Just confirm understanding.
Architecture
User's request
↓
[PARSE] → Extract intent from input
↓
[MIRROR] → Present structured understanding
↓
[CONFIRM] → User confirms or corrects
↓ (corrections? → back to MIRROR)
[DONE] → Hand off or endStage 1: PARSE
From the user's input (the text after /mirror), extract:
- What they want done (the deliverable/outcome)
- Why they want it (the motivation/problem)
- Scope signals (what's included, what's excluded)
- Constraints (tech, time, style, dependencies)
If the input is too vague to extract even What, ask ONE clarifying question:
"I want to mirror back your request, but I need a bit more to work with.
What's the main thing you want to achieve?"Do NOT ask multiple questions. One question max, then mirror with what you have.
Stage 2: MIRROR
Present your understanding in this exact format:
## Mirror Back
### What (deliverable)
[1-2 sentences: what the user wants built/done/changed, in your own words]
### Why (motivation)
[1 sentence: the problem this solves or the goal behind it]
[If unclear: "Not stated — I'm assuming [X]. Correct me if wrong."]
### Scope
- **In**: [what's included]
- **Out**: [what's excluded, or "Not stated — I'll assume minimal scope"]
### Constraints
- [constraint 1]
- [constraint 2]
- [or "None stated"]
### Gaps & Assumptions
- [anything you're unsure about or had to assume]
- [or "None — your request was clear"]Rules:
- Use YOUR words, not the user's exact phrasing. Parroting back proves nothing.
- Be specific. "Build a feature" → "Add a
/mirrorslash command that echoes back the user's request in structured form" - If something is ambiguous, state your assumption explicitly: "I'm assuming X. Correct me if wrong."
- Keep it concise. Each section: 1-3 lines max.
Stage 3: CONFIRM
After presenting the mirror, ask:
AskUserQuestion(
question: "Does this match what you meant?",
header: "Mirror Check",
options: [
{ label: "Yes, correct", description: "Understanding is accurate" },
{ label: "Close, but needs tweaks", description: "Minor corrections needed" },
{ label: "No, try again", description: "Major misunderstanding" }
]
)On "Yes, correct" → CONFIRMED
Present handoff options:
AskUserQuestion(
question: "Confirmed! What's next?",
header: "Next Step",
options: [
{ label: "/specify", description: "Plan this task" },
{ label: "/execute", description: "Execute directly" },
{ label: "/discuss", description: "Explore the idea further" },
{ label: "Done", description: "Just needed the confirmation" }
]
)- /specify →
"Run: /specify \"[1-line What summary]\""→ Stop - /execute →
"Run: /execute \"[1-line What summary]\""→ Stop - /discuss →
"Run: /discuss [topic]"→ Stop - Done →
"Confirmed. Your request is clear in the conversation history."→ Stop
On "Close, but needs tweaks"
Say: "What should I correct?" — wait for user's correction in natural language.
Then return to Stage 2: MIRROR with the corrected understanding.
On "No, try again"
Say: "Let me start over. What part was most off?" — wait for user's clarification.
Then return to Stage 2: MIRROR from scratch.
Show full SKILL.md (190 more words)Show less
Hard Rules
- No planning — Never generate PLAN.md, task lists, or implementation steps
- No code — Never write or suggest code
- No git — No commits, branches, or any git operations
- Max 3 rounds — If not confirmed after 3 mirror attempts, say: "We're going in circles. Can you write out exactly what you want in 2-3 sentences?"
- Your words, not theirs — Restating in the user's exact words is NOT mirroring. Rephrase to prove understanding.
- One question max in PARSE — Don't interrogate. Mirror with what you have, let corrections fill the gaps.
- Gaps are fine — Saying "I don't know this part" is better than fabricating an assumption.
Round Counting
A "round" = one MIRROR presentation + one user response. The counter resets on "Yes, correct" (confirmed).
| Round | State |
|---|---|
| 1 | First mirror attempt |
| 2 | After first correction |
| 3 | Final attempt — if rejected, trigger circuit breaker |
Usage Examples
# Basic
/mirror Build a skill that mirrors back the user's request for confirmation
# With context
/mirror API error handling is inconsistent — I want to unify it with a middleware
# English
/mirror I want to refactor the auth module to use JWT instead of sessions
# Vague (triggers one clarifying question)
/mirror Fix this thingExample Flow
User: "/mirror Login error messages are too generic — users can't tell what went wrong"
[PARSE]
- What: Make login error messages specific
- Why: Users can't identify failure cause
- Scope: Login errors only
- Constraints: not stated
[MIRROR]
## Mirror Back
### What (deliverable)
Replace the generic "login failed" message with specific feedback like
"email not found" or "wrong password" so users know exactly what to fix.
### Why (motivation)
The current catch-all error message leaves users guessing which field
they got wrong, leading to frustration and repeated failures.
### Scope
- **In**: Login flow error messages
- **Out**: Signup, password reset, and other auth flows (not mentioned)
### Constraints
- None stated
### Gaps & Assumptions
- Security tradeoff: Specific errors can reveal whether an account exists.
Unclear how to balance this against UX. Needs a decision.
[CONFIRM]
→ User: "Close, but needs tweaks" — "I know about the security issue,
I want to prioritize UX over enumeration protection"
→ Round 2 MIRROR (reflects UX > security decision)
→ User: "Yes, correct"
→ CONFIRMED → Handoff optionsChecklist Before Stopping
- At least 1 MIRROR presented with all 4 sections (What/Why/Scope/Constraints)
- User explicitly confirmed ("Yes, correct")
- No plans generated
- No code written
- No git commands executed
- Handoff command provided (if user chose next step)
- Round limit respected (max 3)
© team-attention, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skills/mirror of team-attention/hoyeon.
Open the folder on GitHubat commit 7cff032
Compare with similar skills
Mirror next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Mirror this skillteam-attention/hoyeon | 173 | — | ~1.8k | Automated safety check: Pass | MIT | |
| Repo Mirror Sourcesnetdata/netdata | 81k | — | ~1.2k | Automated safety check: Notes | GPL-3.0 | |
| Identity Mirrorsickn33/agentic-awesome-skills | 47k | 2 repos | ~1.3k | Automated safety check: Pass | MIT | |
| Book Mirrorgarrytan/gbrain | 31k | — | ~6.6k | Automated safety check: Pass | MIT | |
| Back Forward Cachethedaviddias/Front-End-Checklist | 74k | — | ~541 | Automated safety check: Pass | MIT | |
| Ask Echohuangruiteng/CS-Notes | 4k | — | ~231 | Automated safety check: Pass | MIT |
Similar skills
Identity Mirror
sickn33/agentic-awesome-skills
One sentence - what this skill does and when to invoke it. An agent skill from sickn33/agentic-awesome-skills.
Book Mirror
garrytan/gbrain
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis.
Back Forward Cache
thedaviddias/Front-End-Checklist
A skill your agent uses when reviewing navigation performance, browser lifecycle events, or resume-from-memory behavior.
Ask Echo
huangruiteng/CS-Notes
使用火山引擎 Ask-Echo 融合信息搜索 API 进行 web 搜索、web 搜索总结版和图片搜索. An agent skill from huangruiteng/CS-Notes.
Consult Echo
marin-community/marin
Search or cite Echo at the start of a fresh Marin investigation when prior-work policy applies, another selected workflow requires it, or the user explicitly asks; reuse relevant results during the…
More from team-attention/hoyeon
All 36 skills in this repoSkill Session Analyzer
team-attention/hoyeon
This skill should be used when the user asks to "analyze session", "evaluate skill execution", "check session logs", provides a session ID with a skill path, or wants to verify that a skill executed…
Browser Work
team-attention/hoyeon
Recon-first browser automation. An agent skill from team-attention/hoyeon.
Check
team-attention/hoyeon
This skill should be used when the user wants to verify their changes before pushing, or update the project's rule checklists.
Compound
team-attention/hoyeon
This skill should be used when the user says "/compound", "compound this", "document learnings", "save what we learned", or after completing a PR.
QA
team-attention/hoyeon
Systematically QA test any application — web apps, native macOS apps, Electron apps, CLI tools, interactive REPLs, or anything on screen.
Tech Decision
team-attention/hoyeon
This skill should be used when the user asks about "technical decision", "what to use", "A vs B", "comparison analysis", "library selection", "architecture decision", "which one to use"…
Questions about Mirror
What does Mirror do?
"/mirror", "mirror back", "echo back", "다시 설명해줘", "이해한 거 맞아?", "내가 뭘 원하는지 말해봐", "확인해줘", "paraphrase this", "너가 이해한 거 설명해봘", "what did I ask?". Mirror is an agent skill from team-attention/hoyeon.
How do I install Mirror in Claude Code?
Run `npx skills add team-attention/hoyeon --skill mirror -a claude-code`. Or copy the skill folder (skills/mirror in team-attention/hoyeon) into .claude/skills/mirror in your project. Claude Code loads it when a task matches its description.
How do I install Mirror in Codex?
Run `npx skills add team-attention/hoyeon --skill mirror -a codex`. Or copy the skill folder (skills/mirror in team-attention/hoyeon) into .agents/skills/mirror in your project. Codex loads it when a task matches its description.
Can I use Mirror in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add team-attention/hoyeon --skill mirror -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/mirror, .gemini/skills/mirror, .github/skills/mirror and .opencode/skills/mirror in your project.
What does Mirror need to run?
SKILL.md names no scripts, command-line tools or credentials: Mirror is instructions for the agent only. Its frontmatter pre-approves these tools: AskUserQuestion, Read, Grep, Glob.
Does Mirror access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Mirror safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Mirror use?
Mirror is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Mirror use?
About 1.8k tokens (SKILL.md is roughly 7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Mirror?
Skills that share tags, products or a category with Mirror: Repo Mirror Sources (netdata/netdata, 81k stars), Identity Mirror (sickn33/agentic-awesome-skills, 47k stars), Book Mirror (garrytan/gbrain, 31k stars) and Back Forward Cache (thedaviddias/Front-End-Checklist, 74k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Mirror?
team-attention (a GitHub organization) maintains it in team-attention/hoyeon, which has 173 GitHub stars. The repository holds 36 skills in this directory. The repository was last updated on May 21, 2026.
Source: team-attention/hoyeon on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.