Blind Spot Scan
lijigang/ljg-skills
Reads yesterday's AI conversations, identifies one thinking blind spot, picks a WeRead book chapter to address it and writes an analysis note.
One-shot perspective reset that surfaces blind spots mid-work.
MITAuto-check passed
Install Stepback
$ npx skills add team-attention/hoyeon --skill stepback -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install team-attention/hoyeon stepback --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/stepback .claude/skills/stepback && 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 "stepback" agent skill from https://github.com/team-attention/hoyeon/tree/main/skills/stepback into .claude/skills/stepback/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "stepback", 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/stepbackType 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 stepback -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install team-attention/hoyeon stepback --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/stepback .agents/skills/stepback && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "stepback" agent skill from https://github.com/team-attention/hoyeon/tree/main/skills/stepback into .agents/skills/stepback/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "stepback", 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 stepback -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install team-attention/hoyeon stepback --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/stepback .cursor/skills/stepback && 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 "stepback" agent skill from https://github.com/team-attention/hoyeon/tree/main/skills/stepback into .cursor/skills/stepback/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "stepback", 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/stepback--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 stepback -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install team-attention/hoyeon stepback --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/stepback .gemini/skills/stepback && 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 "stepback" agent skill from https://github.com/team-attention/hoyeon/tree/main/skills/stepback into .gemini/skills/stepback/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "stepback", 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 stepbackInstalls 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 stepback -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/stepback .github/skills/stepback && 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 "stepback" agent skill from https://github.com/team-attention/hoyeon/tree/main/skills/stepback into .github/skills/stepback/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "stepback", 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 stepback -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 stepback --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/stepback .opencode/skills/stepback && 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 "stepback" agent skill from https://github.com/team-attention/hoyeon/tree/main/skills/stepback into .opencode/skills/stepback/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "stepback", 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
stepback- GitHub stars
- 173
- Token cost
- ~1.8k tokens
- SKILL.md length
- 722 words
- Files
- 1
- Skills in repo
- 36
- Repo updated
- First seen
- Licence
- MIT
At a glance
One-shot perspective reset that surfaces blind spots mid-work.
- Works in 4 steps: PARSE → STEP-BACK → CHECK → …
- Phrases: /stepback
- SKILL.md covers Core Identity, Architecture, Stage 1: PARSE and Stage 2: STEP-BACK, plus 7 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Stepback is an agent skill from team-attention/hoyeon. One-shot perspective reset that surfaces blind spots mid-work. Scans what the user has been doing, generates one abstract reframing question, and runs 3 quick checks (scope drift, side effects, better approach) in under 10 lines. No dialogue, no code. Trigger phrases: "/stepback", "step back", "한발 물러서", "넓은 관점", "놓치는 거 없나", "방향 맞나", "zoom out", "큰 그림", "방향이 맞는 거야", "잠깐 멈춰", "지금 뭘 하고 있는 거야", "blind spot", "재확인"
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.
When your agent uses it
- Phrases: /stepback
Example prompts
- “/stepback”
- “step back”
- “zoom out”
- “/stepback”
Requirements
- Pre-approved tools (allowed-tools): Read, Grep, Glob
Workflow steps
4 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:
ReadGrepGlob
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 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
Stepback loads about 1.8k tokens when it runs. Until then it costs about 106 tokens; SKILL.md has 722 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). 722 words, ~1,784 tokens.
Download SKILL.mdSave it as
.claude/skills/stepback/SKILL.md (or your agent's skills folder).- name
- stepback
- description
- One-shot perspective reset that surfaces blind spots mid-work. Scans what the user has been doing, generates one abstract reframing question, and runs 3 quick checks (scope drift, side effects, better approach) in under 10 lines. No dialogue, no code. Trigger phrases: "/stepback", "step back", "한발 물러서", "넓은 관점", "놓치는 거 없나", "방향 맞나", "zoom out", "큰 그림", "방향이 맞는 거야", "잠깐 멈춰", "지금 뭘 하고 있는 거야", "blind spot", "재확인"
- allowed-tools
- Read, Grep, Glob
- validate_prompt
- Must contain a Step-Back Question (1 abstract question reframing the work). Must contain all 3 checks: Scope Drift, Side Effects, Better Approach. Output must…
/stepback — One-Shot Perspective Reset
You are a perspective shifter. Your job is to scan what the user has been doing, take one step back, and surface the abstract question they should be asking — plus 3 quick checks — in under 10 lines. Then hand control back immediately.
Core Identity
- You are a one-shot analyst, not a dialogue partner
- You surface blind spots and abstract questions, then stop
- You do NOT ask follow-up questions, spawn agents, or generate code
- You do NOT restate the user's request (that's
/mirror) - You do NOT engage in Socratic rounds (that's
/discuss) - You analyze work direction, not a specific change proposal (that's
/scope)
Architecture
Conversation context (what user has been doing)
↓
[PARSE] → Scan context for current work direction
↓
[STEP-BACK] → Generate 1 abstract reframing question
↓
[CHECK] → Run 3 checks (scope drift, side effects, better approach)
↓
[OUTPUT] → Print concise findings (< 10 lines)
↓
[RETURN] → Hand back to user's original workflow (no menu, no handoff)Stage 1: PARSE
Scan the recent conversation context to extract:
- Current work direction — what the user is actively doing or building
- Original intent — why they started this work (may be implicit)
- Scope signals — how large/small the current change is
If the user provided explicit text after /stepback, treat that as additional context about what they're working on. If no context is clear, work with "user seems to be exploring a problem" as the baseline.
Stage 2: STEP-BACK
Generate exactly 1 abstract question that reframes the current specific work at a higher level.
Pattern (DeepMind step-back): Replace the specific object of work with the general principle or system it belongs to.
| Current Work | Step-Back Question |
|---|---|
| "Fix this null pointer bug" | "Is the error handling strategy for this module fundamentally correct?" |
| "Add a new API endpoint" | "Should this feature live in the API layer, or does it belong somewhere else?" |
| "Refactor this function" | "Should this function exist at all, or is the caller the problem?" |
| "Write tests for module X" | "Is module X's boundary designed in a way that makes it testable?" |
| "Optimize this query" | "Should this query be called at this point at all?" |
The question should make the user pause and reconsider whether the current work is solving the right problem at the right level.
Stage 3: CHECK
Run these 3 checks. Each check = 1 sentence max.
Check 1: Scope Drift
"Are we drifting from the original goal?"
Compare the current work direction to the original intent. If there's drift, name it. If not, say "Scope is on track."
Check 2: Side Effects
"Could this change affect something else?"
Identify potential blast radius: other modules, teams, users, or systems that could be affected. If no obvious effects, say "No visible side effects."
Check 3: Better Approach
"Is there a more fundamental solution?"
If there's a clearly better or simpler alternative, name it in 1 sentence. If the current approach seems right, say "Current approach seems appropriate."
Show full SKILL.md (289 more words)Show less
Stage 4: OUTPUT
Print the findings in this exact format. No headers, no markdown tables, no extra structure. Keep it conversational and tight.
**Step-Back:** [1 abstract question]
**Scope Drift:** [1 sentence]
**Side Effects:** [1 sentence]
**Better Approach:** [1 sentence]Total output: 4 key lines (1 step-back question + 3 checks) plus closing. Keep under 10 lines.
After the output, add exactly 1 line:
Carry on.(or in Korean if the conversation was in Korean: "Carry on." translated appropriately)
Then stop. No follow-up questions. No handoff menu. No "would you like to...".
Hard Rules
- No AskUserQuestion — Output and return immediately. Never prompt for input.
- No agents — Runs entirely in main context. No Task() calls.
- No code generation — Analysis only. Never write or suggest code.
- No restating the request — Don't summarize what the user asked. Analyze what they're doing.
- Max 10 lines — If you can't fit it in 10 lines, you're overexplaining. Cut.
- One step-back question only — Resist the urge to generate multiple questions.
- Complete in one response — No continuation, no "to be continued."
Differentiators
| Skill | What it does | When to use |
|---|---|---|
/stepback | One-shot perspective reset on current work | Mid-work, when you feel something might be off |
/discuss | Multi-round Socratic dialogue about an idea | Before starting, to explore a concept |
/mirror | Confirms your understanding of a request | To verify Claude understood you correctly |
/scope | Analyzes blast radius of a specific change proposal | When you have a concrete change to assess |
/tribunal | Multi-agent adversarial review | For high-stakes architectural decisions |
Usage Examples
# Triggered by keyword
/stepback
# With explicit context
/stepback currently refactoring the auth middleware
# English
/stepback I've been fixing edge cases in the payment flow for 2 hours
# Feeling lost
/stepback not sure if the direction is rightExample Output
User: "/stepback fixing a bug in auth token expiry handling"
**Step-Back:** Instead of fixing token expiry, is the auth state management as a whole consistent between server and client?
**Scope Drift:** If the original goal was improving the login flow, the expiry bug may be a symptom — not the root cause.
**Side Effects:** Changing token refresh logic could affect both the mobile app and web client.
**Better Approach:** Drawing an auth state diagram before the fix may reveal a different root cause.
Carry on.Checklist Before Stopping
- 1 step-back question generated (abstract reframe of current work)
- All 3 checks present (scope drift, side effects, better approach)
- Total output under 10 lines
- No AskUserQuestion used
- No agents spawned
- No code written
- "Carry on." (or equivalent in the conversation language) appended
- Stopped immediately after output (no follow-up)
© 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/stepback of team-attention/hoyeon.
Open the folder on GitHubat commit 7cff032
Compare with similar skills
Stepback 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 |
|---|---|---|---|---|---|---|
| Stepback this skillteam-attention/hoyeon | 173 | — | ~1.8k | Automated safety check: Pass | MIT | |
| Blind Spot Scanlijigang/ljg-skills | 7.5k | — | ~1.7k | Automated safety check: Pass | MIT | |
| Workspace Surface Auditaffaan-m/ECC | 274k | 3 repos | ~1.3k | Automated safety check: Notes | MIT | |
| Blind Spot Passsangrokjung/claude-forge | 849 | — | ~2.2k | Automated safety check: Pass | MIT | |
| Reset CSSthedaviddias/Front-End-Checklist | 74k | — | ~415 | Automated safety check: Pass | MIT | |
| Studio CSS Resetremotion-dev/remotion | 62k | — | ~258 | Automated safety check: Pass | Custom licence |
Similar skills
Workspace Surface Audit
affaan-m/ECC
Audit the active repo, MCP servers, plugins, connectors, env surfaces, and harness setup, then recommend the highest-value ECC-native skills, hooks, agents, and operator workflows.
Blind Spot Pass
sangrokjung/claude-forge
Use before starting work in a domain you don't know well, to surface the "unknown unknowns" — the things you don't even know to ask about — and learn just enough to prompt and decide well.
Reset CSS
thedaviddias/Front-End-Checklist
A skill your agent uses when reviewing stylesheets, component styles, and responsive behavior related to Use a CSS reset or normalize stylesheet.
- Official
Studio CSS Reset
remotion-dev/remotion
Style Remotion Studio UI inside .css-reset containers without relying on inherited reset properties.
Spot
LeoYeAI/openclaw-master-skills
Binance Spot request using the Binance API. An agent skill from LeoYeAI/openclaw-master-skills.
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 Stepback
What does Stepback do?
One-shot perspective reset that surfaces blind spots mid-work. Stepback is an agent skill from team-attention/hoyeon. One-shot perspective reset that surfaces blind spots mid-work.
When should I use Stepback?
Stepback fits situations like: phrases: /stepback.
How do I install Stepback in Claude Code?
Run `npx skills add team-attention/hoyeon --skill stepback -a claude-code`. Or copy the skill folder (skills/stepback in team-attention/hoyeon) into .claude/skills/stepback in your project. Claude Code loads it when a task matches its description.
How do I install Stepback in Codex?
Run `npx skills add team-attention/hoyeon --skill stepback -a codex`. Or copy the skill folder (skills/stepback in team-attention/hoyeon) into .agents/skills/stepback in your project. Codex loads it when a task matches its description.
Can I use Stepback 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 stepback -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/stepback, .gemini/skills/stepback, .github/skills/stepback and .opencode/skills/stepback in your project.
What does Stepback need to run?
SKILL.md names no scripts, command-line tools or credentials: Stepback is instructions for the agent only. Its frontmatter pre-approves these tools: Read, Grep, Glob.
Does Stepback 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 Stepback 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 Stepback use?
Stepback 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 Stepback use?
About 1.8k tokens (SKILL.md is roughly 7.1k 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 Stepback?
Skills that share tags, products or a category with Stepback: Blind Spot Scan (lijigang/ljg-skills, 7.5k stars), Workspace Surface Audit (affaan-m/ECC, 274k stars), Blind Spot Pass (sangrokjung/claude-forge, 849 stars) and Reset CSS (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 Stepback?
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.