Vercel Composition Patterns
supabase/supabase
React composition patterns that scale. An agent skill from supabase/supabase.
One-shot perspective reset. An agent skill from AlexZio00/sovereign-skills.
Install Stepback
$ npx skills add AlexZio00/sovereign-skills --skill stepback -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install AlexZio00/sovereign-skills 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/AlexZio00/sovereign-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/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/AlexZio00/sovereign-skills/tree/master/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/AlexZio00/sovereign-skills/tree/master/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 AlexZio00/sovereign-skills --skill stepback -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install AlexZio00/sovereign-skills stepback --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/AlexZio00/sovereign-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/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/AlexZio00/sovereign-skills/tree/master/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 AlexZio00/sovereign-skills --skill stepback -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install AlexZio00/sovereign-skills stepback --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/AlexZio00/sovereign-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/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/AlexZio00/sovereign-skills/tree/master/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/AlexZio00/sovereign-skills.git --path 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 AlexZio00/sovereign-skills --skill stepback -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install AlexZio00/sovereign-skills stepback --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/AlexZio00/sovereign-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/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/AlexZio00/sovereign-skills/tree/master/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 AlexZio00/sovereign-skills 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 AlexZio00/sovereign-skills --skill stepback -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/AlexZio00/sovereign-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/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/AlexZio00/sovereign-skills/tree/master/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 AlexZio00/sovereign-skills --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 AlexZio00/sovereign-skills stepback --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/AlexZio00/sovereign-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/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/AlexZio00/sovereign-skills/tree/master/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
- 139
- Token cost
- ~1.9k tokens
- SKILL.md length
- 778 words
- Files
- 3
- Skills in repo
- 17
- Repo updated
- First seen
- Licence
- MIT
At a glance
One-shot perspective reset. An agent skill from AlexZio00/sovereign-skills.
- Works in 4 steps: PARSE → STEP-BACK → CHECK → …
- Development work in your project
- SKILL.md covers Purpose, Dominant Variable, Key Assumptions and Trigger, plus 13 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Stepback is an agent skill from AlexZio00/sovereign-skills. One-shot perspective reset. Scans current work context, generates 1 abstract reframing question + 3 quick checks (scope drift, side effects, better approach) in under 10 lines. No dialogue, no code, no agents.
Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files (for example `.claude-plugin/plugin.json` and `agents/openai.yaml`).
It sits in Development. The repository describes itself as: 20 production-grade skills for AI coding agents — setup, scope, discipline, code review, security, session management, governance, ops, and quality audits (eval-leakage… The licence is MIT.
When your agent uses it
- Development work in your project
Example prompts
- “/stepback”
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 d814a3a. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
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 1.9k tokens when it runs. Until then it costs about 55 tokens; SKILL.md has 778 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 AlexZio00/sovereign-skills at commit d814a3a, republished under its MIT licence (© AlexZio00). 778 words, ~1,874 tokens.
Download SKILL.mdSave it as
.claude/skills/stepback/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.- name
- stepback
- description
- One-shot perspective reset. Scans current work context, generates 1 abstract reframing question + 3 quick checks (scope drift, side effects, better approach) in under 10 lines. No dialogue, no code, no agents.
- skill_type
- utility
- tools
- Read
- concurrency_profile.read_only
- true
- concurrency_profile.parallel_safe
- true
- tags
- meta, analysis
- version
- 1.0.0
- source
- team-attention/hoyeon pattern
- triggers
- /stepback, step back, zoom out, blind spot, am I on track, big picture, what am I even doing
- user-invocable
- true
- not_for
- Next action recommendation -> next-action skill, Session start -> session-start
/stepback — One-Shot Perspective Reset
Source: team-attention/hoyeon pattern. Read-only, zero side effects.
Purpose
Scan the current work context, generate 1 abstract reframing question + 3 quick checks (scope drift, side effects, better approach) in under 10 lines. No dialogue, no code, no agents.
Use when you're deep in implementation and need to check if you're solving the right problem at the right level.
Dominant Variable
Whether the work direction is solving the right problem at the right level — if this is off, even flawless implementation produces the wrong outcome.
Key Assumptions
- Current work context exists in the conversation — if broken: ask once, "tell me in one line what you're doing."
- Output fits an abstraction level expressible in ≤10 lines — if broken: the question is too concrete → self-check "go more abstract."
Trigger
/stepback- "step back"
- "zoom out"
- "blind spot"
- "am I on track"
- "big picture"
- "what am I even doing"
Discard If
- Work is already completed (use retrospective tools instead)
- Code review requested (use code review tools instead)
- Specific change impact analysis needed (use scope definition tools instead)
Architecture
Recent conversation context (current work direction)
↓
[PARSE] → Extract current direction + original intent + scope signals
↓
[STEP-BACK] → Generate 1 abstract reframing question
↓
[CHECK] → Run 3 checks
↓
[OUTPUT] → Under 10 lines, return immediatelyStage 1: PARSE
Extract from recent conversation:
- Current direction — what the user is actively working on
- Original intent — why this work was started (implicit is OK)
- Scope signals — size/complexity of the change
Stage 2: STEP-BACK
DeepMind step-back pattern: abstract from the specific subject of current work → the general principle/system it belongs to.
| Current Work | Step-Back Question |
|---|---|
| "Fixing this null pointer bug" | "Is the error handling strategy of this module correct in the first place?" |
| "Adding a new API endpoint" | "Should this feature live in the API layer, or somewhere else?" |
| "Refactoring this function" | "Should this function exist at all, or is the caller the real problem?" |
| "Writing tests for module X" | "Is X's boundary designed in a testable way?" |
| "Optimizing this query" | "Should this query be called at this point at all?" |
The question must make the user reconsider whether they're solving the right problem at the right level.
Stage 3: CHECK
Each check = 1 sentence max.
Scope Drift: Has the current work drifted from the original goal?
- If drifted → state how
- If on track → "Scope on track."
Side Effects: Could this change affect something else?
- State potential blast radius (modules, schemas, tests, integrations)
- If none → "No visible side effects."
Better Approach: Is there a more fundamental/simpler solution?
- If yes → 1 sentence
- If current approach is right → "Current approach seems appropriate."
Stage 4: OUTPUT
**Step-Back:** [1 abstract reframing question]
**Scope Drift:** [1 sentence]
**Side Effects:** [1 sentence]
**Better Approach:** [1 sentence]
Continue.4 core lines + closing. Under 10 lines total.
Output and stop immediately. No follow-up questions, no menus, no "would you like to...".
Show full SKILL.md (354 more words)Show less
Hard Rules
- No user questions if context is clear; ask exactly once if unclear — output and return immediately when the work context is clear; only if it is genuinely unclear, ask one clarifying question (see Key Assumptions / Error Recovery), then stop.
- No agent spawning — runs in main context only.
- No code generation — analysis only. No code writing or suggestions.
- No request restatement — don't summarize what the user asked. Analyze what's happening now.
- 10-line cap — more than 10 lines means over-explaining. Cut.
- 1 question only — suppress the urge to generate multiple step-back questions.
Scope Boundary
| Does | Does NOT |
|---|---|
| Read recent conversation context for work direction | Write code or modify files |
| Generate 1 abstract reframing question | Spawn agents or ask user questions |
| Run 3 checks (scope/side effects/better approach) | Suggest next actions or generate menus |
| Output under 10 lines and return immediately | Continue working on the task |
Safety Layers
| Risky Action | Reversibility | Applied Layers |
|---|---|---|
| (none — read-only one-shot) | — | L1 (Invariant 3: immediate return, no further action) |
Invariants (never violate)
- 10-line cap: Output exceeding 10 lines has already failed. Cut it down. Violation → over-explanation dilutes the perspective reset.
- 1 question limit: Multiple questions split focus. Pick the most important one. Violation → user gets a list instead of a lens.
- Immediate return: No follow-up after output. User decides what to do next. Violation → stepback becomes a dialogue instead of a reset.
Error Recovery
| Failure Type | Detection | Recovery |
|---|---|---|
input_error | Current work context unclear | Ask once: "tell me in one line what you're doing now" |
missing_data | No git diff/status context | Infer from user's last message. If inference impossible, use generic reframing |
Example
User: "/stepback"
(Context: debugging a flaky integration test that intermittently times out)
**Step-Back:** Is the test flaky because of a timing issue, or because the component under test has a non-deterministic dependency that shouldn't be there?
**Scope Drift:** Started with fixing one test, now touching retry logic in three modules.
**Side Effects:** Changing the retry config could mask real failures in CI.
**Better Approach:** Check if the test is testing the right thing — a unit test might eliminate the flakiness entirely.
Continue.Rationalization Table
| Rationalization | Counter |
|---|---|
| "10 lines isn't enough, I need to explain more" | If 10 lines isn't enough, the question isn't abstract enough. Go higher. |
| "I should ask the user to confirm before continuing" | Stepback is one-shot. If confirmation is needed, the user will follow up. |
| "Two questions would be more useful" | Two questions halve the focus. Picking one better question is the answer. |
| "Showing code would make it more concrete" | Stepback is direction check, not code review. No code generation. |
© AlexZio00, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 2 other files in stepback of AlexZio00/sovereign-skills.
- SKILL.md
- .claude-plugin/plugin.json
- agents/openai.yaml
Open the folder on GitHubat commit d814a3a
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 skillAlexZio00/sovereign-skills | 139 | — | ~1.9k | Automated safety check: Pass | MIT | |
| Vercel Composition Patternssupabase/supabase | 111k | 59 repos | ~726 | Automated safety check: Pass | MIT | |
| Finishing a Development Branchobra/superpowers | 296k | 5 repos | ~1.9k | Automated safety check: Pass | MIT | |
| Typescript Advanced Typesrolling-scopes/rsschool-app | 10k | 25 repos | ~4.2k | Automated safety check: Pass | MPL-2.0 | |
| PR Babysitteropeninterpreter/openinterpreter | 69k | 3 repos | ~4.2k | Automated safety check: Pass | Apache-2.0 | |
| Code Review ChecklistshareAI-lab/learn-claude-code | 78k | 5 repos | ~1.1k | Automated safety check: Pass | MIT |
Similar skills
- Official
Finishing a Development Branch
obra/superpowers
Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree.
Typescript Advanced Types
rolling-scopes/rsschool-app
Master TypeScript's advanced type system including generics, conditional types, mapped types, template literals, and utility types for building type-safe applications.
PR Babysitter
openinterpreter/openinterpreter
Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.
Code Review Checklist
shareAI-lab/learn-claude-code
Reviews code against a five-part checklist covering security, correctness, performance, maintainability and testing, and reports findings in a fixed format.
Greploop
onyx-dot-app/onyx
Iteratively improves a PR (GitHub), MR (GitLab), or shelved changelist (Perforce) until Greptile gives it a 5/5 confidence score with zero unresolved comments.
More from AlexZio00/sovereign-skills
All 17 skills in this repoProject Overview
AlexZio00/sovereign-skills
A skill your agent uses when the user wants a deterministic cross-project status map generated from registered projects' session handoffs.
Scope
AlexZio00/sovereign-skills
Scope definition before implementation — two modes. An agent skill from AlexZio00/sovereign-skills.
Project Init
AlexZio00/sovereign-skills
Interview-based project setup — generates CLAUDE.md, ROADMAP, .gitignore, .env.example from scratch.
Collab Audit
AlexZio00/sovereign-skills
This skill should be used when the user types /collab-audit or requests AI collaboration diagnosis.
Doc Drift
AlexZio00/sovereign-skills
A skill your agent uses when the user wants to audit the memory and documents Claude Code loads into context — CLAUDE.md (user global + project + nested), MEMORY.md, @imports, .claude/skills…
Session Checkpoint
AlexZio00/sovereign-skills
A skill your agent uses when saving session state before context compaction, switching tasks, or ending a session.
Related
Categories
Questions about Stepback
What does Stepback do?
One-shot perspective reset. An agent skill from AlexZio00/sovereign-skills. Stepback is an agent skill from AlexZio00/sovereign-skills. One-shot perspective reset.
When should I use Stepback?
Stepback fits situations like: development work in your project.
How do I install Stepback in Claude Code?
Run `npx skills add AlexZio00/sovereign-skills --skill stepback -a claude-code`. Or copy the skill folder (stepback in AlexZio00/sovereign-skills) 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 AlexZio00/sovereign-skills --skill stepback -a codex`. Or copy the skill folder (stepback in AlexZio00/sovereign-skills) 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 AlexZio00/sovereign-skills --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.
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 1.9k tokens (SKILL.md is roughly 7.5k 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: Vercel Composition Patterns (supabase/supabase, 111k stars), Finishing a Development Branch (obra/superpowers, 296k stars), Typescript Advanced Types (rolling-scopes/rsschool-app, 10k stars) and PR Babysitter (openinterpreter/openinterpreter, 69k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Stepback?
AlexZio00 (a GitHub user) maintains it in AlexZio00/sovereign-skills, which has 139 GitHub stars. The repository holds 17 skills in this directory. The repository was last updated on September 25, 2026.
Source: AlexZio00/sovereign-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.