Agent skill

Backstage

by LeoYeAI in LeoYeAI/openclaw-master-skills

Anti-drift protocol script. An agent skill from LeoYeAI/openclaw-master-skills.

MITAuto-check passedDevOps & Cloud

Install Backstage

skills CLI
$ npx skills add LeoYeAI/openclaw-master-skills --skill backstage -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install LeoYeAI/openclaw-master-skills backstage --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/backstage .claude/skills/backstage && rm -rf skills-src

Use ~/.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/

Facts

Skill name
backstage
GitHub stars
2.2k
Token cost
~5.5k tokens
SKILL.md length
1,608 words
Files
7
Skills in repo
972
Repo updated
First seen
Licence
MIT

At a glance

Anti-drift protocol script. An agent skill from LeoYeAI/openclaw-master-skills.

  • Works in 3 steps: The work itself → Explicating methodology (ethics,… → Defining WHERE that learning gets stored…
  • Tasks that involve Platform engineering
  • SKILL.md covers ⚠️ Security Notice, 🔴 Why This Skill Exists…, Policies & Checks Enforcement and Mermaid Diagram Generation…, plus 10 more sections
  • Runs Shell scripts from its folder; calls git, rsync and osascript; reaches github.com

What it does

Backstage is an agent skill from LeoYeAI/openclaw-master-skills. Anti-drift protocol script. Ensures parity between docs and system. Triggers: 'bom dia PROJECT' / 'good morning PROJECT' (load project context with health checks)

Its SKILL.md is about 5.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files (for example `_meta.json`, `backstage.sh` and `checks.sh`).

It sits in DevOps & Cloud, covering Platform engineering. The repository describes itself as: 🧠 Curated collection of 1209+ best OpenClaw skills — weekly updated by MyClaw.ai. The licence is MIT.

When your agent uses it

  • Tasks that involve Platform engineering

Example prompts

  • “bom dia PROJECT”
  • “good morning PROJECT”
  • “/backstage”

Requirements

  • A Bash shell

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. The work itself
  2. Explicating methodology (ethics, preferences, protocols)
  3. Defining WHERE that learning gets stored (VISION? SOUL? SKILL? memory?)

What it can do on your machine

Read from SKILL.md and the folder at commit e5199b5. 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

    Ships script files (Shell), which the agent can run.

    Shell commands in SKILL.md call:

    • git
    • rsync
    • osascript

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • github.com

    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

Backstage loads about 5.5k tokens when it runs. Until then it costs about 43 tokens; SKILL.md has 1,608 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~43
When it runs · the whole SKILL.md, loaded when a task matches
~5.5k

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 LeoYeAI/openclaw-master-skills at commit e5199b5, republished under its MIT licence (© LeoYeAI). 1,608 words, ~5,469 tokens.

Download SKILL.mdSave it as .claude/skills/backstage/SKILL.md (or your agent's skills folder). This skill also uses 6 other files; get the full folder from GitHub.
name
backstage
description
Anti-drift protocol script. Ensures parity between docs and system. Triggers: 'bom dia PROJECT' / 'good morning PROJECT' (load project context with health checks)
type
public
version
1.0.2
status
production
author
nonlinear
license
MIT
requires
https://github.com/nonlinear/backstage
dependencies
bash, awk, sed, git

Backstage Skill

Nickname: backstage:

Objective: Universal project status management for AI-assisted development. Ensures documentation matches reality before every commit.


⚠️ Security Notice

This is an admin tool with elevated privileges:

  • Executes checks from global path ($HOME/Documents/backstage/backstage/checks/global/)
  • Pulls remote code from GitHub (https://github.com/nonlinear/backstage)
  • Modifies project files (README, ROADMAP, CHANGELOG with mermaid diagrams)
  • Rsyncs updates when using update backstage trigger

Intended for:

  • Personal use (you control the upstream repo)
  • Trusted teams (shared backstage protocol repo)

Not recommended for:

  • Untrusted third-party projects
  • Public/open-source projects with unknown contributors

Mitigations in place:

  • User confirmation before applying updates
  • Git history (all changes committed, revertable)
  • Symlink detection (admin mode auto-updates)

Use at your own risk. Review update-backstage.sh and checks.sh before running.


🔴 Why This Skill Exists (Anti-Drift)

Backstage-skill = ANTI-DRIFT:

  • ✅ Force context awareness (project/epic)
  • ✅ Health checks prevent chaos
  • ✅ Architecture-first workflow
  • ✅ Roadmap visibility = no surprises

WITHOUT IT:
Work happens outside backstage → drift → broken trust → triple metabolic cost

WITH IT:
"good morning X" → automatic context load → work inside boundaries → paridade maintained


The Metabolic Cost Problem:

Without backstage, delegation costs triple:

  1. The work itself
  2. Explicating methodology (ethics, preferences, protocols)
  3. Defining WHERE that learning gets stored (VISION? SOUL? SKILL? memory?)

This is exhausting for the human.

Investment is worth it ONLY IF plateau is reached:

  • Human teaches ONCE → AI internalizes
  • Each session: READ context files → act according to ethics
  • Each session: LESS explanation needed
  • Plateau = Human delegates, AI executes without supervision

This skill enforces stabilization.
Force context awareness (project/epic/design architecture) to prevent drift.
3x work becomes 1x work.


Policies & Checks Enforcement

Backstage-skill enforces ALL rules in checks/ (deterministic + interpretive, global + local).

Enforcement Model
mermaid
flowchart TD
    READ_CHK["Read checks/<br/>global + local<br/>[Deterministic .sh + Interpretive .md]"]
    
    CONFLICT{Conflict?}
    MERGE[Merge compatible rules]
    LOCAL[Local wins]
    
    AI["AI interprets .md checks<br/>[Contextual enforcement]"]
    SH["Bash executes .sh checks<br/>[Deterministic validation]"]
    
    AI_ACT[✅ Enforce or discuss]
    AI_AMBIG[⚠️ Ask user]
    
    SH_OK[✅ All checks pass]
    SH_FAIL[❌ Checks failed]
    
    REPORT["Report:<br/>📋 Interpretive (always ✅)<br/>🔍 Deterministic (✅/❌)"]
    
    READ_CHK --> CONFLICT
    CONFLICT -->|No| MERGE
    CONFLICT -->|Yes| LOCAL
    MERGE --> AI
    MERGE --> SH
    LOCAL --> AI
    LOCAL --> SH
    
    AI -->|Clear| AI_ACT
    AI -->|Ambiguous| AI_AMBIG
    
    SH -->|Pass| SH_OK
    SH -->|Fail| SH_FAIL
    
    AI_ACT --> REPORT
    AI_AMBIG --> REPORT
    SH_OK --> REPORT
    SH_FAIL --> REPORT

Two enforcement domains:

  1. Checks (Interpretive)

    • checks/global/*.md = Universal workflow rules
    • checks/local/*.md = Project-specific overrides
    • Enforced by: AI (reads markdown, interprets context, acts)
    • Always pass: AI reads, understands, will act accordingly
  2. Checks (Deterministic)

    • checks/global/*.sh = Universal validation tests
    • checks/local/*.sh = Project-specific tests
    • Enforced by: Bash (executes shell scripts, exit codes)
    • Pass or fail: ✅ (exit 0) or ❌ (exit non-zero)

Polycentric governance:

  • Global + local rules coexist
  • Local wins on conflict
  • AI merges when compatible

Report format:

📋 Interpretive checks:
  ✅ checks/global/branch-workflow.md (read)
  ✅ checks/global/commit-style.md (read)
  ✅ checks/local/dogfooding.md (read)

🔍 Checks (deterministic):
  ✅ checks/global/navigation-block-readme.sh
  ✅ checks/global/semver-changelog.sh
  ❌ checks/local/pre-merge-tasks.sh (incomplete tasks)

Self-contained: All prompts in SKILL.md (no external prompt files needed).


Mermaid Diagram Generation (Interpretive)

Purpose: Automatically generate + propagate ROADMAP diagram to all backstage files.

Workflow:

  1. Parse ROADMAP.md (deterministic - SH):

    bash
    parse-roadmap.sh backstage/ROADMAP.md
    # Output: version|status_emoji|name
  2. Read checks/ diagram rules (interpretive - AI):

    • checks/global/navigation-block.md defines default format (linear graph, all epics, sequential)
    • checks/local/*.md can override (gantt, flowchart, or diagram: none)
    • Local wins on conflict
  3. Generate mermaid (interpretive - AI):

    • Apply checks/ rules to parsed data
    • Create mermaid syntax matching specification
    • Example (default):
      mermaid
      graph LR
          A[🏗️ v0.1.0 Active Epic] --> B[📋 v0.2.0 Backlog Epic]
  4. Propagate to all files (deterministic - SH):

    • Insert after > 🤖 marker
    • README.md, ROADMAP.md, CHANGELOG.md
    • Remove old diagrams (anti-drift)

AI Prompt (when running backstage-start/end):

Read checks/global/navigation-block.md and checks/local/*.md for diagram rules. Run parse-roadmap.sh to extract epics. Generate mermaid diagram following checks/ rules (prefer local over global). Insert diagram after navigation block (> 🤖) in all backstage files. If local checks say diagram: none, skip generation.

Tools:

  • parse-roadmap.sh - Extract version|status|name from ROADMAP.md
  • checks/ - Diagram format rules (type, include/exclude logic, status mapping)

Polycentric Governance (How It Works)

mermaid
flowchart TD
    GLOBAL_POL[checks/global/*.md<br/>Universal rules]
    LOCAL_POL[checks/local/*.md<br/>Project-specific overrides]
    
    GLOBAL_CHK[checks/global/*.sh<br/>Universal tests]
    LOCAL_CHK[checks/local/*.sh<br/>Project-specific tests]
    
    AI[AI reads checks/]
    BASH[Bash executes checks/]
    CONFLICT{Conflict?}
    
    GLOBAL_POL --> AI
    LOCAL_POL --> AI
    GLOBAL_CHK --> BASH
    LOCAL_CHK --> BASH
    
    AI --> CONFLICT
    CONFLICT -->|Yes| LOCAL_POL
    CONFLICT -->|No| MERGE[Merge rules]
    
    MERGE --> ACTION[Execute workflow]
    LOCAL_POL --> ACTION
    BASH --> ACTION

This skill enforces polycentric governance:

  • Reads ALL checks/**/*.md files (global + local)
  • Executes ALL checks/**/*.sh files (global + local)
  • Merges checks when compatible
  • Prefers local checks on conflict
  • Reports deterministic check results (pass/fail)

Triggered by: "good morning", "good night", "backstage start/end", "update backstage"


Workflow Diagram

mermaid
flowchart TD
    START["Trigger 1️⃣<br/>[SH]"]
    MODE{"Session mode?"}
    
    %% Common enforcement module
    READ_POL["Read checks/<br/>global + local<br/>[AI interprets MD]"]
    EXEC_CHK["Execute checks/<br/>global + local<br/>[Bash runs SH]"]
    
    REPORT["Report 6️⃣<br/>📋 Interpretive (✅)<br/>🔍 Checks (✅/❌)"]
    CHECKS_GATE{"All checks<br/>passed?"}
    
    %% Start Branch
    START_BRANCH["Read README 🤖 block 2️⃣<br/>[MD → AI]"]
    START_FILES["Locate status files 3️⃣<br/>[SH]"]
    START_GIT["Check git branch 4️⃣<br/>[SH]"]
    START_WORK["Analyze changes 5️⃣<br/>[SH]"]
    START_FIX["🛑 STOP: Fix issues<br/>[AI + SH]"]
    START_UPDATE["Update docs 7️⃣<br/>[SH writes MD]"]
    START_REPORT["Developer context 8️⃣<br/>[AI reads MD]"]
    START_PUSH["Push / Groom 9️⃣<br/>[SH]"]
    
    %% End Branch
    END_FIXES["Add fixes to roadmap<br/>[AI writes MD]"]
    END_PUSH["Commit + push<br/>[SH]"]
    END_VICTORY["Victory lap 🏆<br/>[AI reads MD]"]
    END_BODY["Body check ⏸️<br/>[AI prompt]"]
    END_CLOSE["Close VS Code 🌙<br/>[SH]"]
    END_SILENT["[STAY SILENT]"]
    
    %% Update Backstage Branch
    UPDATE_DETECT["Find backstage/ folder<br/>[SH]"]
    UPDATE_CHECK_SYM{"Symlinked?"}
    UPDATE_SKIP["✅ Already auto-updates<br/>[Report]"]
    UPDATE_FETCH["Fetch upstream<br/>[SH: git clone]"]
    UPDATE_DIFF["Compare local vs upstream<br/>[SH: diff]"]
    UPDATE_UPTODATE{"Changes<br/>found?"}
    UPDATE_UPTODATE_SKIP["✅ Already up to date<br/>[Report]"]
    UPDATE_CHANGELOG["Generate mini changelog<br/>[AI reads diffs]"]
    UPDATE_PROMPT{"User<br/>approves?"}
    UPDATE_ABORT["Aborted<br/>[Report]"]
    UPDATE_APPLY["rsync upstream → local<br/>[SH]"]
    UPDATE_REPORT["🎉 Updated!<br/>[Report changes]"]
    
    %% Flow
    START --> MODE
    
    MODE -->|Start| START_BRANCH
    START_BRANCH --> START_FILES
    START_FILES --> START_GIT
    START_GIT --> START_WORK
    START_WORK --> READ_POL
    START_WORK --> EXEC_CHK
    
    READ_POL --> REPORT
    EXEC_CHK --> REPORT
    REPORT --> CHECKS_GATE
    
    CHECKS_GATE -->|No, start mode| START_FIX
    START_FIX --> READ_POL
    CHECKS_GATE -->|Yes| START_UPDATE
    START_UPDATE --> START_REPORT
    START_REPORT --> START_PUSH
    
    MODE -->|End| READ_POL
    MODE -->|End| EXEC_CHK
    CHECKS_GATE -->|No, end mode| END_FIXES
    CHECKS_GATE -->|Yes| END_PUSH
    END_FIXES --> END_VICTORY
    END_PUSH --> END_VICTORY
    END_VICTORY --> END_BODY
    END_BODY --> END_CLOSE
    END_CLOSE --> END_SILENT
    
    MODE -->|Update| UPDATE_DETECT
    UPDATE_DETECT --> UPDATE_CHECK_SYM
    UPDATE_CHECK_SYM -->|Yes| UPDATE_SKIP
    UPDATE_CHECK_SYM -->|No| UPDATE_FETCH
    UPDATE_FETCH --> UPDATE_DIFF
    UPDATE_DIFF --> UPDATE_UPTODATE
    UPDATE_UPTODATE -->|No| UPDATE_UPTODATE_SKIP
    UPDATE_UPTODATE -->|Yes| UPDATE_CHANGELOG
    UPDATE_CHANGELOG --> UPDATE_PROMPT
    UPDATE_PROMPT -->|No| UPDATE_ABORT
    UPDATE_PROMPT -->|Yes| UPDATE_APPLY
    UPDATE_APPLY --> UPDATE_REPORT

Domain labels:

  • [MD] - Markdown file (checks/*.md, ROADMAP.md) = Human/AI prompts
  • [SH] - Shell script (checks/*.sh, backstage-start.sh) = Machine executables
  • [AI reads MD] - AI parses markdown, understands rules/prompts
  • [AI writes MD] - AI generates markdown content
  • [SH writes MD] - Script modifies markdown files (checkboxes, navigation blocks)
  • [Bash runs SH] - Bash executes shell scripts (deterministic validation)
  • [AI interprets MD] - AI reads checks/, acts contextually

Critical separation:

  • checks/ = prompts - AI reads, interprets, acts
  • checks/ = executors - Bash runs commands, returns exit codes
  • AI intermediates - Reads checks/, executes checks/, integrates report

Notes:

1️⃣ Trigger: "backstage start", "vamos trabalhar no X", "whatsup" (start mode) OR "backstage end", "boa noite", "wrap up" (end mode)

  • Code: backstage-start.sh OR backstage-end.sh

2️⃣ Read README 🤖 block: Find navigation block between > 🤖 markers. Extract all status file paths (ROADMAP, CHANGELOG, checks/, checks/). This is ONLY source of truth for file locations.

  • Code: backstage-start.sh::read_navigation_block()

3️⃣ Locate status files: Use paths from 🤖 block. If missing, STOP and ask user where to create them. Check BOTH global (backstage/checks/global/, backstage/checks/global/) and local (backstage/checks/local/, backstage/checks/local/) for polycentric governance.

  • Code: backstage-start.sh::locate_status_files()

4️⃣ Check git branch: Run git branch --show-current. Determine work context.

  • Code: backstage-start.sh::check_branch()

5️⃣ Analyze changes:

bash
git diff --name-status
git diff --stat
LAST_VERSION=$(grep -m1 "^## v" CHANGELOG.md | cut -d' ' -f2)
git log --oneline "${LAST_VERSION}..HEAD"

Categorize: patch/minor/major. Compare with ROADMAP. Match reality to plans.

  • Code: backstage-start.sh::analyze_changes()

6️⃣ Report - Policies + Checks:

Report format:

📋 Interpretive checks:
  ✅ checks/global/branch-workflow.md (read)
  ✅ checks/global/commit-style.md (read)
  ✅ checks/local/dogfooding.md (read)

🔍 Checks (deterministic):
  ✅ checks/global/navigation-block-readme.sh
  ✅ checks/global/semver-changelog.sh
  ❌ checks/local/pre-merge-tasks.sh (incomplete tasks)

Policies always ✅: AI reads, interprets, will act accordingly

Checks can fail ❌: Exit code determines status

Mode behavior:

  • Start mode: Hard fail (block commit if checks fail)

  • End mode: Soft fail (warn, add to ROADMAP)

  • Code: backstage-start.sh::report_enforcement()

7️⃣ Update docs: If checks pass, auto-update ROADMAP (mark checkboxes) and CHANGELOG (add new entries at TOP, append-only). Bump version. Add navigation menu to all status files.

  • Code: backstage-start.sh::update_docs()

8️⃣ Developer context: Generate outcome-based summary (5 possible states: 🛑 Failed, ⚠️ Mismatch, 🧑 Grooming, ✅ Progress, 🎉 Complete). Show: When, What, Why, Status, Next.

  • Code: backstage-start.sh::show_developer_context()

9️⃣ Push / Groom: If checks passed, commit with appropriate message (progress/release). If grooming mode, just update ROADMAP priorities.

  • Code: backstage-start.sh::prompt_push()

Victory lap 🏆: Brief reminder of achievements (3 main items max + stats). Keep it short.

  • Code: backstage-end.sh::victory_lap()

Body check ⏸️: Ask: Hungry? Thirsty? Tired? Need to stretch? What does body NEED right now?

  • Code: backstage-end.sh::body_check()

Close VS Code 🌙: Run countdown + osascript -e 'quit app "Visual Studio Code"'. CRITICAL: Agent must NOT send ANY message after this or VS Code will prompt "unsaved changes".

  • Code: backstage-end.sh::close_vscode()

[STAY SILENT]: No reply after closing VS Code (prevents unsaved prompt).

🔄 Update Backstage: "update backstage" trigger

  • Find backstage folder: Search CWD for */backstage/ directory
  • Check if symlinked: If checks/global/ is symlink → already auto-updates (skip)
  • Fetch upstream: Clone https://github.com/nonlinear/backstage (temp dir)
  • Compare: Diff local checks/global/ vs upstream
  • Generate changelog: Show NEW, CHANGED, REMOVED files (with descriptions)
  • Prompt user: "Apply updates? (y/n)"
  • Apply if yes: rsync --delete upstream → local
  • Report: What changed, how many files
  • Code: update-backstage.sh

When to Use

Trigger patterns:

"Bom dia" / "Good morning" + PROJECT:

  • bom dia personal / good morning personal
  • bom dia librarian / good morning librarian
  • Action: Load project context + run health checks
  • Output: Current epic, roadmap status, branch info, gaps

"Update backstage":

  • Action: Compare local */backstage/checks/global/ against official repo
  • Detect changes: What's NEW or CHANGED in upstream
  • Show delta: Mini changelog (1 paragraph: what you GAIN if updated)
  • Confirm: User approves update
  • Execute: Pull latest checks/global/ files from upstream
  • Output: Updated files list, what changed

Start mode:

  • "backstage start"
  • "whatsup"
  • "vamos trabalhar no X"
  • "what's the status"
  • Before every commit (especially after long breaks)

End mode:

  • "backstage end"
  • "boa noite"
  • "wrap up"
  • "pause work"
  • End of work session, when tired, or context-switch

Show full SKILL.md (673 more words)Show less

"Update Backstage" Workflow

Trigger: update backstage (from any project using backstage protocol)

Purpose: Sync local checks/global/ with latest from upstream repo, show what's new.

How It Works
  1. Detect project backstage folder:

    bash
    # Search up from CWD for backstage/ folder
    find . -type d -name "backstage" | grep -E "backstage$"
    # Or read README 🤖 block for backstage location
  2. Confirm upstream source:

    bash
    # Check if checks/global/ is symlink (admin mode)
    if [ -L "backstage/checks/global" ]; then
      echo "✅ Symlinked to upstream (auto-updates)"
      exit 0
    fi
    
    # Otherwise, assume official repo
    UPSTREAM="https://github.com/nonlinear/backstage"
    echo "Upstream: $UPSTREAM"
    echo "Confirm this is correct? (y/n)"
  3. Fetch latest from upstream:

    bash
    # Clone or pull latest
    TMP_DIR=$(mktemp -d)
    git clone --depth 1 "$UPSTREAM" "$TMP_DIR/backstage"
  4. Compare local vs upstream:

    bash
    # Diff local checks/global/ vs upstream
    diff -qr backstage/checks/global/ "$TMP_DIR/backstage/backstage/checks/global/"
  5. Generate mini changelog:

    📦 Backstage Updates Available:
    
    NEW files (3):
    - skill-publish-warning.sh (warns before merging unpublished skills)
    - rebase-cadence.md (suggests rebase if branch >7 days old)
    - epic-notes-orphan-detection.md (detects orphan epic notes)
    
    CHANGED files (2):
    - merge-to-main.md (added Step 0: skill publish check)
    - epic-branch.sh (improved detection logic)
    
    WHAT YOU GAIN:
    Better skill publishing workflow, orphan detection, rebase reminders.
  6. Prompt user:

    Apply these updates? (y/n)
  7. Update if confirmed:

    bash
    # Copy upstream checks/global/ to local
    rsync -av --delete "$TMP_DIR/backstage/backstage/checks/global/" backstage/checks/global/
    
    # Cleanup
    rm -rf "$TMP_DIR"
    
    echo "✅ Updated checks/global/ from upstream"
  8. Report:

    🎉 Backstage updated!
    
    Files changed: 5
    - Added: skill-publish-warning.sh, rebase-cadence.md, epic-notes-orphan-detection.md
    - Modified: merge-to-main.md, epic-branch.sh
    
    Next: Run 'backstage start' to test new checks.
Edge Cases

Symlinked (admin mode):

  • If checks/global/ is symlink → already auto-updates
  • Just report: "✅ Already symlinked to upstream (no action needed)"

No changes:

  • If local == upstream → report: "✅ Already up to date"

Conflicts:

  • If user modified global checks locally → warn, ask to resolve
  • Suggest: copy to checks/local/ (overrides) before updating

No internet:

  • If git clone fails → report: "❌ Can't reach upstream (offline?)"

Key Principles

  1. README's 🤖 block = Single source of truth for file locations
  2. Status files = AI prompts (checks/ = tests, checks/ = rules, ROADMAP = backlog, CHANGELOG = history)
  3. Polycentric governance (global + local rules, local wins on conflict)
  4. Checks must pass before commit (non-negotiable for start mode, soft fail for end mode)
  5. CHANGELOG is append-only (never edit old entries, add NEW entry for corrections)
  6. 5 possible outcomes (Failed, Mismatch, Grooming, Progress, Complete)
  7. Documentation auto-syncs with reality (mark checkboxes, bump versions, move epics)
  8. Body check at end (mental health + momentum preservation)
  9. Silent after VS Code close (prevent unsaved prompt)
  10. Works on ANY project (no hardcoded paths, reads README first)

The 5 States (Start Mode)

StateWhenActionCan Push?
🛑 Failed ChecksTests failFix issues❌ NO
⚠️ Docs MismatchCode ≠ docsAuto-update docs✅ YES
🧑 GroomingNo changesPlan next workN/A
✅ In ProgressPartial workUpdate checkboxes✅ YES
🎉 Version CompleteAll done!Move to CHANGELOG✅ YES 🎉

Check Policy

From checks/:

  • Epic branches: Soft fail (warn but allow)
  • Main branch: Hard fail (block merge)
  • Wrap-up (end mode): Soft fail (list fixes, don't push)

The 3-Level System

Level 1: Personal (not tracked)

  • Your books, notes, local config
  • Not part of any project

Level 2: Project-Specific (e.g., Librarian MCP)

  • Generic tool others can use
  • Has status files (ROADMAP, CHANGELOG, checks/, checks/)
  • Example flagship project for Level 3

Level 3: Meta-Workflow (this skill)

  • Works for ANY project
  • No hardcoded paths
  • Reads README to find everything
  • Can be copied anywhere

Reference Prompts

Original prompts (for future refinement):

  • backstage-start.prompt.md - Full start workflow specification
  • backstage-close.prompt.md - Full end workflow specification

Location: /Users/nfrota/Documents/nonlinear/.github/prompts/

Note: This SKILL.md is a DRAFT distillation of those prompts. Future refinements will improve diagram, add emoji notes, clarify steps. The original prompts contain ALL details.


TODO / Future Refinements

  • Update .sh scripts to read checks/ and checks/ folders
  • Add emoji notes (like design-discrepancy 1️⃣-8️⃣ format)
  • Simplify diagram (consolidated enforcement, removed "separate" step)
  • Add code execution points (where scripts run, if any)
  • Create templates (for new projects without status files)
  • Document edge cases (no git, no README, corrupted files)
  • Add examples (successful runs, failed runs, grooming sessions)
  • Test on multiple projects (validate universal workflow)
  • Consider splitting (start vs end as separate skills?)

Created: 2026-02-12 Updated: 2026-02-18 (v1.0.0 - modular checks/checks) Status: Documentation updated, scripts pending Location: ~/Documents/backstage/skills/backstage/SKILL.md

© LeoYeAI, 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 6 other files in skills/backstage of LeoYeAI/openclaw-master-skills.

  • SKILL.md
  • _meta.json
  • backstage.sh
  • checks.sh
  • contract.html
  • parse-roadmap.sh
  • update-backstage.sh

Open the folder on GitHubat commit e5199b5

Compare with similar skills

Backstage 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.

Backstage compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Backstage this skillLeoYeAI/openclaw-master-skills2.2k—~5.5kAutomated safety check: PassMIT
Eks Best Practicesaws-samples/appmod-blueprints113—~5kAutomated safety check: PassMIT-0
Devops EngineerYikai-Liao/symusic1891 repos~1.5kAutomated safety check: PassMIT
Thermo Nuclear Reviewcursor/plugins10k1 repos~1.1kAutomated safety check: PassNone
Mcaf Devexmanagedcode/Storage138—~911Automated safety check: PassMIT
Sap Btp Best Practicessecondsky/sap-skills462—~3.8kAutomated safety check: PassGPL-3.0

Similar skills

  • Eks Best Practices

    aws-samples/appmod-blueprints

    Official

    Advisory guidance for Amazon EKS architecture and configuration decisions — compute strategy, networking, security, reliability, cost, autoscaling, observability, multi-tenancy, and upgrade planning.

    113 GitHub stars~5k tokensUpdated yesterday
    DevOps & CloudAuto-check passed
  • Devops Engineer

    Yikai-Liao/symusic

    Creates Dockerfiles, configures CI/CD pipelines, writes Kubernetes manifests, and generates Terraform/Pulumi infrastructure templates.

    189 GitHub starsUsed in 1 repo~1.5k tokens
    DevOps & CloudAuto-check passed
  • Thermo Nuclear Review

    cursor/plugins

    Official

    Comprehensive security and correctness audit of a branch's changes.

    10k GitHub starsUsed in 1 repo~1.1k tokens
    DevOps & CloudAuto-check passed
  • Mcaf Devex

    managedcode/Storage

    Improve developer experience for multi-component solutions: onboarding, F5 contract, cross-platform tasks, local inner loop, and reproducible setup.

    138 GitHub stars~911 tokensUpdated yesterday
    DevOps & CloudAuto-check passed
  • Sap Btp Best Practices

    secondsky/sap-skills

    SAP BTP best practices for enterprise architecture, account management, security, and operations, with verification evidence tracked in the repository ledger.

    462 GitHub stars~3.8k tokensUpdated 3 days ago
    DevOps & CloudAuto-check passed
  • Patch Backstage

    redhat-developer/rhdh

    Workflow to backport Backstage changes into RHDH by syncing a downstream maintenance branch and generating yarn patches.

    172 GitHub stars~3.3k tokensUpdated today
    DevOps & CloudAuto-check passed

More from LeoYeAI/openclaw-master-skills

All 972 skills in this repo
  • DevOps Pipeline Management

    LeoYeAI/openclaw-master-skills

    Manages pipelines on a DevOps quality and efficiency platform through its OpenAPI: list workspaces and templates, create, update, run and cancel pipelines, and read run records.

    2.2k GitHub stars~4.2k tokensUpdated 2 mo ago
    Auto-check: notes
  • Feishu Document Collaboration

    LeoYeAI/openclaw-master-skills

    Patches OpenClaw's Feishu extension so an edited document triggers an isolated agent session that reads the doc and replies inline, turning it into a live chat space.

    2.2k GitHub stars~2k tokensUpdated 2 mo ago
    Auto-check passed
  • Files Memory System

    LeoYeAI/openclaw-master-skills

    Multi-context memory management system for OpenClaw agents with group-isolated storage, global shared memory, workspace organization, and group-specific skills isolation.

    2.2k GitHub stars~3.8k tokensUpdated 2 mo ago
    Auto-check passed
  • GEO-Claw AI Visibility Agent

    LeoYeAI/openclaw-master-skills

    Runs a brand's AI-search visibility work end to end: diagnosing how AI platforms represent it, repositioning it, producing AI-optimized content and monitoring ongoing mentions.

    2.2k GitHub stars~4.7k tokensUpdated 2 mo ago
    Auto-check passed
  • Google Workspace CLI

    LeoYeAI/openclaw-master-skills

    Installs and authenticates the gws CLI, then automates Gmail, Drive, Sheets, Calendar, Docs, Chat and Tasks with ready-made recipes, persona bundles and security audits.

    2.2k GitHub stars~2.6k tokensUpdated 2 mo ago
    Auto-check: notes
  • HealthFit Health Advisors

    LeoYeAI/openclaw-master-skills

    Runs four advisor roles, a fitness coach, nutritionist, data analyst and TCM practitioner, to build a health profile and track workouts, diet and wellness over time.

    2.2k GitHub stars~4.4k tokensUpdated 2 mo ago
    Auto-check passed

Categories

Questions about Backstage

What does Backstage do?

Anti-drift protocol script. An agent skill from LeoYeAI/openclaw-master-skills. Backstage is an agent skill from LeoYeAI/openclaw-master-skills. Anti-drift protocol script.

When should I use Backstage?

Backstage fits situations like: tasks that involve Platform engineering.

How do I install Backstage in Claude Code?

Run `npx skills add LeoYeAI/openclaw-master-skills --skill backstage -a claude-code`. Or copy the skill folder (skills/backstage in LeoYeAI/openclaw-master-skills) into .claude/skills/backstage in your project. Claude Code loads it when a task matches its description.

How do I install Backstage in Codex?

Run `npx skills add LeoYeAI/openclaw-master-skills --skill backstage -a codex`. Or copy the skill folder (skills/backstage in LeoYeAI/openclaw-master-skills) into .agents/skills/backstage in your project. Codex loads it when a task matches its description.

Can I use Backstage 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 LeoYeAI/openclaw-master-skills --skill backstage -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/backstage, .gemini/skills/backstage, .github/skills/backstage and .opencode/skills/backstage in your project.

What does Backstage need to run?

Going by SKILL.md and its folder, Backstage needs a shell for the scripts in its folder and the command-line tools its instructions call (git, rsync and osascript). Our summary lists: A Bash shell.

Does Backstage access the network?

SKILL.md names 1 domain. In commands or code: github.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Backstage 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 Backstage use?

Backstage is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Backstage use?

About 5.5k tokens (SKILL.md is roughly 22k 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 Backstage?

Skills that share tags, products or a category with Backstage: Eks Best Practices (aws-samples/appmod-blueprints, 113 stars), Devops Engineer (Yikai-Liao/symusic, 189 stars), Thermo Nuclear Review (cursor/plugins, 10k stars) and Mcaf Devex (managedcode/Storage, 138 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Backstage?

LeoYeAI (a GitHub user) maintains it in LeoYeAI/openclaw-master-skills, which has 2,159 GitHub stars. The repository holds 972 skills in this directory. The repository was last updated on July 20, 2026.

Source: LeoYeAI/openclaw-master-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.