Operating Framework Meta-Skill
Enforces procedural checks and prevents skipping mandatory development protocols.
Install
mkdir -p .claude/skills/operating-framework-meta-skill && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/11064" && unzip -o skill.zip -d .claude/skills/operating-framework-meta-skill && rm skill.zipInstalls to .claude/skills/operating-framework-meta-skill
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Process checks for applying the operating framework before actions and task transitions.Key capabilities
- →Enforce process discipline
- →Audit task completion gates
- →Verify test-driven development
- →Validate root cause evidence
How it works
It acts as a background auditor that forces verification of established operating frameworks before actions.
Inputs & outputs
When to use Operating Framework Meta-Skill
- →Enforcing test-driven development
- →Auditing task completion gates
- →Maintaining operational process discipline
About this skill
Operating Framework Meta-Skill
Process discipline enforcement layer. Always active. No exceptions.
Triggers
This skill activates automatically before every action. It is not invoked manually.
The 1% Rule
If there is even a 1% chance that a Operating Framework skill applies to your current task, you MUST check and follow it. Do not rationalize skipping.
Quick-Scan Checklist
Before every action, mentally scan this list:
| If you are about to... | Check this skill |
|---|---|
| Write production code | test-driven-development |
| Fix a bug | debug command (root cause gate) |
| Claim something is "done" | verification-before-completion |
| Start coding from a brainstorm | sc:brainstorm (approval gate) |
| Execute a plan | executing-plans |
| Spawn subagents | subagent-development |
| Work on a feature branch | branch-finishing, git-worktrees |
| Receive review feedback | receiving-code-review |
| Start any implementation | confidence-check (pre-existing) |
| Start any meaningful task | operating-framework — Lane? Risk tier? Council mode? |
Anti-Rationalization Table
These are the 8 most common excuses for skipping process. None are valid.
| Excuse | Reality | Rule |
|---|---|---|
| "It's too small for TDD" | Small changes break systems. Tests take 30 seconds. | Write the test. |
| "I'll add tests later" | You won't. Technical debt compounds. | Write the test NOW. |
| "The code is obvious" | Obvious code still has edge cases. Tests document behavior. | Write the test. |
| "I already know the root cause" | Confirmation bias. Your first guess is often wrong. | Show the evidence first. |
| "This is just a quick fix" | Quick fixes cause regressions. | Follow the full debug cycle. |
| "The user wants it fast" | The user wants it RIGHT. Rework is slower than discipline. | Follow the process. |
| "I verified it mentally" | Mental verification misses runtime behavior. | Run the actual verification. |
| "This skill doesn't really apply" | If you're debating it, the 1% rule says it applies. | Check the skill. |
Priority Order
When instructions conflict, follow this priority:
- User's explicit instructions (highest)
- Operating Framework hard gates (cannot be silently skipped)
- Existing skills and commands
- Default Claude Code behavior (lowest)
Hard Gates Summary
These gates block forward progress until their conditions are met:
| Gate | Blocks | Until |
|---|---|---|
| TDD Gate | Writing production code | A failing test exists for the feature |
| Root Cause Gate | Applying a fix | Root cause is stated with evidence |
| Approval Gate | Coding from brainstorm | User explicitly approves the spec |
| Verification Gate | Claiming "done" | Evidence (test output, logs) is shown |
| Branch Gate | Starting implementation | You are on a feature branch, not main |
What This Skill Does NOT Do
- Does not replace existing skills or commands
- Does not add overhead to simple file reads or exploratory work
- Does not require gates for non-code tasks (research, explanation, documentation)
- Does not override the user's explicit
--skip-gateinstruction
When not to use it
- →When the task is non-code documentation
- →When the user explicitly skips gates
Limitations
- →Does not replace existing skills
- →Requires active process discipline
How it compares
It prevents rationalizing shortcuts by enforcing hard gates for TDD and root cause analysis.
Compared to similar skills
Operating Framework Meta-Skill side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| Operating Framework Meta-Skill (this skill) | 0 | 3mo | No flags | Intermediate |
| conversation-analyzer | 8 | 9mo | Review | Intermediate |
| wrap | 0 | 6mo | Review | Intermediate |
| file-operations | 1 | 9mo | Review | Beginner |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
conversation-analyzer
mhattingpete
Analyzes your Claude Code conversation history to identify patterns, common mistakes, and opportunities for workflow improvement. Use when user wants to understand usage patterns, optimize workflow, identify automation opportunities, or check if they're following best practices.
wrap
team-attention
세션 종료 시 자동 정리를 수행합니다. CLAUDE.md 업데이트 제안, 반복 패턴 자동화 기회 탐지, 배운 것 정리, 미완성 작업 정리. 사용자가 /wrap 또는 세션 마무리 요청 시 사용.
file-operations
mhattingpete
Analyze files and get detailed metadata including size, line counts, modification times, and content statistics. Use when users request file information, statistics, or analysis without modifying files.
triage-issue
mysticaltech
Use when triaging a GitHub issue - analyzes issue, checks for duplicates, categorizes, and drafts response
proof-of-work
MadAppGang
Proof artifact generation patterns for task validation. Covers screenshots, test results, deployments, and confidence scoring.
setup
PackRat-AI
Configure which review agents run for your project. Auto-detects stack and writes compound-engineering.local.md.