Skip to content
All Skills

Sanity Check

Step back, reflect on current work, validate direction and alignment. Use when complexity is increasing, feeling uncertain, before major decisions, or something feels off.

Software Engineering|v1|Updated 7/14/2026|GitHub source
MCP get_skill({ skillId: "sanity-check-fc2af5e8" })

Use this skill with your agent

Create a free account and connect via MCP

Get Started Free
# /sanity-check

Mid-work validation using reflection to catch drift early. Permission to pause and think.

## Usage

```bash
/sanity-check                        # Reflect on current work
/sanity-check --project coordinatr   # Focus on specific project
```

## When to Use

- Complexity is increasing
- Feeling uncertain about direction
- Before major decisions
- Something feels off
- After 30+ minutes of planning work

**Not for**: Session start (use /refresh), after completion (just continue)

## Execution Steps

### 1. Reflect Using Sequential Thinking

Process these questions:
- What are we trying to accomplish?
- What have we done so far?
- What's the current approach?
- Does this align with the project vision?
- Are we solving the right problem?
- What concerns exist?

**Categorize findings:**
- Green: On track, continue
- Yellow: Minor issues, easy fixes
- Red: Major drift, course correction needed

### 2. Read Context Files

```bash
# Project context (if specified)
Read: ideas/{project}/README.md
Read: ideas/{project}/project-brief.md
Read: ideas/{project}/critique.md

# General context
Read: CLAUDE.md
Read: about-me.md

# Recent work
Bash: git log -5 --format="%h - %s"
```

Skip missing files gracefully.

### 3. Analyze Alignment

Check against:
- **Vision**: Does current work support project goals?
- **Brief**: Are we addressing the stated problem?
- **Critique**: Are we avoiding known pitfalls?
- **Patterns**: Are we following repo conventions?

### 4. Provide Assessment

```markdown
## Sanity Check

### Current State
[What we're working on, current approach]

### Alignment Check
- **Vision**: [status] [brief assessment]
- **Problem Fit**: [status] [brief assessment]
- **Approach**: [status] [brief assessment]

### Concerns

**What's Working**
- [Positive observation]

**Minor Issues**
- [Yellow flag + suggested fix]

**Critical Issues**
- [Red flag + required action]

### Recommendation
[Continue as-is | Minor adjustment | Course correction | Pause and discuss]

### Next Steps
1. [Specific action]
2. [Specific action]
```

## Philosophy

- **Permission to pause**: Makes stepping back a legitimate workflow step
- **Catch drift early**: Course correction cheap now, expensive later
- **Trust your gut**: If something feels off, run this command
#personal-productivity#daily-routine#weekly-review#life-planning#personal-knowledge#testinggitfilesystem-access

Related Skills

More skills in Software Engineering

Accessibility Standards

Comprehensive web accessibility standards based on WCAG 2.2 AA, with 38+ anti-patterns, legal enforcement context (EAA, ADA Title II), WAI-ARIA patterns, and framework-specific fixes for modern web frameworks and libraries.

#github-copilot#accessibilityMIT

Accord

Authoring unified specification packages across Business/Development/Design teams via staged elaboration (L0 Vision → L1 Requirements → L2 Team Detail → L3 Acceptance Criteria). No code. Use when authoring cross-team specs, building L0-L3 packages, or aligning Biz/Dev/Design on a single source of truth.

#broad-capability#developmentMIT

Acquire Codebase Knowledge

Use this skill when the user explicitly asks to map, document, or onboard into an existing codebase. Trigger for prompts like "map this codebase", "document this architecture", "onboard me to this repo", or "create codebase docs". Do not trigger for routine feature implementation, bug fixes, or narrow code edits unless the user asks for repository-level discovery.

#github-copilot#documentationMIT

Acreadiness Assess

Run the AgentRC readiness assessment on the current repository and produce a static HTML dashboard at reports/index.html. Wraps `npx github:microsoft/agentrc readiness` and hands off rendering to the @ai-readiness-reporter custom agent. Supports policies (--policy) for org-specific scoring. Use when asked to assess, audit, or score the AI readiness of a repo.

#github-copilot#planningMIT

Acreadiness Generate Instructions

Generate tailored AI agent instruction files via AgentRC instructions command. Produces .github/copilot-instructions.md (default, recommended for Copilot in VS Code) plus optional per-area .instructions.md files with applyTo globs for monorepos. Use after running /acreadiness-assess to close gaps in the AI Tooling pillar.

#github-copilot#skillMIT

Acreadiness Policy

Help the user pick, write, or apply an AgentRC policy. Policies customise readiness scoring by disabling irrelevant checks, overriding impact/level, setting pass-rate thresholds, or chaining org baselines with team overrides. Use when the user asks about strict mode, AI-only scoring, custom weights, CI gating, or wants org-wide standardisation.

#github-copilot#planningMIT