ascii-diagram-validator
Validate ASCII diagram alignment in markdown. TRIGGERS - diagram alignment, ASCII art, box-drawing diagrams.
What this skill does
# ASCII Diagram Validator
Validate and fix alignment issues in ASCII box-drawing diagrams commonly used in architecture documentation, README files, and code comments.
> **Self-Evolving Skill**: This skill improves through use. If instructions are wrong, parameters drifted, or a workaround was needed — fix this file immediately, don't defer. Only update for real, reproducible issues.
## Overview
ASCII diagrams using box-drawing characters (─│┌┐└┘├┤┬┴┼ and double-line variants ═║╔╗╚╝╠╣╦╩╬) require precise column alignment. This skill provides:
1. **Validation script** - Detects misaligned characters with file:line:column locations
2. **Actionable fixes** - Specific suggestions for correcting each issue
3. **Multi-file support** - Validate individual files or entire directories
## When to Use This Skill
Invoke when:
- Creating or editing ASCII architecture diagrams in markdown
- Reviewing documentation with box-drawing diagrams
- Fixing "diagram looks wrong" complaints
- Before committing docs/ARCHITECTURE.md or similar files
- When user mentions "ASCII alignment", "diagram alignment", or "box drawing"
## Supported Characters
### Single-Line Box Drawing
```
Corners: ┌ ┐ └ ┘
Lines: ─ │
T-joins: ├ ┤ ┬ ┴
Cross: ┼
```
### Double-Line Box Drawing
```
Corners: ╔ ╗ ╚ ╝
Lines: ═ ║
T-joins: ╠ ╣ ╦ ╩
Cross: ╬
```
### Mixed (Double-Single)
```
╞ ╟ ╤ ╧ ╪ ╫
```
## Quick Start
### Validate a Single File
```bash
/usr/bin/env bash << 'PREFLIGHT_EOF'
uv run ${CLAUDE_PLUGIN_ROOT}/skills/ascii-diagram-validator/scripts/check_ascii_alignment.py docs/ARCHITECTURE.md
PREFLIGHT_EOF
```
### Validate Multiple Files
```bash
/usr/bin/env bash << 'PREFLIGHT_EOF_2'
uv run ${CLAUDE_PLUGIN_ROOT}/skills/ascii-diagram-validator/scripts/check_ascii_alignment.py docs/*.md
PREFLIGHT_EOF_2
```
### Validate Directory
```bash
/usr/bin/env bash << 'PREFLIGHT_EOF_3'
uv run ${CLAUDE_PLUGIN_ROOT}/skills/ascii-diagram-validator/scripts/check_ascii_alignment.py docs/
PREFLIGHT_EOF_3
```
## Output Format
The script outputs issues in a compiler-like format for easy navigation:
```
docs/ARCHITECTURE.md:45:12: error: vertical connector '│' at column 12 has no matching character above
→ Suggestion: Add '│', '├', '┤', '┬', or '┼' at line 44, column 12
docs/ARCHITECTURE.md:67:8: warning: horizontal line '─' at column 8 has no terminator
→ Suggestion: Add '┐', '┘', '┤', '┴', or '┼' to close the line
```
### Severity Levels
| Level | Description |
| ------- | ---------------------------------------- |
| error | Broken connections, misaligned verticals |
| warning | Unterminated lines, potential issues |
| info | Style suggestions (optional cleanup) |
## Validation Rules
The script checks for:
1. **Vertical Alignment** - Vertical connectors (│║) must align with characters above/below
2. **Corner Connections** - Corners (┌┐└┘╔╗╚╝) must connect properly to adjacent lines
3. **Junction Validity** - T-joins and crosses must have correct incoming/outgoing connections
4. **Line Continuity** - Horizontal lines (─═) should terminate at valid endpoints
5. **Box Closure** - Boxes should be properly closed (no dangling edges)
## Exit Codes
| Code | Meaning |
| ---- | ----------------------------------------------- |
| 0 | No issues found |
| 1 | Errors detected |
| 2 | Warnings only (errors ignored with --warn-only) |
## Integration with Claude Code
When Claude Code creates or edits ASCII diagrams:
1. Run the validator script on the file
2. Review any errors in the output
3. Apply suggested fixes
4. Re-run until clean
### Example Workflow
```bash
/usr/bin/env bash << 'PREFLIGHT_EOF_4'
# After editing docs/ARCHITECTURE.md
uv run ${CLAUDE_PLUGIN_ROOT}/skills/ascii-diagram-validator/scripts/check_ascii_alignment.py docs/ARCHITECTURE.md
# If errors found, Claude Code can read the output and fix:
# docs/ARCHITECTURE.md:45:12: error: vertical connector '│' at column 12 has no matching character above
# → Edit line 44, column 12 to add the missing connector
PREFLIGHT_EOF_4
```
## Limitations
- Detects structural alignment issues, not aesthetic spacing
- Requires consistent use of box-drawing characters (no mixed ASCII like +---+)
- Tab characters may cause false positives (convert to spaces first)
- Unicode normalization not performed (use pre-composed characters)
## Bundled Scripts
| Script | Purpose |
| ---------------------------------- | ---------------------- |
| `scripts/check_ascii_alignment.py` | Main validation script |
## Related
- [ARCHITECTURE.md best practices](https://github.com/joelparkerhenderson/architecture-decision-record)
- [Unicode Box Drawing block](https://www.unicode.org/charts/PDF/U2500.pdf)
---
## Troubleshooting
| Issue | Cause | Solution |
| --------------------------- | ----------------------------- | --------------------------------------------------- |
| Script not found | Plugin not installed | Verify plugin installed with `claude plugin list` |
| False positives with tabs | Tab characters misalign | Convert tabs to spaces before validation |
| Mixed ASCII not detected | Using `+---+` style | Script only validates Unicode box-drawing chars |
| Column numbers off | Unicode width calculation | Use pre-composed characters, avoid combining marks |
| No issues but looks wrong | Aesthetic spacing not checked | Validator checks structure, not visual spacing |
| Exit code 2 unexpected | warnings only mode | Use --warn-only flag to treat warnings as success |
| Can't find validation error | Complex nested diagram | Check line numbers in output, validate section only |
| Unicode chars not rendering | Terminal font missing glyphs | Use font with full Unicode box-drawing support |
## Post-Execution Reflection
After this skill completes, check before closing:
1. **Did the command succeed?** — If not, fix the instruction or error table that caused the failure.
2. **Did parameters or output change?** — If the underlying tool's interface drifted, update Usage examples and Parameters table to match.
3. **Was a workaround needed?** — If you had to improvise (different flags, extra steps), update this SKILL.md so the next invocation doesn't need the same workaround.
Only update if the issue is real and reproducible — not speculative.
Related in Writing & Docs
jax-development
IncludedUse this skill when the user is writing, debugging, profiling, refactoring, reviewing, benchmarking, parallelising, exporting, or explaining JAX code, or when they mention JAX, jax.numpy, jit, grad, value_and_grad, vmap, scan, lax, random keys, pytrees, jax.Array, sharding, Mesh, PartitionSpec, NamedSharding, pmap, shard_map, Pallas, XLA, StableHLO, checkify, profiler, or the JAX repo. It helps turn NumPy or PyTorch-style code into pure functional JAX, fix tracer/control-flow/shape/PRNG bugs, remove recompiles and host-device syncs, choose transforms and sharding strategies, inspect jaxpr/lowering/IR, and benchmark compiled code correctly.
nature-article-writer
IncludedDrafts, rewrites, diagnostically critiques, and style-calibrates primary research manuscripts for Nature and Nature Portfolio journals. Use when the user wants a Nature-style title, summary paragraph or abstract, introduction, results, discussion, methods, figure legends, presubmission enquiry, cover letter, reviewer response, or when a scientific draft sounds generic, jargon-heavy, structurally weak, or AI-ish and needs precise, broad-reader-friendly prose without inventing data, analyses, or references. Best for primary research articles and letters rather than reviews or press releases unless explicitly adapting one.
deckrd
IncludedDocument-driven framework that derives requirements, specifications, implementation plans, and executable tasks from goals through structured AI dialogue. Use when user says "write requirements", "create spec", "plan implementation", "derive tasks", "structure this feature", "break down into tasks", or "document this module". Also use for reverse engineering existing code into docs (/deckrd rev). Do NOT use for direct code writing — use /deckrd-coder after tasks are generated. Do NOT use when the user only wants to run or fix existing code without planning.
clinical-decision-support
IncludedGenerate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading, statistical analysis (hazard ratios, survival curves, waterfall plots), biomarker integration, and regulatory compliance. Outputs publication-ready LaTeX/PDF format optimized for drug development, clinical research, and evidence synthesis.
handling-sf-data
IncludedSalesforce data operations with 130-point scoring. Use this skill to create, update, delete, bulk import/export, generate test data, and clean up org records using sf CLI and anonymous Apex. TRIGGER when: user creates test data, performs bulk import/export, uses sf data CLI commands, needs data factory patterns for Apex tests, or needs to seed/clean records in a Salesforce org. DO NOT TRIGGER when: SOQL query writing only (use querying-soql), Apex test execution (use running-apex-tests), or metadata deployment (use deploying-metadata).
accelint-ac-to-playwright
IncludedConvert and validate acceptance criteria for Playwright test automation. Use when user asks to (1) review/evaluate/check if AC are ready for automation, (2) assess if AC can be converted as-is, (3) validate AC quality for Playwright, (4) turn AC into tests, (5) generate tests from acceptance criteria, (6) convert .md bullets or .feature Gherkin files to Playwright specs, (7) create test automation from requirements. Handles both bullet-style markdown and Gherkin syntax with JSON test plan generation and validation.