Skip to content
Agentmart
Submit a tool

validate

Run the SDLC validation pipeline using direct tool invocations.

Skill by SteveGJones

IndexedMIT★ 41
Write a review

Chalk Labs

Need help deploying validate?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/stevegjones-validate

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Run the SDLC validation pipeline using direct tool invocations. No wrapper scripts required. Use when checking code quality before commits or PRs.

Use cases: data

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/validate

What's inside

Skill name
validate
Description
Run the SDLC validation pipeline using direct tool invocations. No wrapper scripts required. Use when checking code quality before commits or PRs.
License
MIT
Instructions
193 lines in SKILL.md · view on GitHub

Before installing

  • Instructions call the network

Files (1)

  • SKILL.md

SKILL.md (first lines)

# SDLC Validation

Run the validation pipeline at the specified level. Each check calls standard tools directly — no wrapper scripts needed.

## Arguments

- `--syntax` — Syntax only (fast, after every edit)
- `--quick` — Syntax + lint + tests (before commits)
- `--pre-push` — Full pipeline (before PRs). This is the default.

## Preflight

Before running any check, verify the tool is available. Report missing tools clearly:

```
[SKIP] <tool> — not installed (run: <install command>)
```

Missing tools at `--syntax` level: warn but continue.
Missing tools at `--quick` or `--pre-push` level: report all missing tools, then stop.

### Preflight checks

| Tool | Check command | Install command |
|------|--------------|-----------------|
| ruff | `which ruff` | `pip install ruff` |
| pytest | `which pytest` | `pip install pytest` |
| mypy | `which mypy` | `pip install mypy` |
| bandit | `which bandit` | `pip install bandit` |

Also check:
- Virtual environment active: `which python` should contain `.venv`. If not, warn: "No virtual environment active. Run: source .venv/bin/activate"
- Test directory exists: `ls tests/` should find test files. If `tests/` missing or empty, report: "No tests found. Tests are mandatory (Constitution Article 10.2)."

## --syntax (after every edit)

Run these checks:

1. **Python AST check** — verify all .py files parse:
```bash
python -c "
import ast, sys, pathlib
errors = []
for f in pathlib.Path('.').rglob('*.py'):
    if '.venv' in str(f):
        continue
    try:
        ast.parse(f.read_text())
    except SyntaxError as e:
        errors.append(f'{f}:{e.lineno}: {e.msg}')
if errors:
    print('Syntax errors found:')
    for e in errors:
        print(f'  {e}')
    sys.exit(1)
print(f'Syntax OK — {len(list(pathlib.Path(\".\").rglob(\"*.py\")))} files checked')
"
```

2. **Ruff syntax errors only** (if ruff installed):
```bash
ruff check . --select E9,F63,F7,F82
```

Report results:
```
[PASS] Syntax check — N files checked, 0 errors
[PASS] Ruff (syntax) — 0 issues
```

## --quick (before commits)

Run all --syntax checks, then:

3. **Ruff full lint**:
```bash
ruff check .
```

4. **Ruff format check**:
```bash
ruff format --check .
```

5. **Technical debt scan**:
```bash
grep -rn "TODO\|FIXME\|HACK\|XXX" --include="*.py" --exclude-dir=.venv . || true
```
If any matches found, report as failure (Production+) or warning (Prototype).

6. **Test execution**:
```bash
pytest --tb=short -q
```
If pytest is not installed or no tests exist, this is a failure (not a skip).

7. **Import smoke test** — verify the main module imports:
```bash
python -c "import app" 2>/dev/null || python -c "import main" 2>/dev/null || echo "No app/main module found (skipping import check)"
```

Report results:
```
[PASS] Ruff — 0 issues
[PASS] Format — all files formatted
[PASS] Technical debt — 0 markers
[PASS] Pytest — N passed, 0 failed
[PASS] Import check — app module imports cleanly
```

## --pre-push (before PRs)

Run all --quick checks, then:

8. **Type checking**:
```bash
mypy . --ignore-missing-imports
```
Or if mypy.ini or pyproject.toml configures mypy, just:

From SteveGJones/ai-first-sdlc-practices, MIT.

More from SteveGJones/ai-first-sdlc-practices

Signals

Stars
41
Forks
6
Open issues
37
Last commit (this folder)
Apr 9, 2026 (7 months ago)
Last release
Aug 10, 2025 (1 year ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from SteveGJones

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get validate running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying validate?

CallGet help
Cite this page

validate skill. Agent Mart. https://agentmart.dev/skills/stevegjones-validate (last updated 2026-10-24)