Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Validate

ASecurity

Run all quality gates (lint, typecheck, test, env, i18n, license; optional falsify on --full) and produce a structured pass/fail report. Triggers: "validate" | "quality check" | "pre-push check" | "are we green".

9 stars
0 votes
0 copies
0 views
Added 9/23/2026
ai-agentsbashdockerapi

Works with

api

Security Analysis

A100/100

Scanned 9/23/2026

Install to Claude Code

$npx -y skills add Roxabi/roxabi-plugins --skill validate --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Validate?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Validate
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/roxabi-validate/badge)](https://www.skillsdirectory.com/skills/roxabi-validate)

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
SKILL.md
---
name: R-validate
argument-hint: '[--quick | --full | --affected]'
description: Run all quality gates (lint, typecheck, test, env, i18n, license; optional falsify on --full) and produce a structured pass/fail report. Triggers: "validate" | "quality check" | "pre-push check" | "are we green".
version: 0.2.1
allowed-tools: Bash, Read
---

# Validate

## Success

I := ∀ χ ∈ scope → σ = pass
V := Report shows "Result: All checks passed"

Let:
  χ := quality check (name, command from `{commands.*}`, timeout, result)
  σ := {✅ pass (exit 0), ❌ FAIL (exit ≠0), ⚠️ warn (exit 0 + warnings), ⏭ skip (¬in scope)}

**Stack:** Read `.dev/stack.yml` first — every `{field}` placeholder below resolves from it. ¬∃ → output: "`.dev/stack.yml` not found — run `/R-env-setup` to generate it." and stop.

Run all χ sequentially → single structured pass/fail report. ¬stop on first failure — run all for complete picture.

## Pipeline

| Step | ID | Required | Verifies via | Notes |
|------|----|----------|---------------|-------|
| 1 | scope | ✓ | χ set defined | — |
| 2 | run-checks | ✓ | exit codes captured | continue-on-failure |
| 3 | report | ✓ | report printed | — |
| 4 | failure-details | — | error lines shown | ∃ failures |
| 5 | verdict | ✓ | pass/fail declared | — |

## Pre-flight

Success: ∀ χ ∈ scope → σ = pass
Evidence: Report shows "Result: All checks passed"
Steps: scope → run-checks → report → verdict
¬clear → STOP + ask: "Quick or full validation?"

## Usage

```
/R-validate              → Run all checks
/R-validate --quick      → Lint + typecheck only (fastest)
/R-validate --full       → All checks including license, coverage, optional falsify
/R-validate --affected   → Only check files changed vs main
```

## Instructions

### 1. Scope

| Flag | χ set |
|------|-------|
| (none) | lint, typecheck, test, env, i18n |
| `--quick` | lint, typecheck |
| `--full` | lint, typecheck, test, test:coverage, env, i18n, license, falsify |
| `--affected` | lint (affected), typecheck:affected, test:affected |

### 2. Run χ Sequentially

∀ χ ∈ scope: run command, capture stdout+stderr + exit code. Record: name, σ, duration, error summary (first 5 lines if failed).

**¬raw runner** — always use `{commands.*}` from stack.yml. Command ¬defined → σ := ⏭ skip.

**falsify** (optional, `--full` only): prefer `bash ${CLAUDE_PLUGIN_ROOT}/skills/pr/run-falsify.sh --verify artifacts/reviews/{N}-falsify.json` when JSON exists → require `oracle_ok=true`. Else if `{commands.test:falsify}` / `package.json` `test:falsify` **execs the plugin helper** → run it. Else σ := ⏭ skip. ¬fail the suite solely because a consumer repo has no map yet. Stub consumer scripts that do not invoke the helper → ⏭ skip (¬pass).

| χ | Command | Timeout |
|---|---------|---------|
| Lint | `{commands.lint}` | 60s |
| Typecheck | `{commands.typecheck}` | 120s |
| Typecheck (affected) | `{package_manager} run typecheck:affected` | 120s |
| Test | `{commands.test}` | 180s |
| Test (affected) | `{package_manager} run test:affected` | 180s |
| Test coverage | `{package_manager} run test:coverage` | 300s |
| Env check | `{package_manager} run env:check` | 10s |
| i18n | `{package_manager} run i18n:check` | 30s |
| License | `{package_manager} run license:check` | 30s |
| Falsify | `{commands.test:falsify}` ∨ `{package_manager} run test:falsify` | 180s |

### 3. Report

```
Validate Report
═══════════════

  Check          │ Status │ Duration │ Notes
  Lint           │ ✅ pass │ 2.1s     │ —
  Typecheck      │ ✅ pass │ 8.3s     │ —
  Test           │ ❌ FAIL │ 12.4s    │ 2 failed, 48 passed
  Env check      │ ✅ pass │ 0.3s     │ —
  i18n           │ ⚠️ warn │ 1.1s     │ 3 missing keys in fr.json
  ─────────────────────────────────────────────
  Result: FAIL (4/5 passed, 1 failed)
  Total time: 24.2s
```

### 4. Failure Details

∃ χ ∧ σ = ❌ → append failures. First 10 error lines per failing χ.

```
Failures
────────
Test:
  FAIL src/auth/login.test.ts > should validate token
    AssertionError: expected undefined to be defined
  FAIL src/api/health.test.ts > should return 200
    Error: ECONNREFUSED
```

### 5. Verdict

- ∀ χ pass → `All checks passed. Safe to push.`
- ∃ χ fail → `{N} check(s) failed. Fix before pushing.`
- `--quick` ∧ ∀ pass → `Quick checks passed. Run /R-validate for full check.`

## Edge Cases

| Scenario | Behavior |
|----------|----------|
| Command not found | σ := ⚠️ warn, "command not available" |
| Command times out | σ := ❌ FAIL, "timed out after Xs" |
| ¬test files found | σ := ⏭ skip |
| ¬`test:falsify` script ∧ ¬`{commands.test:falsify}` | σ := ⏭ skip (optional χ) |
| Docker ¬running (env/db) | σ := ⚠️ warn, ¬fail |
| Running in worktree | No special handling needed |

## Safety Rules

1. **Read-only** — ¬modify files
2. **¬auto-fix** — report issues, user decides
3. **Run ALL χ** — ¬short-circuit on first failure
4. **`{commands.*}`** — always use commands from stack.yml, never raw runner (Bun runner ≠ Vitest)

## Chain Position

- **Phase:** Verify
- **Predecessor:** `/R-ci-watch`
- **Successor:** `/R-dev-review`
- **Class:** adv (continuous flow, no gate)

## Task Integration

- `/R-dev` owns the dev-pipeline task lifecycle externally
- This skill does NOT update its own dev-pipeline task
- Sub-tasks created: none

## Exit

- **All pass via `/R-dev`:** return control silently. ¬write summary. ¬ask user. ¬announce `/R-dev-review`. `/R-dev` re-scans and advances.
- **All pass standalone:** print verdict block + `Next: /R-dev-review`. Stop.
- **Failure:** return error. `/R-dev` presents Retry | Skip | Abort.

$ARGUMENTS

Attribution

RoxabiRoxabi
View sourceMore from Roxabi →
SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1066601 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

651 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →