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
  • 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.

Back to skills

Command Builder

ASecurity

Generates slash commands with YAML frontmatter, $ARGUMENTS/positional params, and tool permissions. Use when creating .claude/commands/*.md files or fixing command routing.

2 stars
0 votes
0 copies
0 views
Added 9/19/2026
ai-agentsshellbashgitapisecurityperformance

Works with

api

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add bsamiee/Parametric_Portal --skill command-builder --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Command Builder?

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

Security grade badge for Command Builder
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/bsamiee-command-builder/badge)](https://www.skillsdirectory.com/skills/bsamiee-command-builder)

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

Download Zip
Files
SKILL.md
---
name: command-builder
description: >-
    Generates slash commands with YAML frontmatter, $ARGUMENTS/positional params, and tool permissions. Use when creating .claude/commands/*.md files or fixing command routing.
---

# [H1][COMMAND-BUILDER]
>**Dictum:** *Reusable prompt templates reduce repetition and enforce consistency.*

<br>

Load commands from `.claude/commands/` (project) or `~/.claude/commands/` (user). Filename becomes command name.

**Tasks:**
1. Read [workflow.md](./references/workflow.md) — 5-phase creation process
2. Read [variables.md](./references/variables.md) — Argument capture, file references, skill loading
3. Read [hints.md](./references/hints.md) — Argument-hint syntax, enum patterns
4. (prose) Load `style-standards` skill — Voice, formatting, constraints
5. Execute per workflow — UNDERSTAND, ACQUIRE, RESEARCH, AUTHOR, VALIDATE
6. Validate — Quality gate; see §VALIDATION

**References:**

| Domain     | File                                                         |
| ---------- | ------------------------------------------------------------ |
| Workflow   | [workflow.md](references/workflow.md)                        |
| Variables  | [variables.md](references/variables.md)                      |
| Hints      | [hints.md](references/hints.md)                              |
| Validation | [validation.md](references/validation.md)                    |
| Template   | [command.template.md](templates/command.template.md)         |

---
## [1][FRONTMATTER]
>**Dictum:** *Declarative constraints gate command execution.*

<br>

```yaml
---
description: Brief description shown in /help menu
argument-hint: [required-arg] [optional-arg?]
allowed-tools: Read, Write, Edit, Glob, Grep, Task, Bash, TaskCreate
model: opus
---
```

| [INDEX] | [FIELD]             | [TYPE] | [PURPOSE]               | [SYNTAX]                                |
| :-----: | ------------------- | ------ | ----------------------- | --------------------------------------- |
|   [1]   | **`description`**   | string | `/help` menu text       | Verb-first. <80 chars. Outcome-focused. |
|   [2]   | **`argument-hint`** | string | Autocomplete guidance   | `[required]` `[optional?]` `[--flag]`.  |
|   [3]   | **`allowed-tools`** | list   | Scoped tool permissions | Comma-separated tool names.             |
|   [4]   | **`model`**         | string | Override default model  | Full model ID or alias.                 |

[IMPORTANT]:
- [ALWAYS] Use `---` delimiters (three dashes, no spaces).
- [ALWAYS] Quote strings containing `:`, `#`, `[`, `]`, `{`, `}`.
- [NEVER] Use tabs; YAML requires spaces.

[CRITICAL]:
- [ALWAYS] Declare `Read` for every `@path` reference.
- [ALWAYS] Declare `Bash` for every `!command` reference.
- [NEVER] Omit required tools—command fails without output.

---
## [2][MODELS]
>**Dictum:** *Model selection balances capability against cost and latency.*

<br>

[CRITICAL] Session inherits default model. Override for specific capability requirements.

| [INDEX] | [ALIAS]  | [STRENGTH]           | [LATENCY] | [COST] |
| :-----: | -------- | -------------------- | :-------: | :----: |
|   [1]   | `opus`   | Complex reasoning    |   High    |  High  |
|   [2]   | `sonnet` | Balanced performance |  Medium   | Medium |
|   [3]   | `haiku`  | Fast, simple tasks   |    Low    |  Low   |

| [INDEX] | [CHARACTERISTIC]         | [OPUS] | [SONNET] | [HAIKU] |
| :-----: | ------------------------ | :----: | :------: | :-----: |
|   [1]   | **Multi-file scope**     |   X    |          |         |
|   [2]   | **Architectural impact** |   X    |          |         |
|   [3]   | **Standard development** |        |    X     |         |
|   [4]   | **Speed priority**       |        |          |    X    |
|   [5]   | **Deep analysis**        |   X    |    X     |         |

---
## [3][VARIABLES]
>**Dictum:** *Dynamic substitution enables reusable commands.*

<br>

| [INDEX] | [SYNTAX]                   | [CAPTURES]                              | [REQUIRED_TOOL] | [USE_WHEN]           |
| :-----: | -------------------------- | --------------------------------------- | --------------- | -------------------- |
|   [1]   | **`$ARGUMENTS`**           | All args as string                      | None            | Free-form input      |
|   [2]   | **`$1`, `$2`...**          | Positional (1-based)                    | None            | Structured multi-arg |
|   [3]   | **`$ARGUMENTS[N]`**        | Positional (0-based)                    | None            | Indexed access       |
|   [4]   | **`$N`**                   | Shorthand for `$ARGUMENTS[N]` (0-based) | None            | Indexed shorthand    |
|   [5]   | **`${1:-val}`**            | Default if missing                      | None            | Optional parameters  |
|   [6]   | **`${CLAUDE_SESSION_ID}`** | Current session ID                      | None            | Session-specific     |
|   [7]   | **`@path`**                | Include file contents                   | `Read`          | File analysis        |
|   [8]   | **`` !`command` ``**       | Shell preprocessing                     | `Bash`          | Dynamic context      |

[CRITICAL]:
- [NEVER] Mix `$ARGUMENTS` and positional `$1-$N` in same command.
- [ALWAYS] Declare required tools for `@path` and `!command`.

[→references/variables.md](./references/variables.md): Complete reference—examples, skill loading, anti-patterns.

---
## [4][PATTERNS]
>**Dictum:** *Canonical patterns accelerate development.*

<br>

### [4.1][FILE_ANALYSIS]

```markdown
---
description: Analyze file for issues
argument-hint: [file-path]
allowed-tools: Read
---
## Target
@$1
## Task
Identify security, performance, and code quality issues.
```

---
### [4.2][MULTI_FILE_OPERATION]

```markdown
---
description: Process files matching pattern
argument-hint: [glob-pattern]
allowed-tools: Read, Edit, Glob, TaskCreate
---
## Task
Match files via $1. Analyze content. Apply fixes. Track progress via TaskCreate.
```

---
### [4.3][AGENT_WORKFLOW]

```markdown
---
description: Multi-agent analysis
argument-hint: [target-folder]
allowed-tools: Task, Read, Glob, TaskCreate
---
## Task
1. Match files in $1 via Glob
2. Spawn analysis agents via Task
3. Synthesize findings, track via TaskCreate
```

---
### [4.4][SKILL_CONTEXT]

```markdown
---
description: Validate target against skill standards
argument-hint: [target] [focus?]
allowed-tools: Read, Task, Glob, Edit, TaskCreate
---
## Skill Context
@.claude/skills/[skill-name]/SKILL.md
@.claude/skills/[skill-name]/references/[domain]/*.md
## Task
Load context above. Spawn Task agents. Verify findings against loaded context. Apply corrections.
```

[→templates/command.template.md](./templates/command.template.md) — canonical template.

---
## [5][ORGANIZATION]
>**Dictum:** *Namespaces prevent command collision.*

<br>

| [INDEX] | [SCOPE]      | [LOCATION]            | [USE_CASE]            |
| :-----: | ------------ | --------------------- | --------------------- |
|   [1]   | **Personal** | `~/.claude/commands/` | Individual workflows  |
|   [2]   | **Project**  | `.claude/commands/`   | Shared team workflows |

| [INDEX] | [CONVENTION]         | [PATTERN]       | [EXAMPLE]          |
| :-----: | -------------------- | --------------- | ------------------ |
|   [1]   | **Verb-first**       | `action-target` | `create-component` |
|   [2]   | **Lowercase**        | No capitals     | `review-pr`        |
|   [3]   | **Hyphen-separated** | No underscores  | `run-tests`        |
|   [4]   | **Descriptive**      | Clear purpose   | `analyze-coverage` |

```text
.claude/commands/
├── git/
│   ├── commit.md  -> /git:commit
│   └── pr.md      -> /git:pr
└── test/
    └── unit.md    -> /test:unit
```

---
## [6][VALIDATION]
>**Dictum:** *Validation gates prevent incomplete artifacts.*

<br>

[VERIFY] Completion:
- [ ] Workflow: All 5 phases executed (UNDERSTAND → VALIDATE).
- [ ] Frontmatter: Valid YAML, description present, tools declared.
- [ ] Variables: No `$ARGUMENTS` + positional mixing.
- [ ] Tools: All `@path` have `Read`, all `!command` have `Bash`.
- [ ] Quality: LOC < 125, verb-first naming.

[REFERENCE] Operational checklist: [→validation.md](./references/validation.md)

Attribution

bsamieebsamiee
View sourceMore from bsamiee →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

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

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

1023331 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.

3331 votes

catchup

Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.

611 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 →