Skip to content
Back to skills

Help

ASecurity

Use this skill when the user runs /help, /help commands, or /help <command-name>. Shows plugin command reference. Read-only — writes nothing, modifies nothing.

  • 3 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added May 26, 2026
documentationsecurity

Security analysis

A100/100

Scanned May 27, 2026

npx -y skills add lantisprime/claude-sdlc --skill help --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Help?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Help
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/lantisprime-help/badge)](https://www.skillsdirectory.com/skills/lantisprime-help)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: help
description: Use this skill when the user runs /help, /help commands, or /help <command-name>. Shows plugin command reference. Read-only — writes nothing, modifies nothing.
config_requirements: []
---

# Help — Plugin Reference

Read-only. Never writes files. Never modifies artifacts. Never invokes other skills.

## Invocation modes

### No args: `/help`

Print a condensed command list — one line each — then a usage tip. Screen budget: ≤ 20 lines total.

```
SDLC Plugin — command reference

  /configure   set up config/tools.json and config/tools.local.json
  /start       guided intake; fix-fast eligibility check; hands off to /plan
  /plan        Phase 1 — classify task, validate scope, estimate effort
  /analyze     Phase 2 — requirements with stable REQ IDs
  /design      Phase 3 — architecture bundle, tech specs, test cases
  /build       Phase 4 — code + unit tests, scoped to plan
  /test        Phase 5 — test execution, defects, UX conformance
  /deploy      Phase 6 — deployment proposal and supervised execution
  /support     Phase 7 — observability wiring (logging, alerts, dashboards)
  /docs        Phase 8 — docs refresh and traceability matrix
  /status      show in-flight task state and pending sign-offs (read-only)
  /review      cross-cutting diff review (correctness + security)
  /fix-fast    compressed path for small bug fixes only (≤2 files, ≤50 LOC)

Run /help <command> for detail on any command.
Run /help commands for the full reference table.
```

### `/help commands`

Print the full command reference table.

Read each file in `commands/` and extract the YAML `description:` field. Format as a markdown table: `Command | Purpose`. Sort by phase order: configure, start, plan, analyze, design, build, test, deploy, support, docs, status, review, fix-fast, token-review.

### `/help <command>`

1. Read `commands/<command>.md`. Extract the YAML `description:` field and the first non-frontmatter paragraph.
2. Read `skills/<command>/SKILL.md` if it exists. Extract the first non-frontmatter paragraph.
3. If neither file exists, print: `No help entry found for /<command>.`
4. Assemble output (≤ 25 lines):

```
/<command> — <YAML description>

<first paragraph from commands/<command>.md or skills/<command>/SKILL.md>

Example:
  /<command> <inferred one-liner>
```

For the Example line: if the commands file contains a code block with a usage example, extract it. Otherwise construct one from the description — typically `/<command> "<short representative phrase>"` for phase commands, or `/<command> --<flag>` for commands with flags.

## What this skill must NOT do

- Do not write or modify any file.
- Do not invoke any other skill.
- Do not invoke any subagent.
- Do not call any hook.

Attribution

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

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.