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

How To

ASecurity

Chief has multiple skills that serve different purposes. Use this guide to find the right one quickly. ---

65 stars
0 votes
0 copies
0 views
Added 9/20/2026
code-qualityrustgo

Security Analysis

A100/100

Scanned 9/20/2026

Install to Claude Code

$npx -y skills add thaitype/chief --skill how-to --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of How To?

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

Security grade badge for How To
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/thaitype-how-to/badge)](https://www.skillsdirectory.com/skills/thaitype-how-to)

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

Download Zip
Files
capture-a-rule.md
# How to pick the right skill for your situation

Chief has multiple skills that serve different purposes. Use this guide to find the right one quickly.

---

## By job size

### Small — goal is already clear

```
/chief-plan
```

You know what you want. The skill grills you briefly, writes goals and contracts, and breaks the work into tasks. When ready, run `/chief-autopilot` to execute.

### Medium — need to clarify before planning

```
/chief-grill   →   /chief-plan
```

Your goal exists but has open design questions (architecture choices, trade-offs, unknowns). `/chief-grill` works through those questions with you — one at a time, with a background verifier checking your answers against the codebase. Feed the outcome into `/chief-plan`.

### Large — requirement is fuzzy or vision-level

```
/shape-up   →   /chief-grill   →   /slim-down   →   /chief-plan
```

You have a problem or vision but haven't turned it into concrete requirements. `/shape-up` interviews you top-down (from problem to solution) to produce a scoped spec. Then `/chief-grill` stress-tests that spec. If the scope is still too big, `/slim-down` cuts it into a phase-sized piece.

---

## By what you're trying to do

| You want to… | Use |
|---|---|
| Plan a milestone step by step | `/chief-plan` |
| Run a milestone hands-off | `/chief-autopilot` |
| Run a full milestone across many batches, one report per task | `/chief-loop` |
| Stress-test a design before building | `/chief-grill` or `/grill-design` |
| Turn a vague idea into a spec | `/shape-up` |
| Cut a goal down to a manageable phase | `/slim-down` |
| Check a plan is safe to run unattended | `/loop-readiness` |
| Actually run a plan's existing gates/tests before trusting them | `/loop-preflight` |
| Permanently capture a decision as a rule | `/chief-rule` |
| Bootstrap project context once | `/chief-init` |
| Review a milestone after it ships | `/chief-retro` |
| Make a quick commit | `/dump-commit` |

---

## Choosing between `/grill-design` and `/chief-grill`

Both stress-test ideas. The difference is persistence and verification depth.

| | `/grill-design` | `/chief-grill` |
|---|---|---|
| Session saved to file? | No — context only | Yes — `.chief/_grill/opened/` |
| Verifies answers against codebase? | No | Yes — spawns `answer-verifier-agent` per question |
| Token cost | Normal | ~2× (two agents running) |
| Best for | Quick design exploration | High-stakes decisions, sessions you might resume |

Use `/grill-design` for smaller ideas where you don't need audit trail or codebase verification. Use `/chief-grill` when the decision is consequential and you want each answer checked.

---

## Choosing between `/chief-plan` and `/chief-autopilot`

| | `/chief-plan` | `/chief-autopilot` |
|---|---|---|
| Review gates? | Yes — approve at each phase | No — runs to completion |
| Requires existing goals/contracts? | No — creates them | Yes (or creates them and runs immediately) |
| Best for | Complex projects, team work, unfamiliar domains | Prototyping, well-defined goals, solo work |

You can combine: plan carefully with `/chief-plan`, then execute with `/chief-autopilot`.

---

## Choosing between `/chief-autopilot` and `/chief-loop`

`/chief-loop` builds directly on `/chief-autopilot`'s auto mode — same no-stopping-for-ambiguity behavior, but it spans as many batches as it takes to finish the milestone (not just one), and writes a report per task instead of one per batch. Use `/loop-readiness` first if the milestone is large or touches anything you'd want a real-environment check on before letting it run unattended for that long — and if it finds pre-existing gates the milestone depends on, follow up with `/loop-preflight` to actually confirm those still pass before starting `/chief-loop`.

If you want the "stop and ask a human on ambiguity" behavior, use `/chief-autopilot safe` instead — `/chief-loop` has no safe-mode equivalent.

---

## Related

- [Skills reference](../reference/skills.md) — Full list of all skills with parameters
- [How to stress-test a design](stress-test-a-design.md)

Attribution

thaitypethaitype
View sourceMore from thaitype →
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 Review

Ultra-compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Each comment is one line: location, problem, fix. Use when user says "review this PR", "code review", "review the diff", "/review", or invokes /caveman-review. Auto-triggers when reviewing pull requests.

1023331 votes

Caveman Commit

Ultra-compressed commit message generator. Cuts noise from commit messages while preserving intent and reasoning. Conventional Commits format. Subject ≤50 chars, body only when "why" isn't obvious. Use when user says "write a commit", "commit message", "generate commit", "/commit", or invokes /caveman-commit. Auto-triggers when staging changes.

1023331 votes

Springboot Verification

Verification loop for Spring Boot projects: build, static analysis, tests with coverage, security scans, and diff review before release or PR.

2456590 votes

Verification Loop

一个全面的 Claude Code 会话验证系统。

2456590 votes

Django Verification

Verification loop for Django projects: migrations, linting, tests with coverage, security scans, and deployment readiness checks before release or PR.

2456590 votes
View all in code-quality →