Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
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
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Aws

ASecurity

Operate AWS accounts and SSO profiles with aws and aws-sso-util.

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

Works with

cliapimcp

Security Analysis

A100/100

Scanned 10/7/2026

$npx -y skills add fmind/dot --skill aws --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Aws?

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

Security grade badge for Aws
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/fmind-aws/badge)](https://www.skillsdirectory.com/skills/fmind-aws)

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

Download with Pro
Files
SKILL.md
---
name: aws
description: "Operate AWS accounts and SSO profiles with aws and aws-sso-util."
license: MIT
metadata:
  kind: connector
  author: Médéric HURIER (Fmind)
  source: github.com/fmind/dot/tree/main/skills/aws
  created: "2026-09-16"
  updated: "2026-10-07"
---

# Amazon Web Services CLI

Use `aws` and `aws-sso-util` for AWS account, IAM, S3, ECS, and CloudWatch operations.

## Workflow

1. **Resolve identity and profile context**: inspect the active AWS profile, SSO session, and caller identity; never assume role or run commands under ambiguous profiles.

   ```bash
   aws sts get-caller-identity --profile <profile> --output json --no-cli-pager
   aws configure list-profiles
   ```

1. **Authenticate via SSO**: when credentials expire, refresh the session using AWS IAM Identity Center (SSO); avoid long-lived access keys. When Identity Center is unavailable, `aws login` exchanges a console sign-in for short-lived credentials; add `--remote` on a host without a local browser.

   ```bash
   aws sso login --profile <profile>
   # Or using aws-sso-util:
   aws-sso-util login --profile <profile>
   # Without Identity Center:
   aws login --profile <profile>
   ```

1. **Pin every consequential call**: pass `--profile <name>` and `--region <region>` explicitly so environment variables or shell defaults cannot redirect operations to the wrong account or region.
1. **Start read-only with bounded queries**: use `--query` (JMESPath) and `--max-items` to constrain results; describe resources, IAM policies, and CloudWatch metrics before changing anything.

   ```bash
   aws s3 ls --profile <profile>
   aws ecs list-clusters --profile <profile> --region <region> --max-items 20 --output json --no-cli-pager
   ```

1. **Authorize mutations**: resource creation, security group changes, policy updates, and deletions require user authorization; reuse existing authority rather than asking again.

## Gotchas

- **Refresh expired SSO tokens**: SSO tokens expire after their configured duration; refresh via `aws sso login` rather than falling back to static API keys.
- **`--query` runs client-side**: select needed fields and pair with supported server-side filters and `--max-items`; `--page-size` only changes request size, not total results. Preserve `NextToken` in projections, report capped results as partial, and resume deliberately when completeness is required. Use `--no-cli-pager` for agent calls; avoid debug output around credentials.
- **Failures are findings**: report authorization (`AccessDeniedException`) or missing role errors directly; do not attempt permission escalation or modify IAM policies without authorization.

## Official Skills

AWS publishes agent skills through the [Agent Toolkit](https://docs.aws.amazon.com/agent-toolkit/latest/userguide/). Review candidates read-only with `aws agent-toolkit list-available-skills` or `search-skills --search-query <topic>`, `get-skill-metadata --skill-name <name>` (version and file list), and `aws agent-toolkit get-skill-file --skill-name <name> --file-path SKILL.md --skill-version <version>`, then install only through the shared [vendor-skill policy](../agent-project/references/vendor-skills.md). Never run `aws configure agent-toolkit --yes`: it installs default skills into every detected agent and configures the AWS MCP server. The workstation sets `AWS_CLI_AGENT_TOOLKIT_HINT_DISABLED=true` to suppress the toolkit prompt.

## Documentation

- [AWS CLI User Guide](https://docs.aws.amazon.com/cli/latest/userguide/) · [AWS CLI Command Reference](https://docs.aws.amazon.com/cli/latest/)
- Releases: [AWS CLI GitHub Releases](https://github.com/aws/aws-cli/releases)
- Companion skills: [infra-as-code](../infra-as-code/SKILL.md) (provisioned infrastructure), [code-security](../code-security/SKILL.md) (IAM audits), [incident-response](../incident-response/SKILL.md) (live outages).

Attribution

fmindfmind
View sourceSee grades on GitHubMore from fmind →
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

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 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', ...

698461 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 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.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, 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.

741 votes
View all in ai-agents →