Skip to content
Back to skills

System Prompts

ASecurity

The handle is `curl` (or equivalent). The evidence is the response.

  • 12,835 stars
  • 0 votes
  • 0 copies
  • 2 views
  • Added September 3, 2026
ai-agentsgobashapi

Works with

  • cli
  • api

Security analysis

A100/100

Pro scans all 21 files and shows the line behind each finding

Scanned September 3, 2026

npx -y skills add Piebald-AI/claude-code-system-prompts --skill system-prompts --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of System Prompts?

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

Security grade badge for System Prompts
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/piebald-ai-system-prompts-claude-code-system-prompts/badge)](https://www.skillsdirectory.com/skills/piebald-ai-system-prompts-claude-code-system-prompts)

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: "Skill: Verify server/API changes (example for Verify skill)"
description: "Example workflow for verifying a server/API change, as part of the Verify skill"
ccVersion: "2.1.246"
-->
# Verifying a server/API change

The handle is `curl` (or equivalent). The evidence is the response.

## Pattern

1. Start the server (background, with a readiness poll - see below)
2. `curl` the route the diff touches, with inputs that hit the changed branch
3. Capture the full response (status + headers + body)
4. Compare to expected

## Lifecycle

If there's a run-skill it handles this. If not:

```bash
<start-command> &> /tmp/server.log &
SERVER_PID=$!
for i in {1..30}; do curl -sf localhost:PORT/health >/dev/null && break; sleep 1; done
# ... your curls ...
kill $SERVER_PID
```

No readiness endpoint? Poll the route you're about to test until it
stops returning connection-refused, then add a beat.

## Worked example

**Diff:** adds a `Retry-After` header to 429 responses in `rateLimit.ts`.
**Claim (PR body):** "clients can now back off correctly."

**Inference:** hitting the rate limit should now return `Retry-After: <n>`
in the response headers. It didn't before.

**Plan:**
1. Start server
2. Hit the rate-limited endpoint enough times to trigger 429
3. Check the 429 response has `Retry-After` header
4. Check the value is a positive integer

**Execute:**
```bash
# trigger the limit - 10 fast requests, limit is 5/sec per the diff
for i in {1..10}; do curl -s -o /dev/null -w "%{http_code}\n" localhost:3000/api/thing; done
# -> 200 200 200 200 200 429 429 429 429 429

# capture the 429 headers
curl -si localhost:3000/api/thing | head -20
# -> HTTP/1.1 429 Too Many Requests
# -> Retry-After: 12
# -> ...
```

**Verdict:** PASS - `Retry-After: 12` present, positive integer.

## What FAIL looks like

- Header absent -> the diff didn't take effect, or you're not actually
  hitting the 429 path (check the status code first)
- Header present but value is `NaN` / `undefined` / negative -> the
  logic is wrong
- You got 200s all the way through -> you never triggered the changed
  path. Tighten the request burst or check the rate limit config.

Files in this skill

  • agent-prompt-agent-hook.md931 B
  • agent-prompt-artifact-comment-thread-analyst.md2.4 KB
  • agent-prompt-artifact-editor-thread-follow-up.md1.2 KB
  • agent-prompt-auto-mode-rule-reviewer.md1.4 KB
  • agent-prompt-away-summary-generation.md463 B
  • agent-prompt-background-agent-state-classifier.md16.7 KB
  • agent-prompt-background-job-agent-instructions.md2.2 KB
  • agent-prompt-batch-slash-command.md4.4 KB
  • agent-prompt-claude-code-guide.md1.3 KB
  • agent-prompt-claude-guide-agent.md9.5 KB
  • agent-prompt-claude-md-creation.md2 KB
  • agent-prompt-code-review-gitlab-comment-posting.md1.1 KB
  • agent-prompt-code-review-inline-gap-sweep-phase.md479 B
  • agent-prompt-code-review-minimal-mode.md1.8 KB
  • agent-prompt-code-review-part-1-base-finder-angles.md701 B
  • agent-prompt-code-review-part-10-reportfindings-output-format.md1.2 KB
  • agent-prompt-code-review-part-2-low-effort-minimum-findings-mode.md2.2 KB
  • agent-prompt-code-review-part-2-low-effort-mode.md1.9 KB
  • agent-prompt-code-review-part-3-extra-high-and-maximum-effort-modes.md1.5 KB
  • agent-prompt-code-review-part-4-three-state-verification-phase.md584 B

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.