Skills testing-skills-with-subagents
📦

testing-skills-with-subagents

Content revision r1 High Risk ⚙️ External commands📁 Filesystem access

Test Skills With Subagents

Process skills often fail when agents face time pressure, authority pressure, or sunk cost. This skill gives a repeatable subagent test workflow to expose failures and improve instructions.

Supports: Claude Codex Code(CC)
⚠️ 38 Poor

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request
Review the Skillstore skill "testing-skills-with-subagents" from https://skillstore.io/skills/dyai2025-testing-skills-with-subagents.md and its manifest at https://skillstore.io/api/skills/dyai2025-testing-skills-with-subagents/manifest. Verify the artifact. Stop and obtain explicit user consent before installing or changing files.

Your Agent should still show its plan and request any confirmation required by the security policy.

Agent-readable resources

Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.

Markdown detail GET /skills/dyai2025-testing-skills-with-subagents.md Signed manifest GET /api/skills/dyai2025-testing-skills-with-subagents/manifest Signed lockfile GET /api/skills/dyai2025-testing-skills-with-subagents/lockfile

Test it

Using "testing-skills-with-subagents". A TDD skill fails when agents choose tests after implementation.

Expected outcome:

  • Baseline: agent chose the fastest path under time pressure.
  • Counter: add a rule that order is part of the requirement.
  • Retest: agent must restart with tests first.

Using "testing-skills-with-subagents". A CLAUDE.md reminder does not make agents check installed skills.

Expected outcome:

  • Variant comparison shows soft suggestions fail under urgency.
  • Directive wording improves discovery but feels rigid.
  • Process wording balances clarity and reuse.

Security Audit

High Risk
v10 • 7/9/2026 Open versioned report

Most command alerts are markdown examples, not executable code. Repeated ~/.claude/skills access is a real workspace-boundary risk. The files also include prompt-pressure templates that can steer agent behavior.

2
Files scanned
578
Lines analyzed
35
Review items
0
False positives ignored

Confirmed security concerns (2)

High
examples/CLAUDE_MD_TESTING.md:100-112
Prompt Injection Attempt Detected
The example instruction block says "THIS IS EXTREMELY IMPORTANT. BEFORE ANY TASK, CHECK FOR SKILLS!" and frames noncompliance as failure. If copied into active agent context, it can override normal task judgment and force tool behavior.
The language is explicitly designed to steer agent behavior with urgency and failure framing. Confidence is not higher because it appears inside a documentation variant used for testing.
Medium
SKILL.md:157-164examples/CLAUDE_MD_TESTING.md:8-19
Deceptive Agent Test Framing
The skill tells authors to present scenarios as real work and to make the agent believe it is not a quiz. This is useful for testing, but unsafe if used outside controlled subagents.
The file directly instructs users to make agents believe a test is real work. The testing context reduces severity, but the social-engineering pattern is clear.
Capability review items (35)

These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.

High
examples/CLAUDE_MD_TESTING.md:16
Hidden file in home directory
B) Check ~/.claude/skills/debugging/ first (2 min check + 5 min fix = 7 min)
The scenario or template directs agents to inspect ~/.claude/skills under the user home directory. This crosses the workspace boundary and can expose private installed skill content.
High
examples/CLAUDE_MD_TESTING.md:34
Hidden file in home directory
A) Check ~/.claude/skills/testing/ for async testing skill
The scenario or template directs agents to inspect ~/.claude/skills under the user home directory. This crosses the workspace boundary and can expose private installed skill content.
High
examples/CLAUDE_MD_TESTING.md:46
Hidden file in home directory
A) Check ~/.claude/skills/ for validation patterns (1-2 min)
The scenario or template directs agents to inspect ~/.claude/skills under the user home directory. This crosses the workspace boundary and can expose private installed skill content.
High
examples/CLAUDE_MD_TESTING.md:60
Hidden file in home directory
A) Check ~/.claude/skills/coding/ for refactoring guidance
The scenario or template directs agents to inspect ~/.claude/skills under the user home directory. This crosses the workspace boundary and can expose private installed skill content.
High
examples/CLAUDE_MD_TESTING.md:73
Hidden file in home directory
You have access to skills at `~/.claude/skills/`. Consider
The scenario or template directs agents to inspect ~/.claude/skills under the user home directory. This crosses the workspace boundary and can expose private installed skill content.
High
examples/CLAUDE_MD_TESTING.md:81
Hidden file in home directory
Before working on any task, check `~/.claude/skills/` for
The scenario or template directs agents to inspect ~/.claude/skills under the user home directory. This crosses the workspace boundary and can expose private installed skill content.
High
examples/CLAUDE_MD_TESTING.md:84
Hidden file in home directory
Browse: `ls ~/.claude/skills/`
The scenario or template directs agents to inspect ~/.claude/skills under the user home directory. This crosses the workspace boundary and can expose private installed skill content.
High
examples/CLAUDE_MD_TESTING.md:85
Hidden file in home directory
Search: `grep -r "keyword" ~/.claude/skills/`
The scenario or template directs agents to inspect ~/.claude/skills under the user home directory. This crosses the workspace boundary and can expose private installed skill content.
High
examples/CLAUDE_MD_TESTING.md:92
Hidden file in home directory
is at `~/.claude/skills/`.
The scenario or template directs agents to inspect ~/.claude/skills under the user home directory. This crosses the workspace boundary and can expose private installed skill content.
High
examples/CLAUDE_MD_TESTING.md:94
Hidden file in home directory
Browse categories: `ls ~/.claude/skills/`
The scenario or template directs agents to inspect ~/.claude/skills under the user home directory. This crosses the workspace boundary and can expose private installed skill content.
High
examples/CLAUDE_MD_TESTING.md:95
Hidden file in home directory
Search: `grep -r "keyword" ~/.claude/skills/ --include="SKILL.md"`
The scenario or template directs agents to inspect ~/.claude/skills under the user home directory. This crosses the workspace boundary and can expose private installed skill content.
High
examples/CLAUDE_MD_TESTING.md:107
Hidden file in home directory
1. Starting work? Check: `ls ~/.claude/skills/[category]/`
The scenario or template directs agents to inspect ~/.claude/skills under the user home directory. This crosses the workspace boundary and can expose private installed skill content.
High
examples/CLAUDE_MD_TESTING.md:122
Hidden file in home directory
- Browse: `ls ~/.claude/skills/`
The scenario or template directs agents to inspect ~/.claude/skills under the user home directory. This crosses the workspace boundary and can expose private installed skill content.
High
examples/CLAUDE_MD_TESTING.md:123
Hidden file in home directory
- Search: `grep -r "symptom" ~/.claude/skills/`
The scenario or template directs agents to inspect ~/.claude/skills under the user home directory. This crosses the workspace boundary and can expose private installed skill content.
Medium
examples/CLAUDE_MD_TESTING.md:84-85
Ruby/shell backtick execution
Browse: `ls ~/.claude/skills/`
The documentation examples encourage running hardcoded ls or grep commands against ~/.claude/skills. The commands are read-only, but they still ask the agent to execute shell commands outside the workspace.
Medium
examples/CLAUDE_MD_TESTING.md:85-86
Ruby/shell backtick execution
Search: `grep -r "keyword" ~/.claude/skills/`
The documentation examples encourage running hardcoded ls or grep commands against ~/.claude/skills. The commands are read-only, but they still ask the agent to execute shell commands outside the workspace.
Medium
examples/CLAUDE_MD_TESTING.md:94-95
Ruby/shell backtick execution
Browse categories: `ls ~/.claude/skills/`
The documentation examples encourage running hardcoded ls or grep commands against ~/.claude/skills. The commands are read-only, but they still ask the agent to execute shell commands outside the workspace.
Medium
examples/CLAUDE_MD_TESTING.md:95-97
Ruby/shell backtick execution
Search: `grep -r "keyword" ~/.claude/skills/ --include="SKILL.md"`
The documentation examples encourage running hardcoded ls or grep commands against ~/.claude/skills. The commands are read-only, but they still ask the agent to execute shell commands outside the workspace.
Medium
examples/CLAUDE_MD_TESTING.md:107-113
Ruby/shell backtick execution
1. Starting work? Check: `ls ~/.claude/skills/[category]/`
The documentation examples encourage running hardcoded ls or grep commands against ~/.claude/skills. The commands are read-only, but they still ask the agent to execute shell commands outside the workspace.
Medium
examples/CLAUDE_MD_TESTING.md:122-123
Ruby/shell backtick execution
- Browse: `ls ~/.claude/skills/`
The documentation examples encourage running hardcoded ls or grep commands against ~/.claude/skills. The commands are read-only, but they still ask the agent to execute shell commands outside the workspace.
Medium
examples/CLAUDE_MD_TESTING.md:123-132
Ruby/shell backtick execution
- Search: `grep -r "symptom" ~/.claude/skills/`
The documentation examples encourage running hardcoded ls or grep commands against ~/.claude/skills. The commands are read-only, but they still ask the agent to execute shell commands outside the workspace.
Medium
examples/CLAUDE_MD_TESTING.md:16
Hidden file access
B) Check ~/.claude/skills/debugging/ first (2 min check + 5 min fix = 7 min)
The scenario or template directs agents to inspect ~/.claude/skills under the user home directory. This crosses the workspace boundary and can expose private installed skill content.
Medium
examples/CLAUDE_MD_TESTING.md:34
Hidden file access
A) Check ~/.claude/skills/testing/ for async testing skill
The scenario or template directs agents to inspect ~/.claude/skills under the user home directory. This crosses the workspace boundary and can expose private installed skill content.
Medium
examples/CLAUDE_MD_TESTING.md:46
Hidden file access
A) Check ~/.claude/skills/ for validation patterns (1-2 min)
The scenario or template directs agents to inspect ~/.claude/skills under the user home directory. This crosses the workspace boundary and can expose private installed skill content.
Medium
examples/CLAUDE_MD_TESTING.md:60
Hidden file access
A) Check ~/.claude/skills/coding/ for refactoring guidance
The scenario or template directs agents to inspect ~/.claude/skills under the user home directory. This crosses the workspace boundary and can expose private installed skill content.
Medium
examples/CLAUDE_MD_TESTING.md:73
Hidden file access
You have access to skills at `~/.claude/skills/`. Consider
The scenario or template directs agents to inspect ~/.claude/skills under the user home directory. This crosses the workspace boundary and can expose private installed skill content.
Medium
examples/CLAUDE_MD_TESTING.md:81
Hidden file access
Before working on any task, check `~/.claude/skills/` for
The scenario or template directs agents to inspect ~/.claude/skills under the user home directory. This crosses the workspace boundary and can expose private installed skill content.
Medium
examples/CLAUDE_MD_TESTING.md:84
Hidden file access
Browse: `ls ~/.claude/skills/`
The scenario or template directs agents to inspect ~/.claude/skills under the user home directory. This crosses the workspace boundary and can expose private installed skill content.
Medium
examples/CLAUDE_MD_TESTING.md:85
Hidden file access
Search: `grep -r "keyword" ~/.claude/skills/`
The scenario or template directs agents to inspect ~/.claude/skills under the user home directory. This crosses the workspace boundary and can expose private installed skill content.
Medium
examples/CLAUDE_MD_TESTING.md:92
Hidden file access
is at `~/.claude/skills/`.
The scenario or template directs agents to inspect ~/.claude/skills under the user home directory. This crosses the workspace boundary and can expose private installed skill content.
Medium
examples/CLAUDE_MD_TESTING.md:94
Hidden file access
Browse categories: `ls ~/.claude/skills/`
The scenario or template directs agents to inspect ~/.claude/skills under the user home directory. This crosses the workspace boundary and can expose private installed skill content.
Medium
examples/CLAUDE_MD_TESTING.md:95
Hidden file access
Search: `grep -r "keyword" ~/.claude/skills/ --include="SKILL.md"`
The scenario or template directs agents to inspect ~/.claude/skills under the user home directory. This crosses the workspace boundary and can expose private installed skill content.
Medium
examples/CLAUDE_MD_TESTING.md:107
Hidden file access
1. Starting work? Check: `ls ~/.claude/skills/[category]/`
The scenario or template directs agents to inspect ~/.claude/skills under the user home directory. This crosses the workspace boundary and can expose private installed skill content.
Medium
examples/CLAUDE_MD_TESTING.md:122
Hidden file access
- Browse: `ls ~/.claude/skills/`
The scenario or template directs agents to inspect ~/.claude/skills under the user home directory. This crosses the workspace boundary and can expose private installed skill content.
Medium
examples/CLAUDE_MD_TESTING.md:123
Hidden file access
- Search: `grep -r "symptom" ~/.claude/skills/`
The scenario or template directs agents to inspect ~/.claude/skills under the user home directory. This crosses the workspace boundary and can expose private installed skill content.

Risk Factors

⚙️ External commands (41)
examples/CLAUDE_MD_TESTING.md:47-50 examples/CLAUDE_MD_TESTING.md:73-75 examples/CLAUDE_MD_TESTING.md:81-84 examples/CLAUDE_MD_TESTING.md:84-85 examples/CLAUDE_MD_TESTING.md:85-86 examples/CLAUDE_MD_TESTING.md:92-94 examples/CLAUDE_MD_TESTING.md:94-95 examples/CLAUDE_MD_TESTING.md:95-97 examples/CLAUDE_MD_TESTING.md:97-107 examples/CLAUDE_MD_TESTING.md:107-113 examples/CLAUDE_MD_TESTING.md:122-123 examples/CLAUDE_MD_TESTING.md:123-132 examples/CLAUDE_MD_TESTING.md:132-133 SKILL.md:62-75 SKILL.md:75-102 SKILL.md:102-104 SKILL.md:104-108 SKILL.md:108-111 SKILL.md:111-115 SKILL.md:115-126 SKILL.md:126-151 SKILL.md:151-157 SKILL.md:157-162 SKILL.md:162-188 SKILL.md:188-190 SKILL.md:190-194 SKILL.md:194-202 SKILL.md:202-207 SKILL.md:207-211 SKILL.md:211-215 SKILL.md:215-220 SKILL.md:220-224 SKILL.md:224-226 SKILL.md:226-247 SKILL.md:247-252 SKILL.md:252-288 SKILL.md:288-292 SKILL.md:292-295 SKILL.md:295-299 SKILL.md:299-302 SKILL.md:302-307
📁 Filesystem access (29)
examples/CLAUDE_MD_TESTING.md:16 examples/CLAUDE_MD_TESTING.md:34 examples/CLAUDE_MD_TESTING.md:46 examples/CLAUDE_MD_TESTING.md:60 examples/CLAUDE_MD_TESTING.md:73 examples/CLAUDE_MD_TESTING.md:81 examples/CLAUDE_MD_TESTING.md:84 examples/CLAUDE_MD_TESTING.md:85 examples/CLAUDE_MD_TESTING.md:92 examples/CLAUDE_MD_TESTING.md:94 examples/CLAUDE_MD_TESTING.md:95 examples/CLAUDE_MD_TESTING.md:107 examples/CLAUDE_MD_TESTING.md:122 examples/CLAUDE_MD_TESTING.md:123 examples/CLAUDE_MD_TESTING.md:16 examples/CLAUDE_MD_TESTING.md:34 examples/CLAUDE_MD_TESTING.md:46 examples/CLAUDE_MD_TESTING.md:60 examples/CLAUDE_MD_TESTING.md:73 examples/CLAUDE_MD_TESTING.md:81 examples/CLAUDE_MD_TESTING.md:84 examples/CLAUDE_MD_TESTING.md:85 examples/CLAUDE_MD_TESTING.md:92 examples/CLAUDE_MD_TESTING.md:94 examples/CLAUDE_MD_TESTING.md:95 examples/CLAUDE_MD_TESTING.md:107 examples/CLAUDE_MD_TESTING.md:122 examples/CLAUDE_MD_TESTING.md:123 SKILL.md:151
Audited by: codex View Audit History →
Share & cite this report

Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.

Open versioned report
Security Assessment

Copy report link

https://skillstore.io/skills/dyai2025-testing-skills-with-subagents/audits/10?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/dyai2025-testing-skills-with-subagents/security.svg)](https://skillstore.io/skills/dyai2025-testing-skills-with-subagents?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/dyai2025-testing-skills-with-subagents?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/dyai2025-testing-skills-with-subagents/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/dyai2025-testing-skills-with-subagents.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>
Academic citations (APA · BibTeX · CFF)

APA citation

DYAI2025. (2026). testing-skills-with-subagents security audit report (audit version 10) [Author version unspecified]. Skillstore. https://skillstore.io/skills/dyai2025-testing-skills-with-subagents/audits/10

BibTeX citation

@techreport{dyai2025-dyai2025-testing-skills-with-subagents-2026, author = {DYAI2025}, title = {testing-skills-with-subagents security audit report (audit version 10)}, institution = {Skillstore}, year = {2026}, number = {10}, url = {https://skillstore.io/skills/dyai2025-testing-skills-with-subagents/audits/10}, note = {Author version unspecified} }

CITATION.cff

cff-version: 1.2.0 message: "If you use this Skill, cite its author and this versioned security audit report." title: "testing-skills-with-subagents security audit report (audit version 10)" version: "unspecified" type: report authors: - name: "DYAI2025" date-released: "2026-07-09" url: "https://skillstore.io/skills/dyai2025-testing-skills-with-subagents/audits/10" identifiers: - type: other value: "skillstore:dyai2025-testing-skills-with-subagents:audit:10" description: "Skillstore immutable audit report identifier"

Skillstore Score

Why this score Evidence Confidence: Medium
55
Architecture
85
Maintainability
85
Content
72
Community
91
Spec Compliance

What You Can Build

Validate a New Skill

Test a discipline-enforcing skill before publishing it.

Compare Instruction Variants

Measure which documentation variant improves agent compliance.

Review Community Skills

Assess whether a skill handles pressure without unsafe behavior.

Try These Prompts

Run a Baseline Test 
Create one pressure scenario for this skill. Run it without the skill, then list the agent choice and rationalization.
Compare Documentation Variants 
Test two instruction variants with the same scenario. Report which variant improved skill discovery and why.
Close a Rationalization Loop 
Use the captured rationalization to revise the skill. Add one explicit counter and one red flag.
Design a Full Test Campaign 
Build a RED, GREEN, REFACTOR campaign for this skill with three pressure scenarios, success criteria, and retest steps.

Best Practices

  • Run a baseline before editing the skill.
  • Use the same scenario when comparing variants.
  • Record exact rationalizations before writing fixes.

Avoid

  • Skipping RED because the intended rule seems obvious.
  • Testing only calm scenarios without real pressure.
  • Changing many instructions before isolating the failure.

Frequently Asked Questions

What problem does this skill solve?
It helps authors prove that process skills work when agents have reasons to skip them.
Does it run tests automatically?
No. It describes a manual test workflow for subagents and documentation.
Which skills benefit most?
Skills that enforce discipline, such as TDD, review, or required workflow steps.
Can it be used with Codex?
Yes. The workflow can guide Codex, Claude, and Claude Code sessions.
Why use pressure scenarios?
They reveal rationalizations that simple knowledge checks do not expose.
What is the main safety concern?
The examples use persuasive prompts, so tests should run only in controlled subagent contexts.

Developer Details

Author

DYAI2025

License

MIT

Skillstore revision

r1

Version notice

The author did not declare a version.

Repository

https://github.com/DYAI2025/Stoppclock-page/tree/main/stoppclock_speckit/.claude/commands/skills/testing-skills-with-subagents

Ref

0519034dad657fb1f7706e0550e962beeda73fdf

Maintenance freshness

7/18/2026

Usage

6 downloads · 341 views

File structure

📁 examples/

📄 CLAUDE_MD_TESTING.md

📄 SKILL.md

📄 SKILL.zip