Skills writing-skills
📦
writing-skills
Content revision r1 High Risk ⚙️ External commands📁 Filesystem access⚡ Contains scripts
Create Tested AI Skills
Skill instructions often fail under pressure or remain untested. This skill helps authors write, test, and refine AI skills before deployment.
Supports: Claude Codex Code(CC)
Stop for confirmation before installing.
Review the plan and obtain explicit user consent before changing files.
Install with my Agent
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Agent request
Review the Skillstore skill "writing-skills" from https://skillstore.io/skills/cycleaddict-writing-skills.md and its manifest at https://skillstore.io/api/skills/cycleaddict-writing-skills/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.
Test it
Using "writing-skills". I need a skill for debugging intermittent authentication failures.
Expected outcome:
- A focused skill trigger that mentions intermittent failures, authentication flows, logs, and reproduction steps.
- A section plan with overview, when to use, diagnostic workflow, examples, and common mistakes.
- A short test scenario that checks whether an agent uses the skill before guessing.
Using "writing-skills". My TDD skill is ignored when the agent is under time pressure.
Expected outcome:
- A pressure-test scenario with a forced choice and realistic consequences.
- A rationalization table that captures why the agent skipped the rule.
- A revised instruction that closes the specific loophole and requires re-testing.
Using "writing-skills". I want to include flowcharts in a skill.
Expected outcome:
- Guidance on using flowcharts only for non-obvious decisions.
- A recommendation to keep reference content in tables or lists.
- A note that diagram rendering requires local Graphviz support.
Security Audit
High Riskv10 • 7/9/2026 Open versioned report
Most Markdown static findings are benign formatting or example text. Confirmed risks remain in hidden-directory skill-discovery examples, the local Graphviz rendering script, and prompt-injection-like test directives.
7
Files scanned
2,911
Lines analyzed
52
Review items
0
False positives ignored
Confirmed security concerns (2)
High
Prompt Injection Attempt Detected
The example prompt says "THIS IS EXTREMELY IMPORTANT. BEFORE ANY TASK, CHECK FOR SKILLS!" inside XML-like tags. If followed outside the test context, it can override task flow and trigger hidden-directory access.
The text uses all-caps urgency, XML-like control tags, and a before-any-task directive. It is framed as a test fixture, which lowers confidence slightly.
Medium
Dual-use LLM persuasion guidance
The persuasion reference explains how authority, commitment, and scarcity increase LLM compliance. It includes ethical limits, but the guidance is reusable for manipulative prompts.
The file directly describes compliance-increasing techniques and their effect on LLMs. The explicit ethical-use section reduces the severity and confidence.
Capability review items (52)
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
Hidden file in home directory
B) Check ~/.claude/skills/debugging/ first (2 min check + 5 min fix = 7 min)
The scenario directs agents to check ~/.claude/skills, a hidden home directory. Although illustrative, it normalizes out-of-workspace hidden directory access.
High
Hidden file in home directory
A) Check ~/.claude/skills/testing/ for async testing skill
The scenario directs agents to check ~/.claude/skills, a hidden home directory. Although illustrative, it normalizes out-of-workspace hidden directory access.
High
Hidden file in home directory
A) Check ~/.claude/skills/ for validation patterns (1-2 min)
The scenario directs agents to check ~/.claude/skills, a hidden home directory. Although illustrative, it normalizes out-of-workspace hidden directory access.
High
Hidden file in home directory
A) Check ~/.claude/skills/coding/ for refactoring guidance
The scenario directs agents to check ~/.claude/skills, a hidden home directory. Although illustrative, it normalizes out-of-workspace hidden directory access.
High
Hidden file in home directory
You have access to skills at `~/.claude/skills/`. Consider
The scenario directs agents to check ~/.claude/skills, a hidden home directory. Although illustrative, it normalizes out-of-workspace hidden directory access.
High
Hidden file in home directory
Before working on any task, check `~/.claude/skills/` for
The scenario directs agents to check ~/.claude/skills, a hidden home directory. Although illustrative, it normalizes out-of-workspace hidden directory access.
High
Hidden file in home directory
Browse: `ls ~/.claude/skills/`
The example directs agents to run commands against ~/.claude/skills, a hidden home directory. This can expose local skill contents without explicit consent.
High
Hidden file in home directory
Search: `grep -r "keyword" ~/.claude/skills/`
The example directs agents to run commands against ~/.claude/skills, a hidden home directory. This can expose local skill contents without explicit consent.
High
Hidden file in home directory
is at `~/.claude/skills/`.
The scenario directs agents to check ~/.claude/skills, a hidden home directory. Although illustrative, it normalizes out-of-workspace hidden directory access.
High
Hidden file in home directory
Browse categories: `ls ~/.claude/skills/`
The example directs agents to run commands against ~/.claude/skills, a hidden home directory. This can expose local skill contents without explicit consent.
High
Hidden file in home directory
Search: `grep -r "keyword" ~/.claude/skills/ --include="SKILL.md"`
The example directs agents to run commands against ~/.claude/skills, a hidden home directory. This can expose local skill contents without explicit consent.
High
Hidden file in home directory
1. Starting work? Check: `ls ~/.claude/skills/[category]/`
The example directs agents to run commands against ~/.claude/skills, a hidden home directory. This can expose local skill contents without explicit consent.
High
Hidden file in home directory
- Browse: `ls ~/.claude/skills/`
The example directs agents to run commands against ~/.claude/skills, a hidden home directory. This can expose local skill contents without explicit consent.
High
Hidden file in home directory
- Search: `grep -r "symptom" ~/.claude/skills/`
The example directs agents to run commands against ~/.claude/skills, a hidden home directory. This can expose local skill contents without explicit consent.
High
Node.js child_process module
const { execSync } = require('child_process');
The script imports child_process, enabling local process execution. Later calls run Graphviz commands from a community-provided script.
High
Synchronous process execution
return execSync('dot -Tsvg', {
The script runs a local Graphviz-related command with execSync. The command string is hardcoded, but bundled external command execution is a real local risk.
High
Synchronous process execution
execSync('which dot', { encoding: 'utf-8' });
The script runs a local Graphviz-related command with execSync. The command string is hardcoded, but bundled external command execution is a real local risk.
High
Path traversal sequence
./render-graphs.js ../some-skill # Each diagram separately
The documented renderer command passes ../some-skill, causing reads and writes outside the current skill directory. That is intentional, but it is real cross-directory filesystem access.
High
Path traversal sequence
./render-graphs.js ../some-skill --combine # All diagrams in one SVG
The documented renderer command passes ../some-skill, causing reads and writes outside the current skill directory. That is intentional, but it is real cross-directory filesystem access.
Medium
Ruby/shell backtick execution
Browse: `ls ~/.claude/skills/`
The example includes ls or grep commands against ~/.claude/skills. These commands enumerate hidden home-directory skill content if followed.
Medium
Ruby/shell backtick execution
Search: `grep -r "keyword" ~/.claude/skills/`
The example includes ls or grep commands against ~/.claude/skills. These commands enumerate hidden home-directory skill content if followed.
Medium
Ruby/shell backtick execution
Browse categories: `ls ~/.claude/skills/`
The example includes ls or grep commands against ~/.claude/skills. These commands enumerate hidden home-directory skill content if followed.
Medium
Ruby/shell backtick execution
Search: `grep -r "keyword" ~/.claude/skills/ --include="SKILL.md"`
The example includes ls or grep commands against ~/.claude/skills. These commands enumerate hidden home-directory skill content if followed.
Medium
Ruby/shell backtick execution
1. Starting work? Check: `ls ~/.claude/skills/[category]/`
The example includes ls or grep commands against ~/.claude/skills. These commands enumerate hidden home-directory skill content if followed.
Medium
Ruby/shell backtick execution
- Browse: `ls ~/.claude/skills/`
The example includes ls or grep commands against ~/.claude/skills. These commands enumerate hidden home-directory skill content if followed.
Medium
Ruby/shell backtick execution
- Search: `grep -r "symptom" ~/.claude/skills/`
The example includes ls or grep commands against ~/.claude/skills. These commands enumerate hidden home-directory skill content if followed.
Medium
Hidden file access
B) Check ~/.claude/skills/debugging/ first (2 min check + 5 min fix = 7 min)
The scenario directs agents to check ~/.claude/skills, a hidden home directory. Although illustrative, it normalizes out-of-workspace hidden directory access.
Medium
Hidden file access
A) Check ~/.claude/skills/testing/ for async testing skill
The scenario directs agents to check ~/.claude/skills, a hidden home directory. Although illustrative, it normalizes out-of-workspace hidden directory access.
Medium
Hidden file access
A) Check ~/.claude/skills/ for validation patterns (1-2 min)
The scenario directs agents to check ~/.claude/skills, a hidden home directory. Although illustrative, it normalizes out-of-workspace hidden directory access.
Medium
Hidden file access
A) Check ~/.claude/skills/coding/ for refactoring guidance
The scenario directs agents to check ~/.claude/skills, a hidden home directory. Although illustrative, it normalizes out-of-workspace hidden directory access.
Medium
Hidden file access
You have access to skills at `~/.claude/skills/`. Consider
The scenario directs agents to check ~/.claude/skills, a hidden home directory. Although illustrative, it normalizes out-of-workspace hidden directory access.
Medium
Hidden file access
Before working on any task, check `~/.claude/skills/` for
The scenario directs agents to check ~/.claude/skills, a hidden home directory. Although illustrative, it normalizes out-of-workspace hidden directory access.
Medium
Hidden file access
Browse: `ls ~/.claude/skills/`
The example directs agents to run commands against ~/.claude/skills, a hidden home directory. This can expose local skill contents without explicit consent.
Medium
Hidden file access
Search: `grep -r "keyword" ~/.claude/skills/`
The example directs agents to run commands against ~/.claude/skills, a hidden home directory. This can expose local skill contents without explicit consent.
Medium
Hidden file access
is at `~/.claude/skills/`.
The scenario directs agents to check ~/.claude/skills, a hidden home directory. Although illustrative, it normalizes out-of-workspace hidden directory access.
Medium
Hidden file access
Browse categories: `ls ~/.claude/skills/`
The example directs agents to run commands against ~/.claude/skills, a hidden home directory. This can expose local skill contents without explicit consent.
Medium
Hidden file access
Search: `grep -r "keyword" ~/.claude/skills/ --include="SKILL.md"`
The example directs agents to run commands against ~/.claude/skills, a hidden home directory. This can expose local skill contents without explicit consent.
Medium
Hidden file access
1. Starting work? Check: `ls ~/.claude/skills/[category]/`
The example directs agents to run commands against ~/.claude/skills, a hidden home directory. This can expose local skill contents without explicit consent.
Medium
Hidden file access
- Browse: `ls ~/.claude/skills/`
The example directs agents to run commands against ~/.claude/skills, a hidden home directory. This can expose local skill contents without explicit consent.
Medium
Hidden file access
- Search: `grep -r "symptom" ~/.claude/skills/`
The example directs agents to run commands against ~/.claude/skills, a hidden home directory. This can expose local skill contents without explicit consent.
Medium
Node.js fs operations
const markdown = fs.readFileSync(skillFile, 'utf-8');
The script reads from and writes to a user-selected skill directory. This is legitimate diagram output, but it modifies local files.
Medium
Node.js fs operations
fs.mkdirSync(outputDir);
The script reads from and writes to a user-selected skill directory. This is legitimate diagram output, but it modifies local files.
Medium
Node.js fs operations
fs.writeFileSync(outputPath, svg);
The script reads from and writes to a user-selected skill directory. This is legitimate diagram output, but it modifies local files.
Medium
Node.js fs operations
fs.writeFileSync(dotPath, combined);
The script reads from and writes to a user-selected skill directory. This is legitimate diagram output, but it modifies local files.
Medium
Node.js fs operations
fs.writeFileSync(outputPath, svg);
The script reads from and writes to a user-selected skill directory. This is legitimate diagram output, but it modifies local files.
Medium
Synchronous file operations
const markdown = fs.readFileSync(skillFile, 'utf-8');
The script reads from and writes to a user-selected skill directory. This is legitimate diagram output, but it modifies local files.
Medium
Synchronous file operations
fs.writeFileSync(outputPath, svg);
The script reads from and writes to a user-selected skill directory. This is legitimate diagram output, but it modifies local files.
Medium
Synchronous file operations
fs.writeFileSync(dotPath, combined);
The script reads from and writes to a user-selected skill directory. This is legitimate diagram output, but it modifies local files.
Medium
Synchronous file operations
fs.writeFileSync(outputPath, svg);
The script reads from and writes to a user-selected skill directory. This is legitimate diagram output, but it modifies local files.
Medium
Ruby/shell backtick execution
**Visualizing for your human partner:** Use `render-graphs.js` in this directory to render a skill's
This line tells users to run the bundled render-graphs.js script. That script invokes Graphviz and writes diagram files locally.
Low
Node.js fs stat operations
if (!fs.existsSync(skillFile)) {
The script reads from and writes to a user-selected skill directory. This is legitimate diagram output, but it modifies local files.
Low
Node.js fs stat operations
if (!fs.existsSync(outputDir)) {
The script reads from and writes to a user-selected skill directory. This is legitimate diagram output, but it modifies local files.
Risk Factors
⚙️ External commands (50)
anthropic-best-practices.md:434-454 anthropic-best-practices.md:476-478 anthropic-best-practices.md:478-482 anthropic-best-practices.md:482-486 anthropic-best-practices.md:486-492 anthropic-best-practices.md:492-496 anthropic-best-practices.md:496-499 anthropic-best-practices.md:534-535 anthropic-best-practices.md:535-541 anthropic-best-practices.md:541-543 anthropic-best-practices.md:565-572 anthropic-best-practices.md:572-576 anthropic-best-practices.md:1082-1085 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 render-graphs.js:18 render-graphs.js:25 render-graphs.js:72 render-graphs.js:112 render-graphs.js:10-22 render-graphs.js:22 render-graphs.js:30-55 render-graphs.js:58-61 render-graphs.js:67-106 render-graphs.js:106-124 render-graphs.js:124-128 render-graphs.js:128-140 render-graphs.js:140-142 render-graphs.js:142-145 render-graphs.js:145-147 render-graphs.js:147-156 render-graphs.js:156-158 render-graphs.js:158-160 render-graphs.js:160-165 SKILL.md:632 SKILL.md:12 SKILL.md:75-80 SKILL.md:80-96 SKILL.md:96
📁 Filesystem access (47)
anthropic-best-practices.md:870 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 render-graphs.js:120 render-graphs.js:132 render-graphs.js:141 render-graphs.js:146 render-graphs.js:157 render-graphs.js:105 render-graphs.js:131 render-graphs.js:120 render-graphs.js:141 render-graphs.js:146 render-graphs.js:157 render-graphs.js:96 render-graphs.js:97 SKILL.md:320 SKILL.md:321 SKILL.md:12 SKILL.md:12 testing-skills-with-subagents.md:148
⚡ Contains scripts (1)
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.
Copy report link
https://skillstore.io/skills/cycleaddict-writing-skills/audits/10?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/cycleaddict-writing-skills?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/cycleaddict-writing-skills?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/cycleaddict-writing-skills/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/cycleaddict-writing-skills.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
Cycleaddict. (2026). writing-skills security audit report (audit version 10) [Author version unspecified]. Skillstore. https://skillstore.io/skills/cycleaddict-writing-skills/audits/10BibTeX citation
@techreport{cycleaddict-cycleaddict-writing-skills-2026,
author = {Cycleaddict},
title = {writing-skills security audit report (audit version 10)},
institution = {Skillstore},
year = {2026},
number = {10},
url = {https://skillstore.io/skills/cycleaddict-writing-skills/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: "writing-skills security audit report (audit version 10)"
version: "unspecified"
type: report
authors:
- name: "Cycleaddict"
date-released: "2026-07-09"
url: "https://skillstore.io/skills/cycleaddict-writing-skills/audits/10"
identifiers:
- type: other
value: "skillstore:cycleaddict-writing-skills:audit:10"
description: "Skillstore immutable audit report identifier"
Compare variants
9 installable variantsEach author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.
Why this variant is first
Higher Skillstore usage
Author / source Skillstore Score Evidence Confidence Skillstore usage Updated
obra Recommended
obra-writing-skills
Skillstore Score 79
Evidence Confidence High
Skillstore usage 12
Updated
2026-08-21
codingcossack-writing-skills
Skillstore Score 79
Evidence Confidence High
Skillstore usage 8
Updated
2026-08-21
dimon94-writing-skills
Skillstore Score 77
Evidence Confidence High
Skillstore usage 8
Updated
2026-08-21
dyai2025-writing-skills
Skillstore Score 76
Evidence Confidence Medium
Skillstore usage 6
Updated
2026-08-21
sickn33-writing-skills
Skillstore Score 66
Evidence Confidence High
Skillstore usage 16
Updated
2026-08-21
zhanlincui-writing-skills
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 115
Updated
2026-08-21
davila7-writing-skills
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 8
Updated
2026-08-21
Cycleaddict Current
cycleaddict-writing-skills
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 8
Updated
2026-08-21
cygnusfear-writing-skills
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 5
Updated
2026-08-21
Skillstore Score
Why this score Evidence Confidence: Medium 55
Architecture
85
Maintainability
87
Content
71
Community
78
Spec Compliance
What You Can Build
Draft a New Skill
Create a concise SKILL.md with clear triggers, structure, examples, and supporting-file boundaries.
Test Compliance Under Pressure
Design subagent scenarios that show whether an instruction survives time pressure, authority pressure, and sunk cost.
Refine Skill Documentation
Improve naming, descriptions, cross-references, diagrams, and deployment checks for existing AI skills.
Try These Prompts
Create a Skill Outline
Help me outline a new skill for [task]. Include when to use it, when not to use it, key sections, and one example.
Review an Existing Skill
Review this SKILL.md for clarity, trigger quality, token efficiency, reference structure, and likely discovery problems.
Design Pressure Tests
Create three pressure scenarios for this skill. Combine time pressure, authority pressure, sunk cost, and explicit choices.
Harden a Skill After Failure
Given these failed test transcripts, identify rationalizations, rewrite the weak sections, and define a re-test plan.
Best Practices
- Run a baseline pressure scenario before writing or changing a discipline skill.
- Keep description fields focused on when to use the skill, not the full workflow.
- Move long references and scripts into separate files with clear links from SKILL.md.
Avoid
- Do not create skills for one-off project notes or standard practices.
- Do not hide mandatory workflow steps inside broad description text.
- Do not include command examples that access hidden home directories without consent.
Frequently Asked Questions
What is this skill for?
It helps authors create, test, and refine AI skills before deployment.
Does it write skills automatically?
It provides structure and review guidance. The user still decides the final content.
Why does it use TDD language?
It maps test-first development to documentation. Authors verify behavior before trusting a skill.
Can it test reference-only skills?
Yes, but the guidance focuses more on discipline skills that agents may rationalize away.
Does the graph renderer run automatically?
No. The bundled renderer is a local script that requires explicit execution and Graphviz.
Is it suitable for Claude, Codex, and Claude Code?
Yes. The skill declares support for Claude, Codex, and Claude Code workflows.
Developer Details
Author
CycleaddictLicense
MIT
Skillstore revision
r1
Version notice
The author did not declare a version.
Ref
0519034dad657fb1f7706e0550e962beeda73fdf
Maintenance freshness
7/18/2026
Usage
4 downloads · 237 views