Skills writing-skills

📦

writing-skills

Name: writing-skills
Author: Dimon94

Content revision r1 Safe ⚙️ External commands📁 Filesystem access⚡ Contains scripts

Create Reliable AI Skills

Skill authors need a repeatable way to write instructions that agents will discover and follow. This skill applies test-driven documentation, pressure scenarios, and concise authoring rules to improve Claude, Codex, and Claude Code skills.

Supports: Claude Codex Code(CC)

🥉 77 Bronze

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/dimon94-writing-skills.md and its manifest at https://skillstore.io/api/skills/dimon94-writing-skills/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.

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/dimon94-writing-skills.md Signed manifest GET /api/skills/dimon94-writing-skills/manifest Signed lockfile GET /api/skills/dimon94-writing-skills/lockfile

Test it

Using "writing-skills". A vague skill description that explains the whole workflow.

Expected outcome:

A shorter trigger-focused description, a list of searchable symptoms, and notes about what moved into the body.

Using "writing-skills". A discipline skill that agents keep bypassing under deadline pressure.

Expected outcome:

Pressure scenarios, observed rationalizations, explicit counters, and a re-test checklist.

Using "writing-skills". A skill with several decision points and confusing prose.

Expected outcome:

A simplified structure with one small flowchart, clearer headings, and supporting files only where needed.

Security Audit

Safe

v10 • 7/9/2026 Open versioned report

I reviewed all static findings. Most are false positives from markdown examples, copied best-practice text, tutorial paths, or broad prose matches; the confirmed risk is the optional render-graphs.js helper, which executes Graphviz and writes generated diagram files. No evidence found of malicious exfiltration, persistence, or instructions that override security review.

Files scanned

2,911

Lines analyzed

Review items

False positives ignored

Capability review items (14)

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

render-graphs.js:18

Node.js child_process module

const { execSync } = require('child_process');

render-graphs.js imports child_process for the optional Graphviz renderer. That is real local command execution capability even though the later command strings are fixed.

High

render-graphs.js:72

Synchronous process execution

return execSync('dot -Tsvg', {

The helper runs dot -Tsvg through execSync and passes DOT content through stdin. Command injection is limited by the fixed command string, but it still executes a local binary.

High

render-graphs.js:112

Synchronous process execution

execSync('which dot', { encoding: 'utf-8' });

The helper runs which dot through execSync before rendering. It is a hardcoded availability check, but it is still shell command execution in an optional script.

Medium

render-graphs.js:120

Node.js fs operations

const markdown = fs.readFileSync(skillFile, 'utf-8');

The helper reads SKILL.md from the user-provided skill directory. The read is intentional, but it should be disclosed because it accesses local files.

Medium

render-graphs.js:132

Node.js fs operations

fs.mkdirSync(outputDir);

The helper creates a diagrams directory inside the supplied skill directory. This is intended output behavior, but it is a real local write.

Medium

render-graphs.js:141

Node.js fs operations

fs.writeFileSync(outputPath, svg);

The helper writes a combined SVG file to the diagrams directory. This is expected renderer output, but it modifies the local filesystem.

Medium

render-graphs.js:146

Node.js fs operations

fs.writeFileSync(dotPath, combined);

The helper writes the combined DOT source for debugging. This is expected renderer output, but it modifies the local filesystem.

Medium

render-graphs.js:157

Node.js fs operations

fs.writeFileSync(outputPath, svg);

The helper writes per-diagram SVG files to the diagrams directory. This is expected renderer output, but it modifies the local filesystem.

Medium

render-graphs.js:120

Synchronous file operations

const markdown = fs.readFileSync(skillFile, 'utf-8');

The helper synchronously reads SKILL.md from the chosen skill directory. The operation is intentional, but it is real local file access.

Medium

render-graphs.js:141

Synchronous file operations

fs.writeFileSync(outputPath, svg);

The helper synchronously writes a combined SVG file. This is an expected artifact, but it is still a local filesystem write.

Medium

render-graphs.js:146

Synchronous file operations

fs.writeFileSync(dotPath, combined);

The helper synchronously writes a combined DOT source file. This is an expected artifact, but it is still a local filesystem write.

Medium

render-graphs.js:157

Synchronous file operations

fs.writeFileSync(outputPath, svg);

The helper synchronously writes rendered SVG files. This is an expected artifact, but it is still a local filesystem write.

Low

render-graphs.js:105

Node.js fs stat operations

if (!fs.existsSync(skillFile)) {

The helper checks whether SKILL.md exists under the user-provided skill directory. This is legitimate local tooling, but it is real filesystem access.

Low

render-graphs.js:131

Node.js fs stat operations

if (!fs.existsSync(outputDir)) {

The helper checks whether the diagrams output directory exists. This is expected for the renderer, but it is still real filesystem access.

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)

⚡ Contains scripts (1)

render-graphs.js:25

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

Copy report link

https://skillstore.io/skills/dimon94-writing-skills/audits/10?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/dimon94-writing-skills/security.svg)](https://skillstore.io/skills/dimon94-writing-skills?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/dimon94-writing-skills?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/dimon94-writing-skills/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/dimon94-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

Dimon94. (2026). writing-skills security audit report (audit version 10) [Author version unspecified]. Skillstore. https://skillstore.io/skills/dimon94-writing-skills/audits/10

BibTeX citation

@techreport{dimon94-dimon94-writing-skills-2026,
  author = {Dimon94},
  title = {writing-skills security audit report (audit version 10)},
  institution = {Skillstore},
  year = {2026},
  number = {10},
  url = {https://skillstore.io/skills/dimon94-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: "Dimon94"
date-released: "2026-07-09"
url: "https://skillstore.io/skills/dimon94-writing-skills/audits/10"
identifiers:
  - type: other
    value: "skillstore:dimon94-writing-skills:audit:10"
    description: "Skillstore immutable audit report identifier"

Compare variants

9 installable variants

Each 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

codingcossack-writing-skills

Skillstore Score 79

Evidence Confidence High

Skillstore usage 8

Updated

2026-08-21

Dimon94 Current

dimon94-writing-skills

Skillstore Score 77

Evidence Confidence High

Skillstore usage 8

Updated

2026-08-21

DYAI2025

dyai2025-writing-skills

Skillstore Score 76

Evidence Confidence Medium

Skillstore usage 6

Updated

2026-08-21

sickn33

sickn33-writing-skills

Skillstore Score 66

Evidence Confidence High

Skillstore usage 16

Updated

2026-08-21

ZhanlinCui

zhanlincui-writing-skills

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 115

Updated

2026-08-21

davila7

davila7-writing-skills

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 8

Updated

2026-08-21

Cycleaddict

cycleaddict-writing-skills

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 8

Updated

2026-08-21

Cygnusfear

cygnusfear-writing-skills

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 5

Updated

2026-08-21

Skillstore Score

Why this score Evidence Confidence: High

Architecture

Maintainability

Content

Community

Spec Compliance

What You Can Build

Write a New Skill

Create a concise skill with clear trigger conditions, useful supporting files, and testable behavior.

Improve Skill Discovery

Rewrite names, descriptions, and keywords so Claude, Codex, or Claude Code can find the skill at the right time.

Verify Agent Compliance

Design pressure scenarios and subagent tests that reveal whether a skill changes behavior under realistic constraints.

Try These Prompts

Draft a Basic Skill

Create a new skill for [task]. Start with the triggering conditions, then draft a concise SKILL.md outline with required frontmatter.

Improve Discovery Text

Review this skill description for discovery quality. Make it start with Use when, remove workflow summaries, and add searchable symptoms.

Design Pressure Tests

Create three pressure scenarios that test whether an agent follows this skill when speed, sunk cost, or authority pressure is present.

Refactor After Failed Tests

Given these failed pressure-test transcripts, identify the rationalizations, update the skill to close each loophole, and define re-test criteria.

Best Practices

Run a baseline pressure test before writing or changing the skill.
Keep the description focused on when to use the skill, not how the workflow works.
Move heavy references or reusable tools into separate files with clear access instructions.

Avoid

Writing a skill from intuition without first observing agent failure.
Using the description field as a compressed workflow that agents may follow instead of reading the skill.
Adding long examples, many languages, or decorative flowcharts that increase context cost without improving behavior.