writing-skills
Create Better Agent Skills
Agent skills often fail because their triggers, structure, or tests are unclear. This skill provides templates, standards, and review guidance for Claude, Codex, and Claude Code.
Install with my Agent
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Review the Skillstore skill "writing-skills" from https://skillstore.io/skills/sickn33-writing-skills.md and its manifest at https://skillstore.io/api/skills/sickn33-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.
Test it
Using "writing-skills". I need a skill for debugging flaky async tests.
Expected outcome:
Recommended structure: a Tier 1 technique skill. Include symptoms such as timeout and race condition, then add before-and-after examples.
Using "writing-skills". My skill is not loaded when users ask relevant questions.
Expected outcome:
Likely issue: discovery metadata is too broad or workflow-focused. Rewrite the description to start with Use when and include exact symptoms.
Using "writing-skills". I want a strict TDD skill that agents cannot bypass.
Expected outcome:
Use a discipline skill. Add explicit no-exception rules, a rationalization table, red flags, and tests under time pressure.
Security Audit
Medium RiskMost static findings are false positives from Markdown examples, inline code, and documented configuration paths. The bundled Graphviz helper uses hardcoded commands and visible file writes, with no evidence of command injection, exfiltration, persistence, or prompt-injection text. A semantic concern remains because the skill teaches dual-use persuasion techniques for increasing agent compliance.
Confirmed security concerns (1)
Risk Factors
⚙️ External commands (57)
📁 Filesystem access (32)
⚡ Contains scripts (1)
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/sickn33-writing-skills/audits/5?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/sickn33-writing-skills?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/sickn33-writing-skills?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/sickn33-writing-skills/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/sickn33-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
sickn33. (2026). writing-skills security audit report (audit version 5) [Author version unspecified]. Skillstore. https://skillstore.io/skills/sickn33-writing-skills/audits/5BibTeX citation
@techreport{sickn33-sickn33-writing-skills-2026,
author = {sickn33},
title = {writing-skills security audit report (audit version 5)},
institution = {Skillstore},
year = {2026},
number = {5},
url = {https://skillstore.io/skills/sickn33-writing-skills/audits/5},
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 5)"
version: "unspecified"
type: report
authors:
- name: "sickn33"
date-released: "2026-07-07"
url: "https://skillstore.io/skills/sickn33-writing-skills/audits/5"
identifiers:
- type: other
value: "skillstore:sickn33-writing-skills:audit:5"
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
obra-writing-skills
2026-09-09
codingcossack-writing-skills
2026-09-09
dimon94-writing-skills
2026-09-09
dyai2025-writing-skills
2026-09-09
sickn33-writing-skills
2026-09-09
zhanlincui-writing-skills
2026-09-09
davila7-writing-skills
2026-09-09
cycleaddict-writing-skills
2026-09-09
cygnusfear-writing-skills
2026-09-09
Skillstore Score
Why this score Evidence Confidence: HighWhat You Can Build
Create a New Skill
Use the decision tree and templates to draft a focused skill with clear triggers and structure.
Improve Skill Discovery
Rewrite descriptions, tags, and metadata so agents load the right skill at the right time.
Standardize Team Skills
Apply shared naming, testing, and documentation rules across a team skill library.
Try These Prompts
Help me choose the right structure for a new agent skill. It covers [scope], uses [tools], and needs [references].
Create metadata for a skill about [topic]. Include a Use when description, trigger keywords, category, and concise name.
Review this skill draft for clarity, trigger quality, file structure, and agent compliance risks. Suggest concrete edits.
Create realistic tests for this agent skill. Include success cases, failure cases, rationalization pressure, and expected behavior.
Best Practices
- Start descriptions with clear trigger conditions instead of workflow summaries.
- Move detailed references out of SKILL.md and load them only when needed.
- Test skills with realistic prompts that include ambiguity and deadline pressure.
Avoid
- Writing long monolithic skills that consume context before details are needed.
- Using generic names or descriptions that do not match real user symptoms.
- Adding strict rules without testing how agents rationalize around them.