Skills writing-great-skills
📦

writing-great-skills

Content revision r2 Safe ⚙️ External commands

Write Predictable AI Skills

AI skills can become difficult to invoke, follow, and maintain. This reference provides a clear vocabulary and practical principles for predictable skill design.

Supports: Claude Codex Code(CC)
🥉 78 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-great-skills" from https://skillstore.io/skills/mattpocock-writing-great-skills.md and its manifest at https://skillstore.io/api/skills/mattpocock-writing-great-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/mattpocock-writing-great-skills.md Signed manifest GET /api/skills/mattpocock-writing-great-skills/manifest Signed lockfile GET /api/skills/mattpocock-writing-great-skills/lockfile

Test it

Using "writing-great-skills". Choose invocation for a skill that only runs when a person requests a release checklist.

Expected outcome:

Recommendation: user invocation. The person already controls every invocation, so model discovery would add context load without improving reach.

Using "writing-great-skills". Review a long skill containing setup instructions, optional deployment guidance, and repeated definitions.

Expected outcome:

  • Keep setup steps in the main skill and add checkable completion criteria.
  • Move optional deployment guidance behind a clearly worded context pointer.
  • Keep each repeated definition in one authoritative location.

Using "writing-great-skills". Diagnose why an agent rushes through research before writing.

Expected outcome:

The research step has a vague completion criterion and visible later steps. Define an exhaustive evidence target before considering a sequence split.

Security Audit

Safe
v5 • 7/23/2026 Open versioned report

All seven static findings are false positives caused by Markdown backticks around links and filenames. The files contain guidance only, with no executable commands or malicious intent.

2
Files scanned
286
Lines analyzed
0
Review items
0
False positives ignored

Risk Factors

⚙️ External commands (7)
SKILL.md:9 SKILL.md:15 SKILL.md:16 SKILL.md:34 SKILL.md:35 SKILL.md:36 SKILL.md:42
No confirmed security findings were detected by the latest completed static and semantic audit. This does not prove the skill has no side effects.
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/mattpocock-writing-great-skills/audits/5?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

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

HTML badge

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

Embed card

<iframe src="https://skillstore.io/embed/skills/mattpocock-writing-great-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

mattpocock. (2026). writing-great-skills security audit report (audit version 5) [Author version unspecified]. Skillstore. https://skillstore.io/skills/mattpocock-writing-great-skills/audits/5

BibTeX citation

@techreport{mattpocock-mattpocock-writing-great-skills-2026, author = {mattpocock}, title = {writing-great-skills security audit report (audit version 5)}, institution = {Skillstore}, year = {2026}, number = {5}, url = {https://skillstore.io/skills/mattpocock-writing-great-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-great-skills security audit report (audit version 5)" version: "unspecified" type: report authors: - name: "mattpocock" date-released: "2026-07-23" url: "https://skillstore.io/skills/mattpocock-writing-great-skills/audits/5" identifiers: - type: other value: "skillstore:mattpocock-writing-great-skills:audit:5" description: "Skillstore immutable audit report identifier"

Skillstore Score

Why this score Evidence Confidence: High
55
Architecture
85
Maintainability
87
Content
71
Community
83
Spec Compliance

What You Can Build

Draft a First Skill

Structure invocation, steps, references, and completion criteria before writing the final skill.

Refine an Existing Skill

Remove duplication, stale guidance, and no-op instructions while preserving required behavior.

Standardize a Skill Library

Apply shared vocabulary and review criteria across related skills and reference files.

Try These Prompts

Choose an Invocation Mode 
Review my skill purpose: [purpose]. Recommend model invocation or user invocation, and explain the context and cognitive load tradeoff.
Improve a Skill Description 
Rewrite this skill description: [description]. Front-load its leading word, keep one trigger per branch, and remove identity repeated in the body.
Restructure Skill Information 
Review this skill body: [skill text]. Separate steps from reference, identify disclosure candidates, and give every step a checkable completion criterion.
Perform a Full Skill Audit 
Audit this skill and glossary: [content]. Evaluate invocation, branches, hierarchy, co-location, completion criteria, leading words, duplication, relevance, no-ops, sediment, and sprawl.

Best Practices

  • Use one authoritative location for every rule or definition.
  • Give each ordered step a checkable and appropriately demanding completion criterion.
  • Keep shared material inline and disclose branch-specific reference through precise context pointers.

Avoid

  • Do not repeat one trigger using several synonymous phrases.
  • Do not keep stale or behavior-neutral instructions because deletion feels risky.
  • Do not split skills unless independent invocation or sequence isolation justifies the added load.

Frequently Asked Questions

What is the main goal of this skill?
It helps authors make agent behavior more predictable by improving invocation, structure, steering, and maintenance.
Does this skill create files automatically?
No. It provides reference guidance that an agent or author can apply while creating or editing skills.
When should a skill use model invocation?
Use it when an agent must discover the skill independently or another skill must reach it.
When should reference material move to another file?
Move material when only some branches need it and a precise context pointer can retrieve it reliably.
How does this skill reduce premature completion?
It recommends sharpening completion criteria first, then separating later steps only when visible steps still cause rushing.
Can teams use the glossary as a review standard?
Yes. The glossary defines shared terms for reviewing invocation, hierarchy, steering, pruning, and common failure modes.

Developer Details

Author

mattpocock

License

MIT

Skillstore revision

r2

Version notice

The author did not declare a version.

Repository

https://github.com/mattpocock/skills/tree/main/skills/productivity/writing-great-skills/

Ref

ebdfe608f5de2b66ff37ab4af12af8ac4f5e8006

Maintenance freshness

7/25/2026

Usage

23 downloads · 1 views

File structure

📄 GLOSSARY.md

📄 SKILL.md