Skip to content
Back to skills

Staging V0 19

ASecurity

ANTI-PATTERNS (NEVER DO THESE) — extracted from roles.json deepPrompt for writer

  • 8 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added September 5, 2026
ai-agentsrustgogit

Works with

  • terminal

Security analysis

A100/100

Pro scans all 21 files and shows the line behind each finding

Scanned September 5, 2026

npx -y skills add iampantherr/SecureContext --skill _staging_v0_19 --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Staging V0 19?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Staging V0 19
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/iampantherr-staging-v0-19-5a6e67d9/badge)](https://www.skillsdirectory.com/skills/iampantherr-staging-v0-19-5a6e67d9)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
id: writer-anti-patterns-never-do-these@1@global
name: writer-anti-patterns-never-do-these
version: 1
scope: global
description: ANTI-PATTERNS (NEVER DO THESE) — extracted from roles.json deepPrompt for writer
intended_roles: [writer]
mutation_guidance: |
  This skill encodes a behavioral procedure originally embedded in the
  writer role's deepPrompt. When mutating, preserve the imperative
  voice and the numbered/bulleted structure. Sub-rules within a numbered
  point can be edited; the top-level numbering should not change without
  operator approval (it's referenced by other skills + role text).
tags: [writer, role-extracted, v0-19-bootstrap]
acceptance_criteria:
  min_outcome_score: 0.6
  completes_in_seconds: 600
---
# ANTI-PATTERNS (NEVER DO THESE)

_(Extracted from `roles.json` deepPrompt for the **writer** role during the v0.19.0 role/skill split. Original content preserved verbatim. Edit freely; the mutator will propose improvements based on skill_runs telemetry once this skill is invoked by an agent.)_

---

- **Feature-oriented structure**: Organizing docs by product features instead of reader tasks. Readers search by what they want to do, not what the product offers.
- **"Simply" and "just"**: These words signal that the writer forgot what it felt like to not know something. They are always deleted.
- **Concept-dumping before quickstart**: Leading with a 2,000-word architecture overview before the reader has run Hello World. They will leave.
- **Untested examples**: Code that was typed rather than executed. Causes immediate trust damage.
- **Changelog as commit log**: Paste the git log as the release notes. This is developer laziness that creates user confusion.
- **One document, multiple Divio types**: A tutorial that is also a reference that is also an explanation. All three fail.
- **Over-linking**: Hyperlinking every technical term until the prose reads as a Wikipedia article. Links should be deliberate navigation aids, not a vocabulary index.
- **Screenshot-heavy docs**: Screenshots go stale. UI changes. Every screenshot is a maintenance liability. Use them for onboarding flows only. Never use them to show terminal output — use code blocks.
- **Implicit prerequisites**: Starting a how-to guide without stating what the reader must already have installed, configured, or understood. This produces support tickets.
- **"Note", "Warning", "Tip" overuse**: Callout boxes lose signal when overused. If more than 15% of a document's content is in callout boxes, the structure is broken.

Files in this skill

  • _REPORT.md32.8 KB
  • _role_account-executive.slimmed-deepprompt.md2.8 KB
  • _role_account-manager.slimmed-deepprompt.md2.8 KB
  • _role_accountant.slimmed-deepprompt.md2.7 KB
  • _role_analyst.slimmed-deepprompt.md5 KB
  • _role_architect.slimmed-deepprompt.md2.8 KB
  • _role_blogger.slimmed-deepprompt.md2.6 KB
  • _role_board-advisor.slimmed-deepprompt.md2.7 KB
  • _role_brand-architect.slimmed-deepprompt.md2.7 KB
  • _role_brand-designer.slimmed-deepprompt.md2.7 KB
  • _role_brand-manager.slimmed-deepprompt.md2.7 KB
  • _role_brand-strategist.slimmed-deepprompt.md2.7 KB
  • _role_business-analyst.slimmed-deepprompt.md2.7 KB
  • _role_channel-manager.slimmed-deepprompt.md2.8 KB
  • _role_chief-of-staff.slimmed-deepprompt.md2.7 KB
  • _role_comp-analyst.slimmed-deepprompt.md2.8 KB
  • _role_competitive-intel.slimmed-deepprompt.md2.7 KB
  • _role_compliance-officer.slimmed-deepprompt.md2.8 KB
  • _role_consultant.slimmed-deepprompt.md2.7 KB
  • _role_content-marketer.slimmed-deepprompt.md2.8 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.