prompt-output
Use whenever the task is to produce a prompt file (a .prompt.md file, or any "write me a prompt" request), for the required output format.
Skill by ioncache
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/ioncache-prompt-output
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: writing, productivity, agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/prompt-output
What's inside
- Skill name
prompt-output- Description
- Use whenever the task is to produce a prompt file (a .prompt.md file, or any "write me a prompt" request), for the required output format.
- License
- MIT
- Instructions
- 37 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Prompt Output Format ## Hard Rule When the task is to produce a prompt, any phrasing of "write me a prompt," "create a prompt for X," "generate a prompt," or the output is a `.prompt.md` file, the ENTIRE output MUST be a single code-fenced `markdown` block and nothing else. **Correct:** ````markdown ```markdown --- description: '...' --- Prompt content here. ``` ```` **Forbidden:** - Any prose before or after the code fence - Labels such as "Here's the prompt:" or "Prompt:" - Summary text such as "I've created the following prompt..." - Multiple code fences - Markdown rendered outside a code fence ## Why Chat interfaces render markdown as HTML automatically. Text outside a code fence is rendered into formatted HTML and loses its raw markdown, the user cannot copy-paste it. A single code-fenced block is the only format that survives rendering intact and is directly usable.
From ioncache/ioncache-ai-tools, MIT.
More from ioncache/ioncache-ai-tools
- 0.565score
review-validate-fix-loop
ioncache
Autonomously reviews, validates, fixes, and re-reviews code within finite nested loops, preserving decisions in a per-run ledger.
SkillAFreshness: AClaude Code +9 - 0.565score
triage-errors
ioncache
Groups and fixes errors by root cause after a large change.
SkillAFreshness: AClaude Code +9 - 0.565score
verify-unresolved-pr-comments
ioncache
Analyzes unresolved review comments and PR-level feedback on the active PR without making changes.
SkillAFreshness: AClaude Code +9 - 0.565score
investigate
ioncache
Traces how a feature, workflow, or system works without changing files.
SkillAFreshness: AClaude Code +9 - 0.565score
review-code
ioncache
Reviews code for correctness, security, performance, and project standards using independent review passes.
SkillAFreshness: AClaude Code +9 - 0.559score
create-worktree
ioncache
Creates a git worktree and applies the repo's .worktree-setup.json.
SkillAFreshness: AClaude Code +9 - 0.524score
unit-tests
ioncache
Use when writing or reviewing JavaScript/TypeScript unit tests with Vitest, for BDD structure, AAAR comments, and coverage/mocking conventions.
SkillBFreshness: BClaude Code +9 - 0.524score
documentation-writing
ioncache
Use when writing or updating documentation, READMEs, commit messages, or code comments, for sentence style, punctuation, and emphasis rules.
SkillBFreshness: BClaude Code +9 - 0.524score
security
ioncache
Use when writing or reviewing API endpoints, database access, auth, or user input handling, for validation, sanitization, and secret-handling standards.
SkillBFreshness: BClaude Code +9 - 0.524score
code-complexity
ioncache
Use when writing or reviewing functions, for guidance on parameter counts, nesting depth, function length, and single-responsibility structure.
SkillBFreshness: BClaude Code +9 - 0.524score
jsdoc
ioncache
Use when writing or reviewing JSDoc on JavaScript/TypeScript functions, for required tags, typedef rules, and formatting.
SkillBFreshness: BClaude Code +9 - 0.521score
answer-questions
ioncache
Invoke before responding whenever the user asks a direct question.
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 3
- Last commit (this folder)
- Jul 29, 2026 (3 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/ioncache/ioncache-ai-tools
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from ioncache
- 0.565score
triage-errors
ioncache
Groups and fixes errors by root cause after a large change.
SkillAFreshness: AClaude Code +9 - 0.565score
verify-unresolved-pr-comments
ioncache
Analyzes unresolved review comments and PR-level feedback on the active PR without making changes.
SkillAFreshness: AClaude Code +9 - 0.565score
review-validate-fix-loop
ioncache
Autonomously reviews, validates, fixes, and re-reviews code within finite nested loops, preserving decisions in a per-run ledger.
SkillAFreshness: AClaude Code +9 - 0.565score
investigate
ioncache
Traces how a feature, workflow, or system works without changing files.
SkillAFreshness: AClaude Code +9 - 0.565score
review-code
ioncache
Reviews code for correctness, security, performance, and project standards using independent review passes.
SkillAFreshness: AClaude Code +9 - 0.559score
create-worktree
ioncache
Creates a git worktree and applies the repo's .worktree-setup.json.
SkillAFreshness: AClaude Code +9
Cite this page
prompt-output skill. Agent Mart. https://agentmart.dev/skills/ioncache-prompt-output (last updated 2026-10-24)