instruction-generator
- Repo stars 0
- Author updated Live
- Author repo skills-registry
- Domain
- Other
- Compatible agents
-
- Claude Code
- Cursor
- Cline
- Codex
- Windsurf
- Gemini CLI
- +20
- Trust score
- 88 / 100 · community maintained
- Author / version / license
- @tomevault-io · no license declared
- Token usage
- Lean
- Setup complexity
- Plug-and-play
- External API key
- Not required
- Operating systems
- Unspecified (assume cross-platform)
- Runtime requirements
- Python
- Permissions
-
- Read-only
- Write / modify
- Network behavior
- Local-only
- Install commands
- 26 variants
Profile is derived at build time from SKILL.md and install vectors. Subject to drift from author intent.
Heads up: 未限定 allowed-tools，默认拥有全部工具权限。
---
name: instruction-generator
description: >- Use when this capability is needed. Produces clear, scoped, non-contradictory instruction fil…
category: other
runtime: Python
---
# instruction-generator output preview
## PART A: Task fit
- Use case: >- Use when this capability is needed. Produces clear, scoped, non-contradictory instruction files that Claude loads and follows automatically. Instructions are always-on: they apply whenever Claude processes matching runs entirely locally; runs on Python. Works with Claude Code, Cursor, Cline and 23 more..
- Inputs: target material, constraints, expected output, and acceptance criteria.
- Evidence boundary: follow “Quick Decision: Which instruction file? / Workflow / Step 1 — Clarify scope” and do not present inference as author intent.
## PART B: Execution result
- **01** The card summarizes the use case; runtime output centers on “>- Use when this capability is needed. Produces clear, scoped, non-contradictory instruction files that Claude loads and follows automatically. Instructions are always-on: they apply whenever Claude processes matching runs entirely locally; runs on Python. Works with Claude Code, Cursor, Cline and 23 more.”.
- **02** When the source has headings, the agent prioritizes “Quick Decision: Which instruction file? / Workflow / Step 1 — Clarify scope” so the result follows the author’s structure.
- **03** Typical output includes task judgment, concrete steps, required commands or file edits, validation, and follow-up options.
- **04** Risk context follows the fingerprint: read files, write/modify files; mostly runs locally; usually needs no extra API key.
## Running Rules
- read files, write/modify files; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding scope.
- Return the result, validation criteria, and next iteration options.The source does not require a stable slash command. After installation, invoke the skill by name and describe the task.
Name target files or source material, expected output, forbidden changes, and whether network or shell access is allowed. Permission fingerprint: read files, write/modify files.
Start with a small task and check whether the result follows “Quick Decision: Which instruction file? / Workflow / Step 1 — Clarify scope”. Inspect diffs, logs, previews, or tests before expanding scope.
Confirm the final output includes a concrete result, evidence, and next action. If it stays generic, tighten inputs, boundaries, and acceptance criteria.
---
name: instruction-generator
description: >- Use when this capability is needed. Produces clear, scoped, non-contradictory instruction fil…
category: other
source: tomevault-io/skills-registry
---
# instruction-generator
## When to use
- >- Use when this capability is needed. Produces clear, scoped, non-contradictory instruction files that Claude loads a…
- Use it when the task has clear inputs, repeatable steps, and validation criteria.
## What to provide
- Target material, scope, expected result, and forbidden changes.
- Whether network, commands, file writes, or external services are allowed.
## Execution rules
- Organize steps around “Quick Decision: Which instruction file? / Workflow / Step 1 — Clarify scope” and keep inference separate from source facts.
- read files, write/modify files; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding the task.
## Output requirements
- Return the deliverable, key evidence, validation method, and next action.
- Mark missing information as unknown; do not invent commands, platforms, or dependencies.The author source anchors workflow facts; repository files anchor sources and commands; Fluxly only adds fit, limitations, and quality judgment.
skill "instruction-generator" {
input -> user goal + target files + boundaries + acceptance criteria
context -> Quick Decision: Which instruction file? / Workflow / Step 1 — Clarify scope
rules -> SKILL.md triggers / order / output contract
runtime -> Python | read files, write/modify files | mostly runs locally
guardrails -> usually needs no extra API key + small-sample validation + diff/log review
output -> copyable result + checklist + next iteration
}Instruction Generator
Produces clear, scoped, non-contradictory instruction files that Claude loads and follows automatically.
Instructions are always-on: they apply whenever Claude processes matching files or contexts. Keep them concise. Every word in an instruction file costs context tokens on every invocation.
Quick Decision: Which instruction file?
| Need | File | Location |
|---|---|---|
| Applies to the whole workspace / all files | copilot-instructions.md or AGENTS.md |
.github/ or root |
| Applies to specific file types or folders | <name>.instructions.md |
.github/instructions/ |
| Applies to user (cross-workspace) | <name>.instructions.md |
{{VSCODE_USER_PROMPTS_FOLDER}}/ |
applyTo patterns:
"**"— matches all files"**/*.ts"— TypeScript files"src/**"— everything undersrc/"**/*.{ts,tsx}"— multiple extensions- Leave
applyToabsent for on-demand instructions (not auto-applied)
Workflow
Follow these steps in order. Mark each ✓ when done.
Step 1 — Clarify scope
Answer before writing:
- Who is this for? All team members (workspace) or just this user (user-level)?
- What files trigger it? Language, framework, folder, or all files?
- What behavior changes? Style, safety rules, prohibited patterns, or workflow steps?
Step 2 — Choose depth
| Variant | Use when | Target length |
|---|---|---|
| Concise rules | Simple preferences (naming, style, imports) | ≤ 20 lines |
| Extended rules | Fragile workflows, multi-step processes, error-prone areas | 20–60 lines |
| Reference-based | Large rule sets; use progressive disclosure | SKILL body → details.md |
If the instruction body would exceed 60 lines, split it:
- SKILL body: overview + key rules
- Separate
*.mdfile: extended rules, examples, edge cases
Step 3 — Write the instruction
---
applyTo: "<glob>"
description: "<optional: use for on-demand instructions>"
---
# <Short title>
<Context sentence: what this file covers and why>
## Rules
- <Rule 1: imperative, specific, verifiable>
- <Rule 2: imperative, specific, verifiable>
- <Rule n>
## Do not
- <Prohibited action 1>
- <Prohibited action 2>See templates/instructions-concise.md and templates/instructions-extended.md.
To scaffold a stub from the command line:
python skills/instruction-generator/scripts/generate_instruction_stub.py \
--apply-to "**/*.ts" --title "TypeScript rules" [--variant concise|extended]Step 4 — Rewrite vague rules
Run each rule through this test: "Can Claude determine pass/fail without judgment?"
| Vague (reject) | Specific (accept) |
|---|---|
| "Write good code" | "Prefer pure functions; avoid side effects in utility modules" |
| "Be concise" | "Keep function bodies under 40 lines; extract helpers if exceeded" |
| "Handle errors properly" | "Wrap async calls in try/catch; surface errors to the caller — never swallow" |
| "Use modern syntax" | "Use ES2022+; prefer ?. and ?? over manual null checks" |
Step 5 — Check for contradictions
- Does any rule contradict another in this file?
- Does any rule contradict existing instructions in
.github/copilot-instructions.md? - Are
applyTopatterns precise enough? (Overly broad patterns → high context cost)
Step 6 — Validate quality checklist
- Every rule is imperative and verifiable (no "should", "try to", "consider").
-
applyTopattern is correct glob syntax — validated against target file paths. - No time-sensitive information (no version numbers with expiry dates, no API phases).
- Consistent terminology throughout (same term for same concept).
- Instructions don't duplicate VS Code / Copilot defaults.
- File length is appropriate for the chosen depth variant.
Run the validator to catch soft rules and frontmatter issues automatically:
python skills/instruction-generator/scripts/validate_instruction_output.py <path>
# or via poe:
poe validate-instructions <path>Anti-patterns
- Omnibus instructions: one file covering too many unrelated concerns. Split by domain.
- Soft rules: "prefer" without a fallback condition. Use "unless X, then Y" when needed.
- Stale specifics: "until August 2025 use the old API" — becomes wrong immediately.
- Missing
applyTo: without a glob, the file is on-demand only; teams expecting auto-apply will be confused. - Duplicating documentation: instructions should tell Claude what to do, not explain the library.
Output format
Deliver the full instruction file (frontmatter + body) and note:
- Recommended file path
- Recommended scope (workspace vs user)
- Any follow-up rule files if progressive disclosure was used
See examples/ for language-specific and workflow-specific patterns. Concise template: templates/instructions-concise.md Extended template: templates/instructions-extended.md
Source: Anselmoo/universal-creator — distributed by TomeVault.
Decide Fit First
Design Intent
How To Use It
Boundaries And Review