crafting-instructions — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited crafting-instructions (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Choose the format for instructions on Claude.ai — Project instructions, Skills, or standalone prompts — and structure them for the format chosen.
Overlap notice. The Core Optimization Principles below also appear in writing-instructions, which carries them in more depth. This skill owns the format decision; writing-instructions owns how to write well inside a format. The two descriptions are close enough that a request can land on either — route by which of those two questions is being asked.
Ask these questions to determine the right format:
Signals: "for this project", "all conversations about X", "team workspace", "project-specific"
Signals: "every time I", "whenever", "reusable", "across projects", "teach Claude how to"
Signals: "for this task", "right now", "just this once", "can you"
Project + Skill:
Skill + Prompt:
These apply to ALL instruction formats:
Frame as direct action commands, not suggestions:
State WHAT to do, not what NOT to do:
WHY: Negative instructions force inference. Positive instructions state desired behavior directly.
Explain WHY requirements exist:
WHY: Context helps Claude make better autonomous decisions in edge cases.
Provide goals and decision frameworks, not step-by-step procedures:
Current models plan from a stated goal. Write out a sequence only where one sequence is the safe one — destructive commands, auth flows, compliance steps.
Claude's system prompt already covers:
ONLY specify project/domain-specific deviations.
See: references/project-instructions.md
Key points:
See: references/creating-skills.md
Key points:
See: references/standalone-prompts.md
Key points:
Read: references/skill-vs-project.md for detailed comparison
Quick reference:
Project = "Here's what you need to know"
Skill = "Here's how to do things"
Example:
Use both together for powerful combinations.
Examples teach every pattern they contain, including the ones you did not intend.
When including examples:
Default to clear organization:
Use structured markup (XML/JSON) only when:
No prompt phrase turns thinking on. Current Claude models think adaptively by default, and depth is set by configuration — the effort setting on the API, the UI control on Claude.ai. "Think step by step" and hand-written trigger phrases buy nothing.
What instructions can usefully carry is which parts of the domain deserve more deliberation, so the reader knows where to raise effort:
[Specific complexity] in this domain is worth extra deliberation because [why].Match instruction complexity to task needs:
Simple task → Simple prompt or brief instructions Medium task → Structured guidance with decision frameworks Complex task → Comprehensive instructions; raise effort
Before adding complexity: Could simpler formulation work equally well?
Scale density to how far the task sits from what the model does unprompted. State the goal, the constraints, and how success is checked; add procedure only where order is fragile. When the choice is between another rule and more context about why, write the context — that is what the model cannot get elsewhere, and it is what it uses on the cases you did not enumerate.
State explicitly that judgment applies to cases the instructions do not cover.
Before delivering instructions:
Strategic:
Technical:
Execution:
❌ System prompt duplication - "Use web_search for current info, cite sources" ✅ Omit unless project has SPECIFIC deviations
❌ Negative framing - "Don't use lists, never be verbose" ✅ "Present in natural prose paragraphs"
❌ Fake thinking triggers - "Use 'think carefully' for deep thinking" ✅ "Name where deliberation pays in this domain; set effort there"
❌ Procedural micromanagement - "Step 1: X, Step 2: Y..." ✅ "Goal: X. Quality standard: Y. Approach: Z."
❌ Contextless requirements - "Always use formal tone" ✅ "Use formal tone for professional docs because recipients expect authoritative voice"
❌ Imperfect examples - Example uses bullets when you want prose ✅ Either create perfect examples or omit entirely
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.