Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →jamditis/project-memory
Generate CLAUDE.md project memory files that transfer institutional knowledge, not obvious information.
Passed 16 of 22 test cases with the skill, and 10 of 22 without it.
and 3 more in the full report
6 fixed10 passed either way6 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.
Our central enterprise IT security team wants to place a mandatory system-wide policy file on developer workstations so that corporate compliance rules apply across all Claude Code sessions regardless of repository or user settings. On macOS systems, what exact file system path should IT deploy this managed policy memory file to?
| Checked | Without skill | With skill |
|---|---|---|
| Specifies /Library/Application Support/ClaudeCode/CLAUDE.md as the managed policy path on macOS. | Passed | Passed |
| Explains that system-managed policy memory overrides individual user and project settings. | Missed | Passed |
The instructions your model reads when the skill loads.
Create CLAUDE.md files that transfer institutional knowledge, not obvious information. Think like a senior journalist onboarding a competent colleague, you don't explain how journalism works, you explain YOUR project's quirks.
Anthropic is explicit on this point: CLAUDE.md content is delivered as a user message after the system prompt. Claude reads it and tries to follow it, but there's no guarantee of strict compliance, especially with vague or conflicting instructions. Source: https://code.claude.com/docs/en/memory
This affects how you write a CLAUDE.md and what you put elsewhere:
| Mechanism | Use for | Source-of-truth |
|---|---|---|
| CLAUDE.md | Standing facts, conventions, "always do X" rules | Advisory |
| Skills | Multi-step procedures, on-demand workflows | Loaded when invoked |
| Hooks | Actions that must happen every time, no exceptions | Deterministic when the hook blocks: a shell command that exits 2 (e.g. hooks/one-way-door-check.md) or a PreToolUse deny (e.g. hooks/no-ai-attribution.md). A prompt hook such as hooks/bug-report-detector.md only adds a reminder, so do not rely on it for a must-run rule |
If an instruction is "block writes to published/" or "run accessibility check before commit," that belongs in a hook, not CLAUDE.md. If it's "fact-check workflow" or "FOIA-letter drafting," that's a skill. CLAUDE.md is the place for things Claude must hold in every session.
Anthropic publishes an explicit include/exclude table for what makes an effective CLAUDE.md. Source: https://code.claude.com/docs/en/best-practices
| ✅ Include | ❌ Exclude |
|---|---|
| Bash commands Claude can't guess | Anything Claude can figure out by reading code |
| Code style rules that differ from defaults | Standard language conventions Claude already knows |
| Testing instructions and preferred test runners | Detailed API documentation (link to docs instead) |
| Repository etiquette (branch naming, PR conventions) | Information that changes frequently |
| Architectural decisions specific to your project | Long explanations or tutorials |
| Developer environment quirks (required env vars) | File-by-file descriptions of the codebase |
| Common gotchas or non-obvious behaviors | Self-evident practices like "write clean code" |
For journalism projects, translate to:
For every line you write, ask: "Would removing this cause Claude to make mistakes?" If not, cut it.
test cases passed, vs 10 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.