Install
$ agentstack add skill-enbiyagoral-claude-graduate ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Graduate a common mistake
Target item: $ARGUMENTS
Step 1 — Read common-mistakes.md
Read .claude/rules/common-mistakes.md. Show the current list.
Step 2 — Identify the item to graduate
From $ARGUMENTS:
- If a number → graduate that numbered item
- If a keyword → find the item that matches, confirm with user
- If no argument → list all items and ask which to graduate
If the list has fewer than 8 items, ask: "The list isn't full yet — are you sure you want to graduate this now, or is it no longer relevant?"
Step 3 — Check docs/learnings/ template
Read docs/learnings/README.md if it exists to understand the expected format.
Step 4 — Ask for context before writing
Before I graduate "", a few things:
1. Why is this being graduated?
a) It's fully resolved — we fixed the root cause
b) It happened enough times that it needs a proper write-up
c) It's no longer relevant to this project
2. Is there a specific incident or PR where this came up?
(optional — helps future readers understand the severity)
3. Any additional detail beyond what's in the mistake entry?
Wait for answers.
Step 5 — Write docs/learnings/YYYY-MM-DD-.md
Use today's date. Slug = kebab-case version of the mistake title.
#
**Graduated**:
**Source**: common-mistakes.md
## The mistake
## Why it matters
## Root cause
## How to avoid it
## Reference
Step 6 — Remove from common-mistakes.md
Edit .claude/rules/common-mistakes.md:
- Remove the graduated item
- Renumber the remaining items (1, 2, 3...)
- Do not leave a gap or placeholder
Step 7 — Print summary
Graduated: ""
Written to: docs/learnings/YYYY-MM-DD-.md
Removed from: .claude/rules/common-mistakes.md
Remaining items: /10
The learning is now in Tier 2 (docs/learnings/) — loaded when relevant,
not every session. This frees up a slot in common-mistakes.md.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: enbiyagoral
- Source: enbiyagoral/.claude
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.