Install
$ agentstack add skill-alvin-yang-ay-skills-ay-improve ✓ 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
AY Improve
Improve a demonstrated constraint, not an imagined future.
Approval contract
- Read the full request and investigate discoverable facts before asking the user.
- Treat review, diagnosis, explanation, and planning as read-only unless the user also requests change.
- Treat a precise instruction as approval when target, observable result, and acceptance boundary are clear.
- A broad outcome authorizes investigation, not file or artifact changes based on choices the agent must invent.
- For a materially underspecified change, present one recommended proposal and wait for approval.
- After approval, execute autonomously inside the approved boundary; do not ask about ordinary implementation details.
- Reopen approval only when new evidence changes behavior, architecture, data contracts, dependencies, scope, risk, cost, rollback, or external actions.
- Perform external actions only when the request or approved proposal includes them. Confirm the exact target before an irreversible action.
- Preserve unrelated and user-authored work. Verify the real requested outcome before claiming completion.
Find the constraint
Inspect the relevant call paths, tests, history, build or runtime measurements, and change patterns. Name the concrete friction: latency, allocation, duplication, coupling, unclear ownership, difficult testing, slow builds, or repeated change cost.
Do not treat aesthetics, file size alone, or a new abstraction as evidence. If no material constraint is found, say so and recommend no change.
Propose the smallest leverage
Trace every proposed file, dependency, abstraction, and public behavior to the measured constraint. Recommend the smallest option that materially improves it. Include:
- baseline and evidence
- intended improvement and success measure
- affected boundary and behavior that must stay stable
- scope, risk, and relevant alternative
- verification method
Wait for approval before restructuring unless the user's instruction already specifies the exact transformation.
Implement and compare
Preserve behavior unless the approved proposal says otherwise. Prefer a deep, stable interface over layers of helpers. Avoid speculative extensibility, unrelated cleanup, and dependencies whose cost exceeds the improvement.
Verify the success measure and neighboring behavior. Distinguish measured gains from reasoned expectations. Review the final diff for scope traceability, then report the before/after evidence and remaining tradeoffs.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: ALVIN-YANG
- Source: ALVIN-YANG/ay-skills
- 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.