Install
$ agentstack add skill-mr-fang-vlsi-edagent-eda-script-pattern-curator ✓ 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
EDA Script Pattern Curator
When to use
Use this skill when:
- repeated script-writing lessons appear across infrastructure or execution helpers,
- a new wrapper/helper is being considered and prior abstraction/runtime experience should be checked first,
- script anti-patterns should be promoted into durable guidance,
- infra work needs a place to persist coding lessons that are more specific than global governance but broader than one script.
Scope Boundary
This skill owns:
- reusable script-writing patterns,
- wrapper and runtime lessons,
- abstraction triggers for when a one-off helper should become a shared tool,
- script-level anti-pattern capture.
It does not own:
- the tool catalog itself,
- domain experiment conclusions,
- generic artifact hygiene,
- final infrastructure workflow ownership.
Expected Downstream Consumers
Typical consumers:
eda-infra-maintainereda-method-implementerworkflow-scoped-executioneda-context-accessor
Inputs
Provide or derive:
- script or wrapper paths under discussion,
- prior maintenance notes or logs,
- tool-catalog search results,
- runtime/environment constraints when relevant.
Outputs
Emit the smallest useful set:
- script-pattern note or SOP update,
- concrete reuse/abstraction recommendation,
- anti-pattern warning when applicable,
- cross-links to related tools or wrappers.
Hard rules
- Do not create a new shared script just because two scripts look similar; require a clear reuse trigger.
- Keep script-writing lessons separate from experiment-phenomenology lessons.
- Tie every pattern or anti-pattern to concrete script evidence.
- Prefer tool-catalog reuse over new wrapper proliferation.
Operational References
- Load
references/pattern-layers.mdwhen deciding how to separate raw script incidents from reusable patterns. - Load
references/integration-policy.mdwhen wiring script-pattern guidance into infra or execution workflows. - Use
docs/knowledge_base/templates/script_incident_template.mdanddocs/knowledge_base/templates/script_pattern_note_template.mdas the default artifact skeletons when no more specific script-pattern template already exists.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: Mr-Fang-VLSI
- Source: Mr-Fang-VLSI/EDAgent
- 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.