Install
$ agentstack add skill-mr-fang-vlsi-edagent-eda-context-accessor ✓ 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.
About
EDA Context Accessor
When to use
Use this skill when a task needs shared KB retrieval, tool-catalog reuse checks, or both, and you do not want each downstream skill to restate that logic.
Scope Boundary
This skill owns:
- scoped KB context loading,
- scoped tool-registry reuse queries,
- compact context artifact generation for downstream skills.
It does not own:
- final domain conclusions,
- execution gating,
- code implementation,
- routing policy.
Expected Downstream Consumers
Typical consumers include:
workflow-routerbefore routing when shared KB/tool context is needed,- execution skills that need scoped KB evidence without duplicating retrieval logic,
- theory-analysis skills that need professional background evidence before judgment,
eda-infra-maintainerwhen retrieval reveals KB/tool maintenance work.
Inputs
Provide or derive:
- task scope and objective,
- keywords or topic names for KB retrieval,
- keywords for tool reuse query,
- expected downstream consumer skill(s).
Outputs
Return or update:
kb_context.mdor equivalent scoped context note,- tool-query evidence (
tool_query.tsvor cited terminal result), - concise reuse recommendation for downstream skills,
kb_feedback_decisionwith one of:none,maintain,update,overturn,add,kb_feedback_reasontied to affected KB files or missing areas.
Hard Rules
- Prefer local KB and tool-registry evidence before inventing new scripts or assumptions.
- Keep retrieved context scoped to the current task; do not dump unrelated KB content.
- Distinguish retrieved facts from downstream inferences.
- Every handoff must include an explicit KB feedback recommendation, even if the decision is
none.
Operational References
- Load
references/kb-context-loading.mdwhen the task needs scoped KB retrieval or evidence-gap context. - Load
references/tool-reuse-query.mdwhen the task may reuse an existing tool or when a downstream skill is considering a new script/helper. - Load
references/output-contract.mdwhen a downstream skill needs a reusable context artifact rather than raw terminal output. - Load
references/kb-feedback-policy.mdwhen deciding whether the current KB should be maintained, updated, overturned, or expanded.
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.