القائمة
Surveys FeCIM domain knowledge by searching references/, citations/, docs/4-research/, and the local Cognee KG, then synthesizes a cited research note. Use when investigating a physics topic, evaluating a paper, or grounding a design decision in literature.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Audits Go code for goroutine-to-widget access without fyne.Do(...) wrapping, the project's most common GUI freeze cause. Use when reviewing a PR that adds goroutines, async I/O, or simulation tickers in any pkg/gui/ or shell package.
Runs build flows for the canonical Fyne shell and module commands on this Go 1.25 monorepo. Use when building, packaging, or debugging build failures in cmd/fecim-lattice-tools or module GUI commands.
Relentlessly interviews the user about a proposed FeCIM physics, simulation, or GUI change before any code is written — covering source citation, educational-vs-validated framing, TDD-RED test, thread-safety, and honesty-audit alignment. Use when starting a non-trivial change to physics, ISPP, crossbar, or GUI logic.
Runs the FeCIM test matrix (full, race, module-scoped, coverage, golden regen) and interprets physics regression failures using the 5 known bug patterns. Use when running tests, debugging test failures, or regenerating physics golden files.
Verifies and formats FeCIM physics/measurement claims against the project's published-source list and docs/4-research/honesty-audit.md. Use when adding a numeric claim, accuracy figure, or device-parameter assertion to code, docs, PR descriptions, or commit messages.
Enforces docs/4-research/honesty-audit.md policy by scanning PR diffs, READMEs, and presentation material for removed/unverified claims (87% MNIST, 30-states-as-fact, energy multipliers vs NAND/GPUs). Use before committing docs, PRs, or release notes that include accuracy or efficiency numbers.
| name | fecim-researcher |
| description | Surveys FeCIM domain knowledge by searching references/, citations/, docs/4-research/, and the local Cognee KG, then synthesizes a cited research note. Use when investigating a physics topic, evaluating a paper, or grounding a design decision in literature. |
Survey FeCIM literature and project knowledge to ground a design decision or answer a physics question. See tools/fecim-skills/_shared/fecim-context.md for the canonical citation list.
Define the question. Write it in one sentence. If it has multiple sub-questions, split them and run the workflow per sub-question.
Search local sources in this order:
docs/4-research/ (audits, validation notes, error propagation)references/ (academic papers, simulation benchmarks)citations/ (project's citation registry, if present)experimental-data/ (HZO, HfO2, crossbar characterization)Use rg with focused patterns when available (e.g., rg -i "preisach" docs/4-research/ references/). If rg is missing, use grep -RIn or the file-search tool and state the fallback.
If Cognee is configured locally (.env has LLM_API_KEY, .cognee_system/ exists), query the KG:
python3 - <<'PY'
import os, asyncio
os.environ["COGNEE_SKIP_CONNECTION_TEST"] = "true"
os.environ["ENABLE_BACKEND_ACCESS_CONTROL"] = "false"
import cognee
async def main():
results = await cognee.search("YOUR QUERY HERE")
print(results)
asyncio.run(main())
PY
Otherwise skip it explicitly in the evidence log; do not install Cognee or start long bootstrap/download flows during active validation.
Cite findings using the canonical short forms from tools/fecim-skills/_shared/fecim-context.md. Never invent a citation; if no source supports a claim, label it "no source found, requires verification".
Output a structured note:
Question: <...>
Sources: <list with short citation forms>
Finding: <2-5 sentences>
Gaps: <what is unsupported, what should be measured>
Recommended next step: <action>
module1-hysteresis/pkg/ferroelectric/material.go and references/, cites Materlik 2015, returns parameters with units.Research output is observation — TDD: N/A. Any code change suggested by the research triggers the project's TDD hard-rule.