python3 <skill-path>/scripts/analyze_schematic.py --schema
python3 <skill-path>/scripts/analyze_pcb.py --schema
python3 <skill-path>/scripts/analyze_gerbers.py --schema

python3 <skill-path>/scripts/analyze_schematic.py <file.kicad_sch> --analysis-dir analysis/
python3 <skill-path>/scripts/analyze_schematic.py <file.kicad_sch> --analysis-dir analysis/ --compact
python3 <skill-path>/scripts/analyze_schematic.py <file.kicad_sch> --output analysis.json  # one-off, no cache

python3 <skill-path>/scripts/analyze_pcb.py <file.kicad_pcb> --analysis-dir analysis/
python3 <skill-path>/scripts/analyze_pcb.py <file.kicad_pcb> --analysis-dir analysis/ --proximity  # add crosstalk analysis
python3 <skill-path>/scripts/analyze_pcb.py <file.kicad_pcb> --output pcb.json  # one-off, no cache

undefined

Checks: CC-001 connector current capacity, EG-001 ESD protection gaps, DA-001 decoupling adequacy, XV-001..003 schematic/PCB sync. PCB JSON optional.

undefined

Outputs: layer identification (X2 attributes), component/net/pin mapping (KiCad 6+ TO attributes), aperture function classification, trace width distribution, board dimensions, drill classification (via/component/mounting), layer completeness, alignment verification, pad type summary (SMD/THT ratio). Add `--full` for complete pin-to-net connectivity dump. ~10KB JSON.

The gerber analyzer produces a `findings` list with rich format findings: GR-001 missing layers, GR-002 alignment issues, GR-003 drill problems, GR-004 paste aperture mismatches, GR-005 open board outlines.

If the script fails or returns unexpected results, see `references/manual-gerber-parsing.md` for the complete fallback methodology for parsing raw Gerber/Excellon files directly.

All scripts output JSON to stdout by default. Prefer `--analysis-dir analysis/`
to integrate output into the run-folder convention described in "Analysis
Cache Convention" below — every analyzer in a single session then co-locates
inside the same `analysis/<run_id>/` folder and is tracked by the manifest.
Use `--output file.json` only for one-off runs where you don't want the
result cached. Add `--compact` for single-line JSON.

**Analyzer JSON is worth keeping** — these are expensive to regenerate (large
schematics take time). `--analysis-dir` preserves every run and is the form
downstream tools (kidoc, diff_analysis, what_if) expect. They're not worth
committing to git, but don't delete them between analysis steps.

{
    "analyzer_type": "schematic|pcb|emc|cross_analysis|thermal|gerber|lifecycle|spice",
    "schema_version": "1.3.0",
    "summary": {
        "total_findings": 42,
        "by_severity": {"error": 3, "warning": 15, "info": 24}
    },
    "findings": [
        {"rule_id": "...", "detector": "...", "severity": "...", "confidence": "...", "evidence_source": "...", "summary": "...", ...}
    ],
    "trust_summary": {
        "total_findings": 42,
        "trust_level": "high|mixed|low",
        "by_confidence": {"deterministic": 20, "heuristic": 18, "datasheet-backed": 4},
        "by_evidence_source": {"datasheet": 4, "topology": 10, "heuristic_rule": 18, ...},
        "provenance_coverage_pct": 96.5
    }
}

undefined

JSON output always includes all findings. `--stage` adds `stages` and `in_active_stage` fields to each finding plus a `stage_filter` summary. `audience_summary` is always computed with designer/reviewer/manager views. `--text` output respects both flags.

{
  "analysis": {
    "output_dir": "analysis",
    "retention": 5,
    "auto_diff": true,
    "track_in_git": false,
    "diff_threshold": "major"
  }
}

analyzer_type, schema_version, summary, findings, trust_summary,
file, kicad_version, file_version, title_block, statistics,
bom, components, nets, subcircuits, ic_pin_analysis, design_analysis,
connectivity_issues, hierarchy_context, hierarchy_warning,
net_classifications, rail_voltages

analyzer_type, schema_version, summary, findings, trust_summary,
file, kicad_version, file_version, statistics, layers, setup,
nets, net_name_to_id, board_outline, component_groups, footprints,
tracks, vias, zones, keepout_zones, connectivity, net_lengths

analyzer_type, schema_version, summary, findings, trust_summary,
directory, generator, layer_count, statistics, completeness, alignment,
drill_classification, pad_summary, board_dimensions, gerbers, drills

python3 <digikey-skill-path>/scripts/sync_datasheets_digikey.py <file.kicad_sch>
python3 <lcsc-skill-path>/scripts/sync_datasheets_lcsc.py <file.kicad_sch>
python3 <element14-skill-path>/scripts/sync_datasheets_element14.py <file.kicad_sch>
python3 <mouser-skill-path>/scripts/sync_datasheets_mouser.py <file.kicad_sch>

python3 <skill-path>/scripts/datasheet_page_selector.py <pdf_path> --mpn <mpn> --category <category>

undefined

Auto-detects analyzer type (schematic, PCB, EMC, SPICE). Reports:
- **Components**: new, removed, value/footprint/MPN changes
- **Signal analysis**: parameter shifts per detection type, driven by `detection_schema.SCHEMAS` identity and value fields
- **BOM**: added/removed line items, quantity changes
- **Connectivity/ERC**: new/resolved single-pin nets, floating nets, multi-driver nets, ERC warnings
- **EMC findings**: new/resolved findings with severity, risk score delta, per-net score changes
- **SPICE results**: status transitions (pass->fail regressions, fail->pass fixes), Monte Carlo concern changes
- **Severity classification**: `none` (no changes), `minor` (statistics only), `major` (component/signal/finding changes), `breaking` (SPICE regressions, new CRITICAL EMC findings, new ERC warnings)

Also used programmatically by `analysis_cache.should_create_new_run()` to decide whether new outputs warrant a new timestamped run folder.

undefined

Models each power component (LDO, switching regulator, shunt resistor) as a point heat source. Computes Tj = T_ambient + P_diss × Rθ_JA_effective, where Rθ_JA comes from a package lookup table (SOT-223: 60°C/W, QFN-5x5: 25°C/W, etc.) and is corrected for PCB thermal vias and copper pour. Rules:

| Rule | Condition | Severity |
|------|-----------|----------|
| TS-001 | Tj exceeds absolute maximum | CRITICAL |
| TS-002 | Tj within 15°C of absolute maximum | HIGH |
| TS-003 | Tj > 85°C (may affect nearby passives) | MEDIUM |
| TS-004 | P > 0.5W with no thermal vias | MEDIUM |
| TS-005 | Significant power, within safe limits | INFO |
| TP-001 | MLCC within 10mm of hot component | LOW |
| TP-002 | Electrolytic cap within 10mm of hot component | MEDIUM |

Thermal findings and assessments include the rich format envelope (detector, rule_id, summary, evidence_source, report_context). Rule IDs: TS-001..005 (safety), TP-001..002 (proximity), TH-DET (assessments).

undefined

Patches component values in the analyzer JSON, recalculates derived fields (filter cutoff, divider ratio, opamp gain, crystal load, current sense range, regulator Vout), and shows before/after comparison with percentage deltas. Supports single changes, multi-point sweeps (comma or log-range), tolerance corner analysis, inverse fix suggestions with E-series snapping, EMC impact preview, PCB parasitic awareness (auto-discovered or via `--pcb`), and SPICE re-verification.

undefined

Flags: `--top N` (default 20), `--severity` (filter to `critical`/`high`/`warning`/`info`), `--run` (explicit run ID instead of latest), `--json` (machine-readable output).

undefined

Reads the analyzer JSON BOM section, extracts unique MPNs, queries distributors (LCSC no-auth, DigiKey, element14, Mouser) for lifecycle status and operating temperature. Temperature presets: `commercial` (0/70°C), `industrial` (-40/85°C), `extended` (-40/105°C), `automotive` (-40/125°C), `military` (-55/125°C). Also checks datasheet extraction cache for temperature data before making API calls.

The lifecycle audit produces rich format findings: LC-001 (obsolete/discontinued), LC-002 (last time buy), LC-003 (NRND), LC-004 (unknown status), LC-005 (single source), LC-006 (long lead time), LT-001 (temperature violation).

**Requires network access** — unlike the core analyzers, this script calls distributor APIs. Same environment variables as the distributor skills (DIGIKEY_CLIENT_ID/SECRET, MOUSER_SEARCH_API_KEY, ELEMENT14_API_KEY). LCSC requires no credentials.