Skip to content

hashgraph-online/awesome-codex-plugins / plugins/aklofas/kicad-happy/skills/kicad

Analyze KiCad projects and PDF schematics: schematics, PCB layouts, Gerbers, footprints, symbols, netlists, and design rules. Reviews designs for bugs, traces nets, cross-references schematic to PCB, extracts BOM data, checks DRC/ERC, DFM, power trees, and regulator circuits. Every finding carries a confidence label and evidence source with trust_summary rollup. Analyzes PDF schematics from dev boards, reference designs, eval kits, and datasheets. Supports KiCad 5–10. Use whenever the user mentions .kicad_sch, .kicad_pcb, .kicad_pro, PCB design review, schematic analysis, PDF schematics, reference designs, Gerber files, DRC/ERC, netlist issues, BOM extraction, signal tracing, power budget, DFM, or wants to understand, debug, compare, or review any hardware design. Also for "check my board", "review before fab", "what's wrong with my schematic", "is this ready to order", "check my power supply", "verify this circuit", OSHWA certification readiness, or any electronics/PCB design question.

FileKindSize
SKILL.mdskill md79.1 KB
references/config-reference.mdmarkdown19.1 KB
references/datasheet-verification.mdmarkdown16.5 KB
references/deep-review.mdmarkdown9.7 KB
references/design-intent.mdmarkdown5.6 KB
references/diff-analysis.mdmarkdown17.6 KB
references/file-formats.mdmarkdown15.1 KB
references/gerber-parsing.mdmarkdown33.5 KB
references/manual-gerber-parsing.mdmarkdown24.5 KB
references/manual-pcb-parsing.mdmarkdown17.2 KB
references/manual-schematic-parsing.mdmarkdown12.8 KB
references/net-tracing.mdmarkdown12.0 KB
references/oshwa-certification.mdmarkdown4.5 KB
references/output-schema.mdmarkdown33.4 KB
references/pcb-layout-analysis.mdmarkdown27.3 KB
references/pdf-schematic-extraction.mdmarkdown15.2 KB
references/report-generation.mdmarkdown56.3 KB
references/schematic-analysis.mdmarkdown63.9 KB
references/standards-compliance.mdmarkdown33.5 KB
references/supplementary-data-sources.mdmarkdown12.5 KB
references/what-if.mdmarkdown19.5 KB
review/README.mdmarkdown4.1 KB
review/fixtures/deep_review.example.jsonconfig1.2 KB
review/fixtures/design_context.example.jsonconfig388 B
review/fixtures/review_annotations.example.jsonconfig707 B
review/prompts/design_context.mdmarkdown4.9 KB
review/schemas/deep_review.schema.jsonconfig3.3 KB
review/schemas/design_context.schema.jsonconfig2.2 KB
review/schemas/review_annotations.schema.jsonconfig1.9 KB
review/scripts/_mini_jsonschema.pyscript6.6 KB
review/scripts/build_review_plan.pyscript2.3 KB
review/scripts/deep_review_gate.pyscript27.3 KB
review/scripts/merge_annotations.pyscript7.0 KB
review/scripts/validate_review.pyscript2.6 KB
scripts/.gitignoreother13 B
scripts/README.mdmarkdown23.4 KB
scripts/analysis_cache.pyscript42.1 KB
scripts/analyze_gerbers.pyscript90.9 KB
scripts/analyze_pcb.pyscript7.4 KB
scripts/analyze_schematic.pyscript6.7 KB
scripts/analyze_thermal.pyscript48.5 KB
scripts/analyzer_envelope.pyscript15.5 KB
scripts/capability_mode.pyscript10.2 KB
scripts/check_report_sections.pyscript10.6 KB
scripts/cross_analysis.pyscript69.4 KB
scripts/cross_verify.pyscript23.1 KB
scripts/design_intent.pyscript13.5 KB
scripts/detection_schema.pyscript26.0 KB
scripts/detector_helpers.pyscript15.2 KB
scripts/diff_analysis.pyscript23.5 KB
scripts/diff_engine.pyscript47.2 KB
scripts/domain_detectors.pyscript260.5 KB
scripts/envelopes/__init__.pyscript0 B
scripts/envelopes/cross_analysis.pyscript5.9 KB
scripts/envelopes/gerber.pyscript16.1 KB
scripts/envelopes/pcb.pyscript25.9 KB
scripts/envelopes/schematic.pyscript23.1 KB
scripts/envelopes/thermal.pyscript7.4 KB
scripts/export_issues.pyscript27.6 KB
scripts/fab_release_gate.pyscript29.8 KB
scripts/finding_schema.pyscript25.7 KB
scripts/gen_output_schema_md.pyscript9.2 KB
scripts/inputs_builder.pyscript4.0 KB
scripts/kicad_core/__init__.pyscript0 B
scripts/kicad_core/classify.pyscript32.5 KB
scripts/kicad_core/cli.pyscript4.2 KB
scripts/kicad_core/coords.pyscript2.0 KB
scripts/kicad_core/diagnostics.pyscript1.9 KB
scripts/kicad_core/executables.pyscript1.0 KB
scripts/kicad_core/fields.pyscript5.9 KB
scripts/kicad_core/fileio.pyscript5.4 KB
scripts/kicad_core/hotloop.pyscript3.1 KB
scripts/kicad_core/instances.pyscript5.7 KB
scripts/kicad_core/model.pyscript4.8 KB
scripts/kicad_core/netnames.pyscript19.1 KB
scripts/kicad_core/netquery.pyscript6.7 KB
scripts/kicad_core/pairing.pyscript1.9 KB
scripts/kicad_core/parts.pyscript28.9 KB
scripts/kicad_core/passives.pyscript10.0 KB
scripts/kicad_core/pdn.pyscript1011 B
scripts/kicad_core/project.pyscript43.2 KB
scripts/kicad_core/render.pyscript2.7 KB
scripts/kicad_core/sexp.pyscript12.6 KB
scripts/kicad_core/textvars.pyscript5.4 KB
scripts/kicad_core/token_cache.pyscript2.2 KB
scripts/kicad_core/values.pyscript14.1 KB
scripts/kicad_types.pyscript15.1 KB
scripts/lifecycle_audit.pyscript6.7 KB
scripts/lifecycle_engine.pyscript52.8 KB
scripts/lookup_detectors.pyscript29.9 KB
scripts/lookup_helpers.pyscript3.0 KB
scripts/methodology_gerbers.mdmarkdown23.1 KB
scripts/methodology_pcb.mdmarkdown22.2 KB
scripts/methodology_schematic.mdmarkdown43.1 KB
scripts/netlist_queries.pyscript4.2 KB
scripts/output_filters.pyscript16.8 KB
scripts/output_io.pyscript5.3 KB
scripts/pcb/__init__.pyscript0 B
scripts/pcb/assembly.pyscript58.3 KB
scripts/pcb/connectivity.pyscript27.7 KB
scripts/pcb/copper.pyscript61.0 KB
scripts/pcb/dfm.pyscript56.9 KB
scripts/pcb/geometry.pyscript59.5 KB
scripts/pcb/pipeline.pyscript30.3 KB
scripts/pcb/presentation.pyscript24.3 KB
scripts/pcb/reader.pyscript87.1 KB
scripts/pcb/routing.pyscript53.5 KB
scripts/project_config.pyscript23.1 KB
scripts/risk_summary.pyscript3.1 KB
scripts/run_id.pyscript1.7 KB
scripts/schema_codec.pyscript5.0 KB
scripts/schematic/__init__.pyscript0 B
scripts/schematic/audits.pyscript56.0 KB
scripts/schematic/bom_stats.pyscript6.1 KB
scripts/schematic/connectivity.pyscript62.9 KB
scripts/schematic/erc_pins.pyscript8.4 KB
scripts/schematic/hierarchy.pyscript21.5 KB
scripts/schematic/ic_analysis.pyscript21.4 KB
scripts/schematic/legacy_reader.pyscript49.4 KB
scripts/schematic/net_analysis.pyscript75.5 KB
scripts/schematic/pipeline.pyscript72.2 KB
scripts/schematic/presentation.pyscript20.9 KB
scripts/schematic/reader.pyscript64.7 KB
scripts/schematic/system_analyses.pyscript126.9 KB
scripts/signal_detectors.pyscript248.0 KB
scripts/summarize_findings.pyexecutablescript17.4 KB
scripts/validation_detectors.pyscript75.3 KB
scripts/what_if.pyscript68.4 KB

references/diff-analysis.md

View on GitHub
# Diff Analysis Reference

Compare two KiCad analysis JSON files (base vs head) and report changes. Supports schematic, PCB, EMC, and SPICE analyzer outputs with auto-detection. Zero dependencies — Python 3.10+ stdlib only.

## Table of Contents

1. [Overview](#overview)
2. [CLI Reference](#cli-reference)
3. [Analyzer Types](#analyzer-types)
4. [Severity Classification](#severity-classification)
5. [Identity Matching](#identity-matching)
6. [Output Schema](#output-schema)
7. [Integration with analysis_cache](#integration-with-analysis_cache)
8. [Common User Intents](#common-user-intents)

---

## Overview

The diff pipeline has five stages:

1. **Detect type** -- Read `analyzer_type` from both JSONs (falls back to heuristic key inspection for older files). Reject if types mismatch.
2. **Dispatch** -- Route to the type-specific diff function: `diff_schematic`, `diff_pcb`, `diff_emc`, or `diff_spice`.
3. **Match by identity** -- For list-based sections (components, detections, findings, footprints), build identity maps from each side and partition into added, removed, and matched pairs.
4. **Compare values** -- For matched pairs, compare registered value fields. Numeric deltas below the threshold percentage are suppressed.
5. **Classify severity** -- Walk the diff result and assign an overall severity: `none`, `minor`, `major`, or `breaking`.

The tool operates on pre-analyzed JSON produced by `analyze_schematic.py`, `analyze_pcb.py`, `analyze_emc.py`, or the SPICE pipeline. It never re-parses source files.

**When to use it:**
- Comparing design revisions (base branch vs PR, v1 vs v2).
- Reviewing what changed after a schematic edit.
- Tracking EMC regression/improvement across iterations.
- Verifying SPICE simulation stability after component changes.
- Automated CI gating via severity threshold.

---

## CLI Reference

```
python3 diff_analysis.py <base> <head> [options]
python3 diff_analysis.py --analysis-dir <analysis_dir> [options]
```

### Positional Arguments

| Argument | Description |
|----------|-------------|
| `base` | Path to base (old) analysis JSON (not needed with `--analysis-dir`) |
| `head` | Path to head (new) analysis JSON (not needed with `--analysis-dir`) |

### Options

| Flag | Description |
|------|-------------|
| `--output FILE`, `-o FILE` | Write output to file instead of stdout |
| `--text` | Human-readable text output instead of JSON |
| `--threshold FLOAT` | Ignore numeric deltas below this percentage (default: `1.0`) |
| `--analysis-dir DIR`, `-d DIR` | Resolve base and head from the folder's `manifest.json`; with no `--run`, diffs the previous run against the current one |
| `--run RUN_ID` | Run to compare: give it twice (base, then head), or once to diff that run against the current one. Accepts `current`, `previous`, or a run ID (`YYYY-MM-DD_HHMM`) |
| `--type TYPE` | Output to diff with `--analysis-dir` (`schematic`, `pcb`, `emc`, `spice`, `deep_review`). Default: the first output both runs have; `--trend` defaults to `schematic` |
| `--trend N` | Show metric trends across the last N runs instead of a diff (requires `--analysis-dir`) |
| `--only-deterministic` | Read `analysis/<run>/<analyzer>.json` even when an `analysis/merged/<run>/` overlay exists |

### Exit Codes

| Code | Meaning |
|------|---------|
| 0 | Success |
| 1 | Invalid input, parse error, type mismatch, or unrecognized analyzer type |

---

## Analyzer Types

### Schematic

Diff function: `diff_schematic(base, head, threshold)`

Compared sections:

| Section | Identity Key | Compared Fields | Source Path |
|---------|-------------|-----------------|-------------|
| Statistics | n/a (scalar paths) | `total_components`, `total_nets`, `unique_parts`, `total_wires`, `total_no_connects` | `statistics.*` |
| Components | `reference` | `value`, `footprint`, `mpn` | `components[]` |
| Signal analysis | Per-type via SIGNAL_REGISTRY, else finding identity (below) | Per-type via SIGNAL_REGISTRY, plus `severity`; `summary` for types with no value fields | `findings[]` grouped by detector via `group_findings_by_detection_type()` |
| BOM | `(value, footprint)` tuple | `quantity` | `bom[]` |
| Connectivity | JSON-serialized item, unnamed-net numbers ignored | new/resolved (set diff) | `connectivity_issues.{single_pin_nets,floating_nets,multi_driver_nets}` |
| ERC warnings | `(type, net, message)` tuple; on an unnamed net, its pins instead of its number | new/resolved (set diff) | `design_analysis.erc_warnings[]` |

Signal analysis is reconstructed from `findings[]` via `group_findings_by_detection_type()`, then iterates all detector types present in either base or head. For each detection type, identity and value fields come from `SIGNAL_REGISTRY` (derived from `detection_schema.SCHEMAS`). Unknown detection types fall back to `["reference"]` identity with no value fields. A detection keeps that registry key (its `detection_id` first) only when no other finding of its type shares it in either run; every other finding is matched by its identity (`diff_engine.finding_key`): its `finding_id`, unless the id is positional — a `#N` collision suffix, or a locator naming an `__unnamed_N` net — in which case a content key of `rule_id`, sorted nets (unnamed-net numbers dropped), sorted components and `summary`. Findings that still share a key are numbered after sorting by content, so list order never pairs two different findings, and a renumbered unnamed net never reads as a change. Severities compare by meaning (legacy `WARN` = `warning`). The diff output still uses `signal_analysis` as a key for backward compatibility with diff consumers.

### PCB

Diff function: `diff_pcb(base, head, threshold)`

| Section | Identity Key | Compared Fields | Source Path |
|---------|-------------|-----------------|-------------|
| Statistics | n/a (scalar paths) | `footprint_count`, `track_segments`, `via_count`, `zone_count`, `net_count`, `copper_layers_used`, `board_width_mm`, `board_height_mm`, `total_track_length_mm` | `statistics.*` |
| Routing completeness | n/a (scalar) | `routing_complete`, `unrouted_count` | `connectivity.*` |
| Footprints | `reference` | `value`, `footprint` (the `Lib:Name` FPID; `library` or `lib_id` in older JSON), `layer` | `footprints[]` |
| Findings | finding identity (as schematic) | `severity` (new/resolved/changed) | `findings[]` |

### EMC

Diff function: `diff_emc(base, head, threshold)`

| Section | Identity Key | Compared Fields | Source Path |
|---------|-------------|-----------------|-------------|
| Risk score | n/a (scalar) | `emc_risk_score` (0 = worst, 100 = lowest risk; a fall is a regression) | `summary.emc_risk_score` |
| Severity distribution | n/a (scalar paths) | `error`, `warning`, `info` (`critical`, `high`, `medium`, `low`, `info` in pre-v1.4 output) | `summary.by_severity.*` (`summary.*`) |
| Findings | finding identity (as schematic); `rule_id::sorted(nets)::sorted(components)` for findings without a `finding_id` | `severity` (new/resolved/changed) | `findings[]` |
| Per-net scores | `net` | `score` (filtered by threshold) | `per_net_scores[]` |

Per-net score changes are sorted by absolute delta (largest first).

### SPICE

Diff function: `diff_spice(base, head, threshold)`

| Section | Identity Key | Compared Fields | Source Path |
|---------|-------------|-----------------|-------------|
| Summary counts | n/a (scalar paths) | `pass`, `warn`, `fail`, `skip`, `info`, `total` | `summary.*` |
| Simulation results | `subcircuit_type::sorted(components)` | `status` (transitions annotated) | `simulation_results[]` |
| Monte Carlo concerns | `subcircuit_type::metric` | new/resolved (set diff) | `monte_carlo_summary.concerns[]` |

Status transitions from `pass` to `fail` or `warn` are annotated as regressions with up to 3 delta fields from the result.

---

## Severity Classification

Function: `classify_severity(analyzer_type, diff_result)`

Evaluation order (first match wins):

### Breaking

| Analyzer | Condition |
|----------|-----------|
| SPICE | Any `status_changes` entry where `base_status == "pass"` and `head_status == "fail"` |
| EMC | Any new finding whose normalized severity is `error` (legacy `CRITICAL` or `HIGH`) |
| Schematic | Any new ERC warning (`erc.new_warnings` non-empty) |

### Major

| Condition |
|-----------|
| `signal_analysis` key present in diff |
| `components` key present in diff |
| `findings` key present in diff (EMC) |
| `status_changes` key present in diff (SPICE) |
| `footprints` with any added, removed, or modified entries (PCB) |
| `routing_complete` or `unrouted` present (PCB) |

### Minor

| Condition |
|-----------|
| Any other non-empty section: `statistics`, EMC `risk_score`, `by_severity` or `per_net_scores`, `bom`, `connectivity`, resolved-only `erc`, SPICE `summary`, `new_results`, `removed_results` or `monte_carlo`, assessments added or removed |

### None

No section changed (an `assessments` block holding only `unchanged_count` is not a change).

### Regressions

`classify_regressions(analyzer_type, diff_result)` lists changes that made the design worse: new ERC warnings, new connectivity issues and removed protection devices (schematic), new error-severity findings and a fall in the EMC risk score (EMC; the score is 0 = worst, 100 = lowest risk), pass-to-fail transitions (SPICE), and an increase in unrouted nets (PCB).

---

## Identity Matching

### SIGNAL_REGISTRY

`SIGNAL_REGISTRY` is derived at import time from `detection_schema.SCHEMAS`:

```python
SIGNAL_REGISTRY = {dt: (s.identity_fields, s.value_fields) for dt, s in _SCHEMAS.items()}
```

Each detection type maps to `(identity_fields, value_fields)` where both are lists of dotpath strings.

**Registered detection types and their identity/value fields:**

| Detection Type | Identity Fields | Value Fields |
|---------------|-----------------|--------------|
| `rc_filters` | `resistor.ref`, `capacitor.ref` | `cutoff_hz` |
| `lc_filters` | `inductor.ref`, `capacitor.ref` | `resonant_hz` |
| `voltage_dividers` | `r_top.ref`, `r_bottom.ref` | `ratio`, `vout_estimated` |
| `feedback_networks` | `r_top.ref`, `r_bottom.ref` | `ratio` |
| `opamp_circuits` | `reference` | `gain`, `gain_dB`, `configuration` |
| `crystal_circuits` | `reference` | `frequency`, `effective_load_pF` |
| `current_sense` | `shunt.ref` | `max_current_50mV_A`, `max_current_100mV_A` |
| `power_regulators` | `ref` | `vout_estimated`, `topology` |
| `transistor_circuits` | `reference` | `type` |
| `protection_devices` | `reference`, `type` | `protected_net` |
| `bridge_circuits` | `topology` | (none) |
| `rf_matching` | `antenna_ref` | (none) |
| `bms_systems` | `bms_reference` | `cell_count` |
| `decoupling_analysis` | `rail_net` | (none) |
| `rf_chains` | (none) | (none) |
| `ethernet_interfaces` | `phy_ref` | (none) |
| `memory_interfaces` | `type` | (none) |
| `isolation_barriers` | `isolator_ref` | (none) |
| `snubber_circuits` | (none) | (none) |

### Dotpath Resolution

Identity and value fields use dotted paths (e.g., `r_top.ref`) resolved by `_resolve()`. Each segment indexes into nested dicts. Returns `None` if any segment is missing.

### Identity Key Building

`_identity_key(item, fields)` extracts the value at each dotpath and joins them with `::`. List values are sorted and joined with `|`. If any field resolves to `None`, the entire key is `None` and the item is excluded from matching.

Example: for a voltage divider with `r_top.ref = "R1"` and `r_bottom.ref = "R2"`, the identity key is `R1::R2`.

### Generic Fallback

When a detection type is not in `SIGNAL_REGISTRY`, `_generic_identity()` is used. It tries:

1. Top-level `reference` or `ref` field.
2. Any nested dict with a `ref` sub-key.

Returns `None` if nothing is found. The diff then matches the item by its `finding_id`, or, without one, by a content key (rule id, nets, components and summary); only the multi-run trend extraction skips it.

### Validation

`validate_signal_registry(sample_output)` checks that every key in `SIGNAL_REGISTRY` has at least one finding with a matching detector in `findings[]`. Returns warning strings for any missing keys. Useful for catching stale registry entries after schema changes.

---

## Output Schema

### Top-Level Structure

```json
{
  "diff_version": "1.0",
  "analyzer_type": "schematic|pcb|emc|spice",
  "base_file": "/path/to/base.json",
  "head_file": "/path/to/head.json",
  "has_changes": true,
  "summary": {
    "total_changes": 5,
    "added": 2,
    "removed": 1,
    "modified": 2,
    "metric_changes": ["statistics.total_components"],
    "severity": "major"
  },
  "diff": { ... }
}

```

### Summary Counts

`summary.total_changes` = `added + removed + modified`, each counting listed items:

| Analyzer | Added | Removed | Modified |
|----------|-------|---------|----------|
| Schematic | New components, detections, BOM lines, connectivity issues, ERC warnings | Removed components, detections, BOM lines; resolved connectivity issues and ERC warnings | Changed components and detections; BOM quantity changes |
| PCB | New footprints + new findings | Removed footprints + resolved findings | Changed footprints + severity-changed findings |
| EMC, thermal | New findings | Resolved findings | Severity-changed findings; changed per-net scores (EMC) |
| SPICE | New simulation results + new Monte Carlo concerns | Removed simulation results + resolved Monte Carlo concerns | Status-changed results |

Assessments added or removed count on every analyzer type.

`summary.metric_changes` lists, sorted, the analyzer-output paths of the scalars that moved: `statistics.*`, `connectivity.routing_complete`, `connectivity.unrouted_count`, `summary.emc_risk_score`, `summary.by_severity.*` and the SPICE `summary.*` counts. They are not in `total_changes`, so one added part is not counted again through every rollup it moves.

`has_changes` is true when any diff section changed, including a metric-only change (`total_changes` 0).

### Diff Section (by analyzer type)

The `diff` object contains only sections with actual changes. Empty sections are omitted.

**Schematic diff keys:** `statistics`, `components`, `signal_analysis`, `bom`, `connectivity`, `erc`

**PCB diff keys:** `statistics`, `routing_complete`, `unrouted`, `footprints`, `findings`

**EMC diff keys:** `risk_score`, `by_severity`, `findings`, `per_net_scores`

**SPICE diff keys:** `summary`, `status_changes`, `new_results`, `removed_results`, `monte_carlo`

### List Diff Format

All list-based sections (components, signal analysis detections, footprints) use the same structure:

```json
{
  "added": [{ "reference": "R5", "value": "10k", ... }],
  "removed": [{ "reference": "R3", "value": "4.7k", ... }],
  "modified": [{
    "identity": "R1/R2",
    "changes": [{
      "field": "ratio",
      "base": 0.5,
      "head": 0.33,
      "delta_pct": -34.0
    }]
  }],
  "unchanged_count": 12
}
```

The `delta_pct` field is only present for numeric comparisons where the base value is nonzero.

### Text Output

The `--text` flag renders a summary header followed by per-section detail. Items are capped at `MAX_TEXT_ITEMS` (20) with a "... and N more changes" footer counting the listed items not printed. Per-section caps: 5 items for components/footprints/findings, 3 items for signal analysis detections per type. Routing, unrouted and statistics changes print as `base → head` lines; the findings block is labelled by source (`EMC Findings:`, `PCB Findings:`, `Thermal Findings:`). `--output` files are written as UTF-8. When both runs hashed the same source file contents with the same config, a second line says the design files are unchanged and the changes come from the analyzer; JSON mode prints that sentence to stderr.

Format:

```
Design Changes: schematic (major) — 5 changes
  +2 added, -1 removed, ~2 modified

Components:
  + R5 10k 0402
  - R3 4.7k 0603
  ~ R1: value 10k → 4.7k

Signal Analysis:
  + New Voltage Dividers: r_top_ref=R5 r_bottom_ref=R6
  ~ Rc Filters R1/C3: cutoff_hz 1591.55 → 3386.28
```

---

## Integration with analysis_cache

`analysis_cache.should_create_new_run()` uses diff_analysis programmatically to decide whether new analyzer outputs warrant a new timestamped run folder.

**Protocol:**

1. Import `diff_engine` (adding the scripts directory to `sys.path` if needed).
2. For each output type present in both the current run and the new outputs, load both JSONs.
3. Read `analyzer_type` from the base JSON and dispatch to the matching diff function (`diff_schematic`, `diff_pcb`, `diff_emc`, `diff_spice`).
4. Call `classify_severity()` on the diff result.
5. If any severity meets or exceeds the configured threshold (default: `major`), return `True` (create new run). At the default a finding- or routing-only change starts a new run; a statistics- or score-only change (`minor`) overwrites the current one.
6. If no current run exists, return `True` (first run).
7. If all diffs are below threshold, return `False` (overwrite current run).

The threshold comparison uses a severity ordering: `none=0`, `minor=1`, `major=2`, `breaking=3`.

---

## Common User Intents

Natural-language queries and their corresponding command invocations.

| User Says | Command |
|-----------|---------|
| "What changed between these two analyses" | `diff_analysis.py old.json new.json --text` |
| "Show me changes as JSON" | `diff_analysis.py old.json new.json` |
| "Ignore small changes" | `diff_analysis.py old.json new.json --threshold 5.0 --text` |
| "Compare my schematic revisions" | `diff_analysis.py base.json head.json --text` |
| "Did the EMC risk get worse" | `diff_analysis.py emc_old.json emc_new.json --text` |
| "Any SPICE regressions" | `diff_analysis.py spice_old.json spice_new.json --text` |
| "Save the diff report" | `diff_analysis.py base.json head.json --output diff.json` |
| "Diff my last two runs" | `diff_analysis.py --analysis-dir analysis/ --text` |
| "Show trends over time" | `diff_analysis.py --analysis-dir analysis/ --trend 5 --text` |
finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the workStars: 321kUpdated Claude CodeCodexVerifiedInstall
systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixesStars: 321kUpdated Claude CodeCodexVerifiedInstall
test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation codeStars: 321kUpdated Claude CodeCodexVerifiedInstall
skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.Stars: 197kUpdated Claude CodeCodexVerifiedInstall