Move all three skills into skills/; add root README; fix paths

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>

.gitignore

@@ -4,3 +4,4 @@ node_modules/
 .venv/
 .claude/worktrees/
 rpa-run-tab/logs/
+skills/rpa-run-tab/logs/

CLAUDE.md

@@ -1,6 +1,6 @@
 # RPA SKILLS
 
-Shared Claude skills for building RPA dashboards: `rpa-dashboard-no-ai`, `rpa-dashboard-ai`, and `rpa-run-tab` (Tebra-style Run tab). See `PLAN.md`.
+Shared Claude skills for RPA bots, all in `skills/`: `rpa-run-tab` (Tebra-style Run tab), `rpa-dashboard-no-ai` and `rpa-dashboard-ai`. See `README.md` and `PLAN.md`.
 
 ## Agent skills
 

PLAN.md

@@ -73,12 +73,12 @@ Build both in `D:\RPA SKILLS\<skill-name>\`. The user installs them into Claude
 ## Status: what already exists
 
 ```
-rpa-dashboard-no-ai/
+skills/rpa-dashboard-no-ai/
   templates/dashboard.html     DONE: generic page, works in Qt (QWebChannel) or web (polling)
   templates/contract.md        DONE: event/JSON contract + Tebra lessons
   templates/bridge.py          DONE: minimal PyQt6 host + subprocess log tailing
   templates/reference/         DONE: tebra_dashboard.html, tebra_bridge_part1/2.py (raw extracts)
-rpa-dashboard-ai/
+skills/rpa-dashboard-ai/
   templates/reference/web/     DONE: Superbill index.css, DESIGN.md, bands.ts, theme.tsx, types.ts, api.ts,
                                      components (BrandHeader, Sidebar, StatsBar, Donut, SplitPane,
                                      RunPanel, ReviewPane, RoiTab, PdfPane, Tooltip, icons)
@@ -86,24 +86,24 @@ rpa-dashboard-ai/
 ```
 
 ## TODO for the implement skill
-1. **Fix the lint error in `rpa-dashboard-no-ai/templates/bridge.py:15`.** `STEPS = {{STEPS_PY}}` is not valid Python, so the lint hook flags it (F821). Change it to `STEPS = ["{{STEP_1}}", "{{STEP_2}}"]` or similar.
-2. **Write `rpa-dashboard-no-ai/SKILL.md`.**
+1. **Fix the lint error in `skills/rpa-dashboard-no-ai/templates/bridge.py:15`.** `STEPS = {{STEPS_PY}}` is not valid Python, so the lint hook flags it (F821). Change it to `STEPS = ["{{STEP_1}}", "{{STEP_2}}"]` or similar.
+2. **Write `skills/rpa-dashboard-no-ai/SKILL.md`.**
    - Frontmatter `name` and `description`. The trigger should cover "RPA dashboard", "automation dashboard", "bot dashboard", and "without AI".
    - The workflow above.
    - Point to `templates/*`.
-3. **Write `rpa-dashboard-ai/SKILL.md`.**
+3. **Write `skills/rpa-dashboard-ai/SKILL.md`.**
    - Trigger: "AI RPA dashboard", "extraction dashboard", "LLM/OCR review dashboard".
    - The workflow above.
    - Web path: React + Vite + Tailwind v4, adapted from `reference/web`.
    - Desktop path: copy the no-AI `dashboard.html`, then add the AI sections.
 4. **Write `templates/themes.md` in both skills.** Content is in the Theme presets section above.
-5. **Write `rpa-dashboard-ai/templates/contract.md`.** It extends the no-AI contract with:
+5. **Write `skills/rpa-dashboard-ai/templates/contract.md`.** It extends the no-AI contract with:
    - `Run{job_id,status:pending|queued|running|done|failed,model,pages_done,pages_total,summary:{green,amber,red,unscored}}`
    - `ReviewRow{row_id,field,value,band,score,reason,verified,corrected_value}`
    - `RoiRun{model,input_tokens,output_tokens,thinking_tokens,total_cost}`
    - Endpoints: `PATCH /review/{row_id}`, `POST /runs/{id}/approve` (server gate), `GET /roi`.
    - Polling: 1.5–2s only while a run is busy.
-6. **Write `rpa-dashboard-ai/templates/ai-sections.html`.** Plain HTML/CSS/JS versions of the band legend, the review split pane and the ROI tiles, for the desktop path.
+6. **Write `skills/rpa-dashboard-ai/templates/ai-sections.html`.** Plain HTML/CSS/JS versions of the band legend, the review split pane and the ROI tiles, for the desktop path.
 7. **Strip project-specific bits from the AI reference files.** Remove ECW/Tebra project names, SPB_* tables and patient/ticket wording, or mark them as such. **Never** ship real patient data (PHI), internal IPs or keys. The reference copies have already been checked for these, but check again after editing.
 8. **Verify.** Open `dashboard.html` in a browser using sample data. Check light, dark and narrow width. Load each SKILL.md and make sure every path it references exists.
 

README.md

@@ -0,0 +1,30 @@
+# RPA SKILLS
+
+Claude skills for building the dashboard of an RPA bot. All three live in [`skills/`](skills/).
+
+| Skill | Use it when | What it builds |
+|---|---|---|
+| [`rpa-run-tab`](skills/rpa-run-tab/README.md) | You have a PyQt6 desktop bot and only need a Run tab, in about 5 minutes. | The Tebra-style Run tab: trigger button, Excel input, progress, checkpoints, live log, dark mode. |
+| [`rpa-dashboard-no-ai`](skills/rpa-dashboard-no-ai/SKILL.md) | The bot has no AI step. | A full dashboard: run panel, overview, report, optional sections (checkpoints, admin, login). Desktop (PyQt) or web. |
+| [`rpa-dashboard-ai`](skills/rpa-dashboard-ai/SKILL.md) | The bot uses an LLM or OCR. | Everything in the no-AI skill, plus confidence bands, review-and-approve (the server refuses approval until fields are verified), and a cost/ROI page. |
+
+## Install
+
+Copy the skill folders you need from `skills/` into `~/.claude/skills/`.
+`rpa-dashboard-ai` reuses files from `rpa-dashboard-no-ai`, so install the two dashboard skills together, side by side.
+
+## Use
+
+In your bot's project, ask Claude for what you want, for example *"add the run tab"* or *"build an RPA dashboard"*.
+If the project already has a frontend, the dashboard skills report it and ask whether to keep its look or restyle it.
+
+## Repo layout
+
+| Path | What it is |
+|---|---|
+| `skills/` | The three skills |
+| `tests/` | Template tests, page checks (Playwright) and skill evals. See [`tests/README.md`](tests/README.md). |
+| `PLAN.md`, `GLOSSARY.md`, `docs/` | Background, domain terms and decisions |
+| `.scratch/` | Spec and tickets |
+
+Run all tests: `uv run --with pytest --with playwright pytest tests`

docs/adr/0002-bot-talks-through-tagged-log-file.md

@@ -8,4 +8,4 @@ The bot runs as a **separate process** with no Qt. The Run tab starts it with `-
 
 **Why:** this comes from Tebra Auto Post. UI automation inside a Qt worker thread was unreliable (bug-094). A windowed PyInstaller child's stdout pipe is block-buffered, so log lines arrived in late bursts; reading the log file fixed that. Tagging lines saves each project from writing a table of phrase→friendly-text rules.
 
-**Conflict:** `rpa-dashboard-no-ai/templates/bot_runner.py` reads `stdout=PIPE`, which is the approach Tebra dropped. Fix it there, or point it at the Run tab skill's runner.
+**Conflict:** `skills/rpa-dashboard-no-ai/templates/bot_runner.py` reads `stdout=PIPE`, which is the approach Tebra dropped. Fix it there, or point it at the Run tab skill's runner.

skills/rpa-run-tab/README.md

@@ -0,0 +1,35 @@
+# rpa-run-tab
+
+A Claude skill that adds a **Tebra-style Run tab** to any desktop RPA bot (PyQt6) in about 5 minutes.
+
+## What you get
+- **Trigger button** with three states: Upload a file / Trigger automation / Running...
+- **Excel input card:** drop zone, sheet tabs, a 200-row preview with passwords masked, and a Sample input download
+- **Progress bar** with an elapsed timer, a step list and a friendly live log
+- **Checkpoint boxes** with time limits. A stuck checkpoint is killed and shown in red.
+- **Endings:** green Completed, amber "N of M failed", red Failed or Stuck
+- **Dark mode** and a close-while-running guard. The bot runs in its own process.
+
+## Install
+Copy this folder to `~/.claude/skills/rpa-run-tab/`.
+
+## Use
+In your bot project, ask Claude: *"add the run tab"*. The skill:
+1. Scans your bot. It never runs it.
+2. Asks three things: **colour** (Tebra Sky, TVL Teal, or your hex), **checkpoints** (names and time limits), and **Excel input or none**.
+3. Builds `run_tab/` and adds a few `rt.checkpoint()` / `rt.ui()` lines to your bot.
+4. Checks the result with a fake bot (`python run_tab/run_tab.py --selfcheck`).
+
+Start it with `python run_tab/run_tab.py`.
+
+## Files
+| File | What it is |
+|---|---|
+| `SKILL.md` | Steps Claude follows |
+| `templates/run_tab.html` | The page (layout fixed, colours themable) |
+| `templates/run_tab.py` | PyQt6 window and bridge, plus the CONFIG block and `--selfcheck` |
+| `templates/runner.py` | Starts the bot, reads its log, handles stuck checkpoints and the ending |
+| `templates/rt.py` | Helpers the bot calls |
+| `templates/fake_bot.py` | Fake bot used by the self-check |
+| `templates/palette.py` | Colour presets or a custom hex, with a contrast check |
+| `docs/adr/` | Why it works this way |

tests/README.md

@@ -72,4 +72,4 @@ uv run --with pytest --with playwright pytest tests
   passwords, checkpoints driving steps/boxes/progress, green/amber/red endings, the no-input
   mode, the dark toggle and no horizontal scroll, each in light, dark and narrow mode. The
   Python side covers line parsing, endings, the sample workbook and `palette.py --write`.
-  The end-to-end fake-bot check lives in the skill itself: `python rpa-run-tab/templates/run_tab.py --selfcheck`.
+  The end-to-end fake-bot check lives in the skill itself: `python skills/rpa-run-tab/templates/run_tab.py --selfcheck`.

tests/evals/run_eval.py

@@ -202,7 +202,7 @@ def main(fixture):
         shutil.copy(pages[0], results / f"{fixture}.dashboard.html")
         checks["no placeholders left"] = "{{" not in html
         if cfg.get("brand"):
-            spec = importlib.util.spec_from_file_location("palette", ROOT / "rpa-dashboard-no-ai/templates/palette.py")
+            spec = importlib.util.spec_from_file_location("palette", ROOT / "skills/rpa-dashboard-no-ai/templates/palette.py")
             palette = importlib.util.module_from_spec(spec)
             spec.loader.exec_module(palette)
             t = palette.derive(cfg["brand"])

tests/page_check/conftest.py

@@ -16,7 +16,7 @@ import pytest
 from page_check_common import FAKE_BRIDGE, MODES, TEST_FILL, WIRED, open_page
 
 ROOT = Path(__file__).resolve().parents[2]
-TEMPLATE = ROOT / "rpa-dashboard-no-ai" / "templates" / "dashboard.html"
+TEMPLATE = ROOT / "skills" / "rpa-dashboard-no-ai" / "templates" / "dashboard.html"
 
 
 @pytest.fixture(scope="session")

tests/page_check_ai/conftest.py

@@ -23,7 +23,7 @@ import pytest
 from page_check_common import MODES, TEST_FILL, load_stub, open_page
 
 ROOT = Path(__file__).resolve().parents[2]
-TEMPLATE = ROOT / "rpa-dashboard-ai" / "templates" / "web"
+TEMPLATE = ROOT / "skills" / "rpa-dashboard-ai" / "templates" / "web"
 TEST_FILL = {**TEST_FILL, "APP_NAME": "Test Extractor", "API_BASE": "/api"}
 RECORD_ACTIONS = """
 window.__calls = [];

tests/page_check_ai_desktop/conftest.py

@@ -22,8 +22,8 @@ import pytest
 from page_check_common import FAKE_BRIDGE, MODES, TEST_FILL, WIRED, load_stub, open_page
 
 ROOT = Path(__file__).resolve().parents[2]
-NO_AI = ROOT / "rpa-dashboard-no-ai" / "templates" / "dashboard.html"
-AI = ROOT / "rpa-dashboard-ai" / "templates"
+NO_AI = ROOT / "skills" / "rpa-dashboard-no-ai" / "templates" / "dashboard.html"
+AI = ROOT / "skills" / "rpa-dashboard-ai" / "templates"
 
 
 @pytest.fixture(scope="session")

tests/page_check_run_tab/conftest.py

@@ -9,7 +9,7 @@ import pytest
 from page_check_common import FAKE_BRIDGE, MODES, open_page
 
 ROOT = Path(__file__).resolve().parents[2]
-TEMPLATE = ROOT / "rpa-run-tab" / "templates" / "run_tab.html"
+TEMPLATE = ROOT / "skills" / "rpa-run-tab" / "templates" / "run_tab.html"
 CFG = {"title": "Test Bot", "sub": "Page check", "input": True, "inputHint": "Test workbook",
        "sample": True, "darkKey": "test_dark",
        "checkpoints": [{"name": "Sign in", "max": 300}, {"name": "Process rows", "max": 0},

tests/test_bands.py

@@ -3,7 +3,7 @@ import importlib.util
 import re
 from pathlib import Path
 
-BANDS = Path(__file__).resolve().parents[1] / "rpa-dashboard-ai" / "templates" / "web" / "bands.py"
+BANDS = Path(__file__).resolve().parents[1] / "skills" / "rpa-dashboard-ai" / "templates" / "web" / "bands.py"
 spec = importlib.util.spec_from_file_location("bands", BANDS)
 bands = importlib.util.module_from_spec(spec)
 spec.loader.exec_module(bands)

tests/test_bot_runner.py

@@ -7,7 +7,7 @@ from pathlib import Path
 
 import pytest
 
-RUNNER = Path(__file__).resolve().parents[1] / "rpa-dashboard-no-ai" / "templates" / "bot_runner.py"
+RUNNER = Path(__file__).resolve().parents[1] / "skills" / "rpa-dashboard-no-ai" / "templates" / "bot_runner.py"
 
 
 @pytest.fixture

tests/test_detect_frontend.py

@@ -5,7 +5,7 @@ import subprocess
 import sys
 from pathlib import Path
 
-DETECT = Path(__file__).resolve().parents[1] / "rpa-dashboard-no-ai" / "templates" / "detect_frontend.py"
+DETECT = Path(__file__).resolve().parents[1] / "skills" / "rpa-dashboard-no-ai" / "templates" / "detect_frontend.py"
 spec = importlib.util.spec_from_file_location("detect_frontend", DETECT)
 detect_frontend = importlib.util.module_from_spec(spec)
 spec.loader.exec_module(detect_frontend)

tests/test_palette.py

@@ -4,7 +4,7 @@ import subprocess
 import sys
 from pathlib import Path
 
-PALETTE = Path(__file__).resolve().parents[1] / "rpa-dashboard-no-ai" / "templates" / "palette.py"
+PALETTE = Path(__file__).resolve().parents[1] / "skills" / "rpa-dashboard-no-ai" / "templates" / "palette.py"
 spec = importlib.util.spec_from_file_location("palette", PALETTE)
 palette = importlib.util.module_from_spec(spec)
 spec.loader.exec_module(palette)

tests/test_pricing.py

@@ -5,7 +5,7 @@ from pathlib import Path
 
 import pytest
 
-SRC = Path(__file__).resolve().parents[1] / "rpa-dashboard-ai" / "templates" / "web" / "pricing.py"
+SRC = Path(__file__).resolve().parents[1] / "skills" / "rpa-dashboard-ai" / "templates" / "web" / "pricing.py"
 spec = importlib.util.spec_from_file_location("pricing", SRC)
 pricing = importlib.util.module_from_spec(spec)
 spec.loader.exec_module(pricing)

tests/test_reference_scan.py

@@ -6,8 +6,8 @@ from pathlib import Path
 import pytest
 
 ROOT = Path(__file__).resolve().parents[1]
-SKILLS = [ROOT / "rpa-dashboard-ai", ROOT / "rpa-dashboard-no-ai"]
-AI_REFERENCE = ROOT / "rpa-dashboard-ai" / "templates" / "reference"
+SKILLS = [ROOT / "skills" / "rpa-dashboard-ai", ROOT / "skills" / "rpa-dashboard-no-ai"]
+AI_REFERENCE = ROOT / "skills" / "rpa-dashboard-ai" / "templates" / "reference"
 FORBIDDEN = {
     "internal IP": r"\b(10\.\d{1,3}|192\.168|172\.(1[6-9]|2\d|3[01]))\.\d{1,3}\.\d{1,3}\b",
     "Google API key": r"AIza[0-9A-Za-z_-]{30,}",

tests/test_run_tab.py

@@ -4,7 +4,7 @@ import sys
 from pathlib import Path
 
 ROOT = Path(__file__).resolve().parents[1]
-T = ROOT / "rpa-run-tab" / "templates"
+T = ROOT / "skills" / "rpa-run-tab" / "templates"
 sys.path.insert(0, str(T))
 import runner  # noqa: E402
 

tests/test_sections.py

@@ -10,7 +10,7 @@ from pathlib import Path
 import pytest
 
 ROOT = Path(__file__).resolve().parents[1]
-TEMPLATES = ROOT / "rpa-dashboard-no-ai" / "templates"
+TEMPLATES = ROOT / "skills" / "rpa-dashboard-no-ai" / "templates"
 spec = importlib.util.spec_from_file_location("sections", TEMPLATES / "sections.py")
 sections = importlib.util.module_from_spec(spec)
 spec.loader.exec_module(sections)

tests/test_templates.py

@@ -10,9 +10,9 @@ ROOT = Path(__file__).resolve().parents[1]
 HOOK_RULES = "E9,F63,F7,F82,F811"  # same rule set as the PostToolUse lint hook
 
 
-@pytest.mark.parametrize("template", ["rpa-dashboard-no-ai/templates/bridge.py",
-                                      "rpa-dashboard-no-ai/templates/bot_runner.py",
-                                      "rpa-dashboard-ai/templates/desktop/ai_bridge.py"])
+@pytest.mark.parametrize("template", ["skills/rpa-dashboard-no-ai/templates/bridge.py",
+                                      "skills/rpa-dashboard-no-ai/templates/bot_runner.py",
+                                      "skills/rpa-dashboard-ai/templates/desktop/ai_bridge.py"])
 def test_template_passes_lint_hook_unfilled(template):
     ruff = shutil.which("ruff") or pytest.skip("ruff not on PATH")
     r = subprocess.run([ruff, "check", "--select", HOOK_RULES, "--no-cache", str(ROOT / template)],
@@ -21,7 +21,7 @@ def test_template_passes_lint_hook_unfilled(template):
 
 
 def test_tebra_sky_preset_is_the_template_default():
-    templates = ROOT / "rpa-dashboard-no-ai" / "templates"
+    templates = ROOT / "skills" / "rpa-dashboard-no-ai" / "templates"
     themes = (templates / "themes.md").read_text(encoding="utf-8")
     sky = themes.split("## 1. Tebra Sky")[1].split("```css\n")[1].split("```")[0]
     assert sky in (templates / "dashboard.html").read_text(encoding="utf-8")
@@ -29,13 +29,13 @@ def test_tebra_sky_preset_is_the_template_default():
 
 @pytest.mark.parametrize("skill", ["rpa-dashboard-no-ai", "rpa-dashboard-ai"])
 def test_skill_description_fits_the_1024_char_limit(skill):
-    text = (ROOT / skill / "SKILL.md").read_text(encoding="utf-8")
+    text = (ROOT / "skills" / skill / "SKILL.md").read_text(encoding="utf-8")
     description = re.search(r"^description: (.+)$", text, re.MULTILINE)[1]
     assert len(description) <= 1024, len(description)
 
 
 def test_ai_skill_references_files_that_exist():
-    skill = ROOT / "rpa-dashboard-ai"
+    skill = ROOT / "skills" / "rpa-dashboard-ai"
     text = (skill / "SKILL.md").read_text(encoding="utf-8")
     paths = re.findall(r"`((?:templates/|<no-ai>)[\w./-]+)`", text)
     assert len(paths) > 5