SKILL.md step 4 now tells Claude to render the SOP as one styled HTML page
(A4, 1.8 cm margins, 10.5 pt sans, bordered tables with a shaded header,
grey email box) and print it with headless Chrome or Edge, then look at
every page. The skill is one 54-line SKILL.md. Tests updated; the docx
selfcheck test is removed with the converter.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The skill is now one SKILL.md (54 lines) with the SOP shape inline, plus
templates/to_docx.py for the Word and PDF. Removed: the template, the MEK
reference example and the skill README. The converter's selfcheck uses a
built-in sample. Tests now check the skill is that one short file, has the
6 don't-miss checks, and its SOP shape has the 5 sections and To/CC lines.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The skill itself read as too detailed. SKILL.md is now a short checklist
(460 words, was 1,321): 5 steps, 5 rules, and 6 one-line "don't miss"
checks that replace the 12 Tebra failure classes (failure-classes.md
removed). The MEK Charge Reconciliation SOP - the 3-page PDF ops liked -
replaces the Tebra example as the model (emails swapped for examples).
New test keeps SKILL.md under 500 words with 6 checks.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- Section 5 of the SOP now names a real "To" (the developer) and "CC"
(the developer's manager, not the operator's), and the email block to
copy starts with To: and CC: lines. The skill asks for both addresses.
- to_docx.py --pdf also writes the PDF (Word through PowerShell on Windows,
LibreOffice elsewhere) and prints the real page count against MAX_PAGES.
The PDF is what ops gets.
- Tebra reference and README updated; new test for the To/CC lines.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The first real handover (MEK Charge Reconciliation) came out at 9 pages.
Ops want it short: which URL to open and what to click, what shows where
after the click, what to do when an exception comes, and how to email us.
- Output is "<Project Name> Handover SOP" (HANDOVER-SOP.md + .docx) with
5 sections: how to run, what you see while it runs, result, when
something goes wrong, email us. HANDOVER-DEV.md is dropped; dev-team
findings go in the chat.
- At most ~1,400 words; to_docx.py prints the word count and flags overflow,
and renders *italic* for the variable parts of messages.
- Every quoted message, label and URL is checked against the code. The SOP
must say what clicking Run again does to the data.
- One scan subagent; failure classes stay as a scan checklist.
- Tebra reference rewritten in the SOP format; test, README, glossary
updated; ADR-0005 supersedes ADR-0004.
The handoff eval runner (tests/evals/run_handoff_eval.py) still grades an
older 13-section format and was already out of date; not touched here.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
New last step: templates/to_docx.py turns the finished HANDOVER.md into a
Word document (python-docx), the skill checks it and gives that path to
the user as the deliverable. --selfcheck converts the Tebra example and
is run by tests/test_templates.py.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The skill scans a bot with subagents (never runs it) and writes
HANDOVER.md, an 11-section ops guide in the operator's order: where is
what, how to run, how long to wait, after the run, how to see an
exception, exception list, how you will know, how to tell us, don'ts,
issues seen before. Dev material (check against 12 failure classes from
Tebra Auto Post, gaps with file:line, incidents) goes to HANDOVER-DEV.md.
Also adds ADR-0004, glossary terms, five fixture bots and a handoff eval
runner (--resume, --regrade) with results from 47 runs of the earlier
13-section version. The grader still expects that structure and must be
updated before the next eval run.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The Run tab from Tebra Auto Post, scrubbed and themable (Tebra Sky, TVL Teal,
or a custom hex checked for contrast). The skill wires the real bot through
tagged log-file lines and checks itself with a fake bot (complete, partial,
stuck, crash) plus light and dark screenshots. Grill decisions R1-R14 are in
PLAN.md, terms in GLOSSARY.md, and ADRs 0001-0003.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
AI description trimmed to 754 chars (test: both stay <= 1024). Both SKILL.md files say templates/ (and <no-ai>) resolve against the skill's own folder, skills side by side; no-AI commands use <skill>/templates/. AI step 5 names the App.tsx/RunPanel.tsx markers and no longer remembers the model per user.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
ai_sections.html fetches {API_BASE}+path when window.qt is absent; a page-check case routes those requests to server_stub.dispatch(). AI SKILL.md step 6 and frontend.md send plain-HTML/Vue/Angular/Svelte projects to it.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
MODES, TEST_FILL, FAKE_BRIDGE, the stub loader, the page opener and the no-AI case list now live in one place; sample_data and push move to tests/conftest.py.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The merged AI desktop page check filled the no-AI template directly and hit
{{CHECKPOINTS_JSON}}. It now runs sections.py with none picked first. No-AI step 6
names the sections.py run, and the AI skill says how its desktop and web paths get
the checkpoint, admin and login sections.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Brings in tickets 05-07 (AI skill, cost page, AI desktop sections). tests/README.md
keeps both the optional-section notes and the AI page-check notes.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
ai_sections.html pastes into the no-AI dashboard.html; ai_bridge.py adds one
ai_request slot that hands every AI contract request (incl. GET /roi) to the
review backend's dispatch(). Desktop page check reruns the web review and cost
cases plus a tampered-page gate case. Eval fixture e-pyqt-ai added.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- templates/web/pricing.py: pricing table with source and as-of date; cost_for_call
(input rate + (output + thinking) at output rate, long-context above threshold;
unknown model raises naming the known models).
- Cost tab: coverage pill, total/this-month/tokens tiles, month-by-month table,
per-run tokens and cost ("not priced", never $0), by-hand panel with editable
assumptions labelled as such.
- Contract: RoiRun and GET /roi; optional GET /models and POST /runs/{id}/retry.
- SKILL.md: cost page wiring, model picker and retry-on-other-model as optional sections.
- Tests: test_pricing.py self-check, page_check_ai/test_ai_cost.py.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- rpa-dashboard-ai/SKILL.md: trigger description and the shared question flow;
points at the no-AI frontend.md, themes and palette instead of copying them.
- templates/contract.md: runs, review rows, endpoints and the server approve gate.
- Superbill extracts: patient names and the client name removed, every file
carries an EXAMPLE ONLY banner. tests/test_reference_scan.py checks both skills
for patient data, internal IPs, credentials and keys.
- tests/fixtures/d-ai-extraction and its eval entry, which runs page_check_ai
on the built folder.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
React + Vite + Tailwind starter with the no-AI shell, band legend, review
split pane with drafts and verify, and a server stub that refuses approval
while flagged fields are unverified. Band self-check and AI page check.
Both page checks share one Chromium via tests/conftest.py.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Keeps both sides: frontend detection and bot wiring from tickets 02/03, optional
sections from ticket 04. The a-empty-sections eval now uses the shared "fixture" key.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- dashboard.html: each section sits in OPTIONAL:<name> BEGIN/END blocks in
the style, markup and script, with sample answers so a page with no bot
shows it working. Core change: setUser records the role on <body>, so CSS
hides admin-only parts from operators.
- templates/sections.py keeps the chosen sections and deletes the rest,
markers included; it stops on a broken marker.
- templates/sections.md: what each section needs from the host (events,
actions, desktop slot snippets, the role re-check, the login hand-off).
- SKILL.md step 5 asks one multi-select question and runs sections.py.
- Page check: checkpoint states, admin visibility by role and assign/remove,
login theme and hand-off to auth or the stub. Cases skip on a generated
page without the section; the template must carry all three. The harness
signs in when the page has a login screen.
- tests/test_sections.py: no sections leave no trace, and that page still
passes the page check.
- Eval runner: a-empty-sections variant (all three) and per-section checks.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- templates/bot_runner.py (new, no Qt): runs the bot as a child process
(unbuffered, UTF-8), tails its output, keeps raw lines in bot_raw.log,
and turns lines into step/log/status events. Step markers and friendly
rules use specific substrings, first match wins; unmatched error lines
are always shown, other unmatched lines hidden. Dry run:
python dashboard/bot_runner.py prints the events the page would get.
- bridge.py: delegates to bot_runner, one run at a time, restores the
saved dark mode on every page load (fixes sample-data mode in PyQt),
adds load_latest_report / download_report slots the page calls.
- SKILL.md: skip the stack question for a PyQt project; desktop wiring
steps from the bot's real output; verify steps for the host.
- tests: assert-based self-check for the line logic and run loop; Seam 1
run replay (status dot, Run button, steps, log) and wired-page mode;
fixture b-pyqt-bot and its Seam 2 eval (all 14 checks pass).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- templates/detect_frontend.py: finds plain HTML, React/Vue/Angular/Svelte apps
and PyQt web views; prints location, stack, main colours, font and every
token block (CSS custom properties, <style> tags, Tailwind config).
- templates/frontend.md: shared report / keep / restyle procedure, written
so rpa-dashboard-ai can point to it.
- SKILL.md steps 1, 2 and 6 point to it.
- tests: detection self-check; fixture c-web-existing-frontend; eval entries
c-keep and c-restyle (new pages only, per-question grading, checks on what
changed in the existing files), both passing.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
On Windows a multi-line argv prompt is cut at its first newline, which
also dropped the permission flags. The a-empty eval now passes every
check, including the page check on the page the skill built.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- rpa-dashboard-no-ai/SKILL.md: trigger description and the workflow in spec
order (scan, report/keep-or-restyle, colours, stack, sections, build, wire,
verify).
- templates/themes.md: Tebra Sky and Superbill Ember, light and dark blocks.
- templates/palette.py: derives a custom palette from one brand hex and
checks text contrast in light and dark.
- dashboard.html: built-in sample data so a page with no bot works on first
open; cleared batches in the donut; component tokens so Ember is a
token-only swap; accessible names for KPI cards, nav, steps, log, search
and the dark toggle.
- bridge.py: placeholders inside string literals, so it passes the lint hook
unfilled.
- tests/page_check: Seam 1 harness (fake Qt bridge, light/dark/narrow).
- tests/evals: Seam 2 runner and fixture a-empty.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
