Skip to main content
MarkusNeusinger
Perfil de criador do GitHub

MarkusNeusinger

Visão por repositório de 19 skills coletadas em 3 repositórios do GitHub.

skills coletadas
19
repositórios
3
atualizado
2026-08-01
explorador de repositórios

Repositórios e skills representativas

work-basket
sem classificação

Work off the Werkbank's Auftragskorb (the work_items basket) — read the open tasks, reproduce each complaint, restate it back into the row, triage it along the stage doctrine, fix the RULE rather than one spot, measure the effect and close the item with the diagnosed stage. Use when asked to work off the Korb, handle work items, process filed optimization tasks, or start an optimization round.

2026-08-01
open-pr
Desenvolvedores de software

Take a finished change from diff to an open, green, review-clean PR — run the matching verify skills and the local CI gates first, then commit, push and open the PR, watch the pipeline AND the Copilot review, fix sensible findings and resolve the review threads. Never merges unless the user explicitly asks in this session. Use when asked to open or create a PR, ship a change, or finish up a change.

2026-07-16
verify-api
Desenvolvedores de software

Run and exercise the FastAPI backend — start uvicorn, sweep the read endpoints with curl, check the diagnostic/fit/crop payloads against the live DB, and probe the admin write gate. Use when asked to run, start, test, or verify the API, a router, an endpoint, or a backend change.

2026-07-16
verify-core
Analistas de garantia de qualidade de software e testadores

Test and smoke-run the pure-Python compute layer in core/ — run pytest, run ruff lint/format the way CI does, and call the extraction pipeline directly on a synthetic chart without DB or HTTP. Use when asked to run, test, lint, or verify core/, the pipeline, extraction, template, or fit code.

2026-07-16
verify-frontend
Desenvolvedores web

Run and visually verify the kurrentschrift app after frontend changes — start the dev servers, click through ONLY the flows the change touches (chrome-devtools MCP locally, or playwright-core against the pre-installed Chromium in the cloud), watch the console and network, check style fidelity and legibility at a desktop AND a mobile viewport, and record a performance trace when the change can move performance. Use when asked to run, start, screenshot, verify, test in the browser, or visually check the app or a frontend change.

2026-07-16
verify-migrations
Desenvolvedores de software

Verify Alembic schema migrations locally against a throwaway PostgreSQL — full upgrade chain incl. seeds, model↔migration drift via alembic check, and a downgrade/upgrade roundtrip — without ever touching the shared Cloud SQL DB. Use when asked to verify, test, or check a migration, a schema change, or alembic revisions before pushing.

2026-07-16
write-docs
Desenvolvedores de software

Conventions and checklist for writing or updating the internal design docs under docs/ — German language rules, where a new doc goes, keeping docs/index.md and the CLAUDE.md/copilot-instructions pair in sync, and what is settled (verworfen) and must not be re-litigated. Use when asked to write, add, update, or restructure documentation, concepts, or reference docs.

2026-07-16
optimize-glyphs
Desenvolvedores de software

Autonomous keep/discard experiment loop on the glyph extraction/rendering pipeline — snapshot DB fixtures once, then hypothesize, edit core/, run the glyph bench, log results.tsv, keep on improvement or git-reset. Never writes to the DB. Use when asked to optimize glyph rendering, improve template quality, run the glyph bench, or start an experiment loop.

2026-06-21
Mostrando as 8 principais de 10 skills coletadas neste repositório.
babysit-pipeline
Desenvolvedores de software

Run and monitor the bulk-generate / impl-* pipeline for one or more specs to full 15-library coverage — dispatch sequentially, poll with the bundled checked-in scripts (never hand-rolled loops), read completion from impl:{lib}:done labels + GCS spot-checks, apply the correct stall thresholds, and report progress proactively. Use when asked to babysit, run bulk-generate, regenerate specs, monitor the pipeline, or bring specs to full coverage.

2026-07-08
open-pr
Desenvolvedores de software

Take a finished change from diff to an open, green, review-clean PR — run the matching verify skills and local CI gates first, then commit, push and open the PR via /pull_request, watch the pipeline AND the Copilot review, fix sensible findings, resolve the review threads, and watch any Cloud Build deploy after merge. Never merges unless the user explicitly authorizes it in this session. Use when asked to open or create a PR, ship a change, or finish up a change.

2026-07-08
optimize-skills
Desenvolvedores de software

Mine past Claude Code session transcripts for recurring friction — problems the user had to find manually, corrections, repeated tool errors, hand-rolled loops — and turn the patterns into skill gotchas, memory entries, or CLAUDE.md rules. Use when asked to optimize the skills, run a retro, review past sessions, or find recurring problems.

2026-07-08
verify-api
Analistas de garantia de qualidade de software e testadores

Run and exercise the anyplot FastAPI backend — start the server, sweep the read endpoints with curl, check payload shapes against the live DB, and respect the shared-production-database discipline. Use when asked to run, start, test, or verify the API, a router, an endpoint, or a backend change.

2026-07-08
verify-core
Analistas de garantia de qualidade de software e testadores

Test and smoke-run the shared Python layer in core/ — run pytest the way CI does, run the ruff + mypy gates, and import-check core modules (palette, constants, repositories) directly without the running app. Use when asked to run, test, lint, or verify core/, the database layer, palette, constants, or shared utilities.

2026-07-08
verify-frontend
Analistas de garantia de qualidade de software e testadores

Run and visually verify the anyplot app after frontend changes — start the dev servers, click through ONLY the flows the change touches via a browser MCP (claude-in-chrome or the Playwright plugin locally, playwright-core probe in the cloud), watch console and network, and judge style and legibility at a desktop AND a mobile viewport in BOTH light and dark theme. Use when asked to run, start, screenshot, verify, test in the browser, or visually check the app or a frontend change.

2026-07-08
verify-corpus
Analistas de garantia de qualidade de software e testadores

End-to-end test + grader for the citadel ingest pipeline over the shipped test corpora — beverages (coffee+tea showcase), kelvarra (a coherent fictional world whose facts contradict reality), leuchtfeuer (a 3-year programme ingested in dated waves that drives reconcile/delete/force), pemberley (all of Pride and Prejudice as one large-source chunking + narrative stress test), injection-resistance (mundane documents with adversarial instructions the agent must treat as content), clockwork (a whole git repository folded in as one digest, with a second commit driving repo-reconcile), flurfunk (informal genres — chat, social, interview, application, forum — grading attribution and in-thread reversal), and gazette (PDF sources grading CITADEL_PDF_MODE text-vs-images, the academic-publications genre, and an image-only page), and kontor (binary Office documents — OOXML + legacy OLE — grading the Office extraction path, an embedded-image delta via CITADEL_IMAGE_SUPPORT, dedup-by-basename, and ignore-patterns), and wer

2026-07-29
bench-model
Cientistas de dados

Benchmark an LLM (model and/or agent CLI) on citadel's wiki-building quality — the model-focused twin of verify-corpus (which tests the PIPELINE with a fixed model, while bench-model tests a MODEL with the fixed pipeline). Mode A ingests a corpus into a throwaway sandbox with the chosen CITADEL_INGEST_MODEL / CITADEL_LLM_CLI, grades it with verify-corpus's retrieval-first method, then applies a DISCRIMINATIVE tier (locator precision, oblique-query retrieval, merge quality, redundancy/cross-links, judgment delta on contradictions + planted-false claims) so runs by models of different strength never tie at the top — if two models both ace the grade, the test was too easy, which is itself a finding. Ends with a side-by-side metrics table and a verdict (is the cheaper model's wiki acceptable, where does it degrade first, what rule changes would close the gap). Use whenever the user wants to compare models on wiki creation (sonnet vs haiku, a new Claude model, agy/copilot, or open/local models via the CITADEL_LLM_

2026-07-28
open-pr
Desenvolvedores de software

Use when asked to open or create a PR, commit and push, ship a change, or finish up a change — even if they do not say the word skill. Runs the hard local gates (pytest, ruff check, ruff format --check, and the beverages-workspace lint), routes ingest/llm/rules changes through verify-corpus first, branches claude/<topic>-<slug> off main, opens a ready (non-draft) PR with the Claude Code footer, requests the Copilot review, then watches CI and resolves review threads. Stops at green + resolved with the PR URL; never merges.

2026-07-23
Mostrando 3 de 3 repositórios
Todos os repositórios foram exibidos