Development skills

OCR scanned or image-only corpora with vision-language models in four phases: `triage` inventories the scans, identifies script and language, and shortlists models by script, hardware, and data constraints; `evaluate` picks a system by measured CER/WER against ground truth, using born-digital twins, a second reader, and decision rules set in advance; `run` builds the production pipeline; and `clean` removes model artifacts, audits what every cleaning rule deletes, corrects with rule-based and LLM passes, and records provenance. Born-digital documents with a text layer go to $doc-to-markdown; runs on Leiden's ALICE cluster add $vlm-ocr-alice.

The English summary is being prepared. Showing the original description.

Advises on setting up and validating topic models for survey and experimental text: discovery vs. measurement, STM/LDA/BERTopic choice, preprocessing, covariate formulas, choosing K across coherence, FREX, held-out likelihood, and residuals, validating topics against human coding, robustness, and reporting. Coding against a fixed codebook goes to text-classification.

The English summary is being prepared. Showing the original description.

Advises on setting up and validating LLM text classification: codebook, learning regime and model choice, prompts, validation against human coding (kappa, F1), hybrid review, measurement error, and reporting, plus a short resumable batch pattern with a rule-based baseline. Use to classify, code, or label text at scale; category discovery goes to topic-modeling.

The English summary is being prepared. Showing the original description.

Design and format publication-quality tables. Use for column order, row grouping, notes, statistical precision, accessibility, and reproducibility.

The English summary is being prepared. Showing the original description.

Retired. Reporting feedback and sharing a session are documented by the CLI itself: run `deepline feedback send --help` and `deepline sessions send --help`. Kept only so installed CLIs that still list this skill keep syncing.

The English summary is being prepared. Showing the original description.

Provides coding assistance with best practices and code review

The English summary is being prepared. Showing the original description.

Systematic debugging approach for identifying and fixing issues

The English summary is being prepared. Showing the original description.

Score your Claude Code environment on a fun 0-10 ladder (Tourist → Swarm) calibrated to the quickstart's 4 systems — Context, Skills, Integrations, Orchestration. Two front doors - an interactive quiz (zero setup, shareable) or a silent scan of your repo. Outputs a next-level roadmap plus a branded HTML dashboard or a paste-anywhere ASCII card. The default mastery skill of this quickstart. Triggers - "level", "what's my claude code level", "claude code level quiz", "assess my setup", "how good is my setup", "claude code maturity"

The English summary is being prepared. Showing the original description.

This skill should be used when the user asks to "add docstrings", "write error handling", "use naming conventions", "handle exceptions", or when writing new Python code for StreamFlow that requires docstring format, naming conventions, exception handling, or async cleanup patterns.

The English summary is being prepared. Showing the original description.

This skill should be used when the user asks to "update the changelog", "add a changelog entry", "write a CHANGELOG entry", or when preparing a git commit in StreamFlow that requires updating the `## [Unreleased]` section of `CHANGELOG.md`.

The English summary is being prepared. Showing the original description.

Assess and address review feedback on GitHub PRs, GitLab MRs, or in conversation. Use when checking new reviews, responding to comments, rechecking after a push, or following up on approvals and change requests.

The English summary is being prepared. Showing the original description.

Ensemble SOLID review — fans the ruleset across overlapping focused workers over the same code, then reduces by corroboration.

The English summary is being prepared. Showing the original description.

Use when the user asks what to do next, asks for a plan under uncertainty, challenges stalled or low-trust work, requests multiple possible approaches before action, or needs an evidence-first loop that uses RT-ICA-style prerequisite checks, adversarial review, subagent coordination, real validation, and durable concern tracking.

The English summary is being prepared. Showing the original description.

Use when creating or backfilling AI-categorized daily GitHub releases from branch commits.

The English summary is being prepared. Showing the original description.

Python web and API development enforcing strict route/domain/data layer separation, Pydantic v2 strict request-response models, edge-resolved auth, and async-safe HTTP clients. Use when working with FastAPI, Starlette, Django, Flask, HTTP endpoints, request models, authentication flows, async handlers, or any Python web framework task.

The English summary is being prepared. Showing the original description.

Use when building dependency-free Python 3.11+ scripts for airgapped, stdlib-only, or restricted environments where third-party package installation is prohibited — triggers on "stdlib-only", "airgapped", "no dependencies", "no internet", "restricted environment", or confirmed environments where external packages cannot be installed.

The English summary is being prepared. Showing the original description.

Shared Python 3.11+ development rules — type safety and the boundary policy for `Any` (ty, native generics, Protocol, TypeIs, Pydantic), layered architecture and SOLID, error handling, security, performance, identifier naming, PEP 723 script dependencies, Rich/Typer output, tooling defaults (uv, ruff, ty, hatchling, pytest), and testing requirements (behavioral coverage, TDD). Activates when any Python skill or agent needs the shared rules for implementation, code review, refactoring, or test authoring.

The English summary is being prepared. Showing the original description.

Validates and corrects Python shebangs and PEP 723 inline script metadata by applying four shebang-selection rules. Use when auditing or fixing shebangs in Python files — choosing between plain python3 and the uv shebang for standalone scripts with external dependencies, adding or removing PEP 723 metadata blocks to match actual import requirements, checking execute bit presence, or avoiding redundant transitive dependencies when typer is declared.

The English summary is being prepared. Showing the original description.

Runs structured Python cleanup and modernization — static analysis via prek/ruff, smell investigation to root cause, typed-boundary hardening by inventorying Any usage, and modernization within the project's requires-python lane. Use when refactoring Python code, removing dead code, hardening type boundaries, or running a modernization pass on a file or scope.

The English summary is being prepared. Showing the original description.

Provides Hatchling build backend guidance for Python packaging — use when configuring pyproject.toml metadata, build targets (wheel, sdist, binary), file selection with git-style globs, build hooks, metadata hooks, version management (code/regex/env sources), editable installs, the hatch-vcs plugin, plugin development, build environment setup (UV/pip/Cython), setuptools migration, or troubleshooting Hatchling errors. Covers PEP 517/518/621/660 standards and context variable interpolation.

The English summary is being prepared. Showing the original description.

Auto-selects and enforces the strongest valid Python typing lane for the detected Python version and dependencies — no user input required. Use when adding or tightening type annotations, eliminating Any usage in internal code, designing boundary validators or parsers, choosing between stdlib typing (TypedDict, Protocol, dataclasses), Pydantic models, or Hypothesis property tests, addressing ty or mypy failures, or applying version-specific features (TypeIs, ReadOnly, PEP 695 generics, PEP 649 deferred evaluation). Enforces boundary isolation — raw payloads validated immediately at ingress and returned as typed internal objects.

The English summary is being prepared. Showing the original description.

Mermaid diagram syntax reference for all diagram types — flowchart, sequence, class, state, ER, gantt, git graph, mindmap, timeline, user journey, pie, quadrant, XY chart, block, sankey, C4, kanban, and more. Use when constructing or debugging any Mermaid diagram definition.

The English summary is being prepared. Showing the original description.

Executes a four-phase feature addition workflow (Discovery, Planning, TDD Implementation, Verification) for Python projects. Use when adding a new feature end-to-end — discovering project structure and integration points, drafting a feature spec with MoSCoW-prioritized requirements and BDD acceptance criteria, implementing via test-first TDD cycles, then verifying with ruff lint, ty type checks, and behavior-focused regression and contract coverage.

The English summary is being prepared. Showing the original description.

Provides agent selection criteria, workflow patterns (TDD, feature addition, code review, refactoring, debugging), quality gates, and python-cli-architect vs stdlib-scripting routing for Python engineering tasks. Activated by python-engineering:orchestrate at Step 1 before any task is routed. Also activates when an orchestrator needs to select the correct Python specialist agent or chain agents across a multi-step Python workflow.

The English summary is being prepared. Showing the original description.