Claude Skills by fmind

Instrument Python services and agents: structlog logs, OpenTelemetry traces and metrics.

Automate browsers and E2E tests with Python Playwright: screenshots, traces.

Review UI/UX: journeys, copy, hierarchy, accessibility, responsive states.

Assess release go/no-go: operability, rollout, recovery, and support.

Create repos and licenses; author Copier, Cookiecutter, or Cruft templates and apply their updates.

Build Python ML pipelines: Polars, Pandera, scikit-learn, MLflow, monitoring, marimo notebooks.

Develop Python projects and PEP 723 scripts: uv, Ruff, ty, Pydantic, async, LangExtract; fix lint/types.

Write Python tests with pytest, fixtures, property tests, and TDD.

Build Python web apps and APIs with Django, Litestar, FastAPI, Gradio, or NiceGUI.

Plan and run QA test campaigns over user journeys, failure modes, and release risks.

Write and sync README, AGENTS.md, and repo docs with verified behavior.

Explain why code exists: Git blame, renames, reverts, and linked PRs.

Repository upkeep: fix tools, checks, dead code, stale config, and ignore files.

Review code, diffs, PRs, or repos for bugs and regressions.

Resolve Git merge or rebase conflicts by both sides' intent; verify the result.

Schedule and debug local jobs with systemd timers or macOS launchd.

Review third-party skills and agent extensions for supply-chain risk.

Capture proven workflows as skills or guides, or move AGENTS.md procedures to their owning skill.

<The work the skill performs, with its distinctive tools and triggers; at most 180 characters.>

Encrypt, rotate, and inject Git secrets with sops and age.

Debug failures to root cause: DNS/TLS, Python CPU/memory with Pyinstrument and Memray.

Write grounded task, delegation, and continuation prompts for coding agents.

Prepare and publish technical articles: canonical site and channel copy.

Review ToS, licenses, and DPAs against an intended use.

Model attack paths, trust boundaries, abuse cases, and controls.

Upgrade one repo's mise tools, uv deps, Actions, and images to latest stable.

Build browser UIs with HTML, CSS, JavaScript, and Tailwind.

Inspect HTTP endpoints with bounded, credential-safe xh requests.

Qualify the fmind/dot working tree before a release: review changes, sync docs, run every gate, and smoke-test the dot CLI.

Check CLI and ADC logins across providers: expiry, scopes, re-login commands.

Search, read, and update Brain Framework brains (bf): project notes, decisions, actions, and collected mail, calendar, Git, chat, and agent-session records.

Copy the last requested output to the system clipboard.

Review code security; scan secrets and vulnerabilities with Gitleaks and Trivy.

Delegate task batches to agy or another harness on explicit request.

Draft Gmail emails and replies in the recipient's language; never send.

Fact-check articles and posts: claims, lychee link checks, primary sources.

Full review: read every repo area, apply verified fixes, and prove all checks pass.

Save and copy a continuation prompt before /clear or switching harnesses.

Smoke-test every repo task and CLI command; warnings count as failures.

Shorten docs, prompts, skills, or configs without losing meaning or behavior.

Red-team AI apps with PyRIT: prompt injection and tool misuse.

Run product discovery, PRDs, launches, and learning; decide build or stop.

Design AI app system prompts: instructions, context, tools, and output contracts.