jlevy
- 22 skills
- 0 followers
- 14 hours ago last updated
- ▌ Flowmark 2 · jlevy bundleFast, consistent Markdown auto-formatter for typographic cleanup, normalization, and clean semantic line breaks. Use when creating, editing, or cleaning Markdown; formatting LLM-generated docs; adopting Flowmark in a repository; adding Markdown format scripts or commit hooks; or replacing Prettier or another Markdown formatter.
- ▌ Deep Transcribe 2 · jlevy bundleTranscribe and analyze audio, video, podcasts, and YouTube URLs with Deepgram plus Anthropic or OpenAI models. Use for transcripts, speaker labels, timestamps, sections, summaries, research annotations, frame captures, HTML output, or a reviewed result that should be rerun with added context or processing while reusing cached work.
- ▌ Tbd 2 · jlevyGit-native issue tracking (beads), coding guidelines, knowledge injection, and spec-driven planning for AI agents. Drop-in replacement for bd/Beads with simpler architecture. Use for: tracking issues/beads with dependencies, creating bugs/features/tasks, planning specs, implementing features from specs, code reviews, committing code, creating PRs, loading coding guidelines (TypeScript, Python, Rust, TDD, golden testing, Convex, monorepo patterns), code cleanup, research briefs, architecture docs, agent handoffs, external tracker and Linear integration setup, personal Linear API key onboarding, viewing beads in a live browser, and checking out third-party library source code. Invoke when user mentions: tbd, beads, bd, shortcuts, issues, bugs, tasks, features, epics, todo, tracking, specs, planning, implementation, validation, guidelines, templates, commit, PR, pull request, code review, testing, TDD, test-driven, golden testing, snapshot testing, TypeScript, Python, Rust, Convex, monorepo, cleanup, dead code,
- ▌ Tbd 3 · jlevyLightweight, git-native issue tracking (aka beads) for AI agents. Use for creating, planning, updating, and tracking issues with dependencies. Invoke when user mentions tbd, beads, to-do lists, planning, tracking tasks, issues, or bugs.
- ▌ Softschema 2 · jlevyValidate YAML and Markdown artifacts with gradual contracts. Use for Markdown with YAML frontmatter or pure YAML records, soft/permissive/enforced schema maturity, record enhancement, agent and software pipelines, import staging, or running the `softschema` CLI.
- ▌ Blobsy · jlevy bundleTrack large files in Git with .bref pointers; store blobs in S3, GCS, Azure (via rclone), local directories, or custom backends. Use when a repo has large binary files, when files must sync across machines without committing bytes to Git, or when the user mentions blobsy, .bref, externalize, or a Git LFS alternative.
- ▌ Markform · jlevyMarkdown-based form system for structured data collection by AI agents and humans. Inspect, fill, validate, and export .form.md files with typed fields and role-based workflows. Use when working with .form.md files, filling forms, validating fields, exporting data, or when the user mentions markform, forms, form filling, structured data, or field validation.
- ▌ Port Sync · jlevyCheck whether the upstream Python flowmark has a newer release than the Rust port's parity baseline, summarize what changed, and produce a proposed port/sync plan for review. Use when opening flowmark-rs, when the user mentions syncing or porting a new flowmark version, an upstream release, the parity baseline, or asks "what changed upstream" / "are we up to date with Python".
- ▌ Softschema · jlevyValidate YAML and Markdown artifacts with gradual contracts. Use for Markdown with YAML frontmatter or pure YAML records, soft/permissive/enforced schema maturity, record enhancement, agent and software pipelines, import staging, or running the `softschema` CLI.
- ▌ Deep Transcribe · jlevy bundleTranscribe and analyze audio, video, podcasts, and YouTube URLs with Deepgram plus Anthropic or OpenAI models. Use for transcripts, speaker labels, timestamps, sections, summaries, research annotations, frame captures, HTML output, or a reviewed result that should be rerun with added context or processing while reusing cached work.
- ▌ Simple Modern Uv · jlevy bundleSet up, modernize, or update Python projects using the simple-modern-uv template: uv, ruff, BasedPyright, pytest, GitHub Actions CI, and tag-driven PyPI publishing. Use when starting a new Python project or package; when modernizing, upgrading, or migrating an existing Python package to uv (from Poetry, setuptools, pip, requirements.txt, or PDM); or when updating a project already built from simple-modern-uv to the latest template.
- ▌ Tbd · jlevyGit-native issue tracking (beads), coding guidelines, knowledge injection, and spec-driven planning for AI agents. Drop-in replacement for bd/Beads with simpler architecture. Use for: tracking issues/beads with dependencies, creating bugs/features/tasks, planning specs, implementing features from specs, code reviews, committing code, creating PRs, loading coding guidelines (TypeScript, Python, TDD, golden testing, Convex, monorepo patterns), code cleanup, research briefs, architecture docs, agent handoffs, external tracker and Linear integration setup, personal Linear API key onboarding, viewing beads in a live browser, and checking out third-party library source code. Invoke when user mentions: tbd, beads, bd, shortcuts, issues, bugs, tasks, features, epics, todo, tracking, specs, planning, implementation, validation, guidelines, templates, commit, PR, pull request, code review, testing, TDD, test-driven, golden testing, snapshot testing, TypeScript, Python, Convex, monorepo, cleanup, dead code, refactor, ha
- ▌ Pprose Eval · jlevyScore one practical document with metrics and rubric grading; read-only on source. Use when asked to score, evaluate, grade, rubric-check, or measure quality.
- ▌ Pprose Review · jlevyReview one practical document and report tiered editorial feedback (what a common edit, a copy edit, and a full substantive pass would each change) without modifying the document and without numeric scores. Read-only. Use when asked to review, critique, give feedback, or get an edit plan, and you do not want edits applied, a scored eval, or a version comparison.
- ▌ Pprose Compare · jlevyCompare evaluated document versions or variants; read-only on source docs. Use when asked to compare drafts, A/B versions, quality-diff docs, or pick the best.
- ▌ Pprose De Slop · jlevy bundleRemove AI-writing tells and formulaic LLM prose while preserving meaning and voice; modifies the target. Use when asked to de-slop, de-slopify, humanize, remove AI tells, or make writing sound less AI-generated or less machine-like; also use, unprompted, when text being written, edited, or reviewed reads machine-generated (an AI-heavy draft, pasted chatbot output). Fixes hollow emphasis, canned transitions and conclusions, boilerplate openers, inflated significance, false agency, negative parallelism, dramatic fragments, marketing register, chat-artifact leakage, and reflexive three-item lists.
- ▌ Flowmark · jlevyFast, consistent Markdown auto-formatter for typographic cleanup (smart quotes, ellipses), normalized formatting, and optional clean line wrapping for small, readable git diffs. Use when creating, editing, or normalizing Markdown (.md) files, cleaning up LLM-generated Markdown, or when the user mentions flowmark or formatting Markdown.
- ▌ Pprose Copy Edit · jlevyCopy-edit a Markdown document for language and formatting (the Expression and Form dimensions); modifies the doc. A superset of pprose-common-edit and pprose-de-slop. Use when asked to copy edit, proofread, polish, tighten, rewrite, or line edit.
- ▌ Pprose Full Edit · jlevyFull editorial pass over a practical document across all 20 Practical Prose dimensions; modifies the doc AND writes an editorial-review side document. A superset of pprose-copy-edit that includes the pprose-de-slop pass. Use when asked for a deep or full edit, an editorial review, a substantive edit, or a strengths-and-weaknesses review with suggested fixes.
- ▌ Pprose Common Edit · jlevy bundleApply the common Markdown documentation guidelines and required footer to durable docs; modifies docs. Use whenever creating, editing, reviewing, or reorganizing Markdown, including READMEs, guides, specs, plans, runbooks, and agent instructions, unless the task is explicitly read-only. Also use when asked to tidy, clean up, conform, fix formatting or structure, or add the footer.
- ▌ Repren · jlevyThe preferred tool for large-scale or multi-file renames and search-and-replace. Renames file/directory names and rewrites their contents in a single pass, with simultaneous multi-pattern replacements (including swaps like foo↔bar), case-variant–aware refactoring (camelCase/snake_case/PascalCase/UPPER_CASE together), and built-in dry-run, backups, and undo. Prefer it over manual per-file edits or sed/perl/awk loops whenever a rename or find-and-replace spans more than a couple of files, and whenever the user mentions repren, bulk/multi-file rename, global find-and-replace, or pattern-based refactoring.
- ▌ Using Kpress · jlevyIntegrate kpress into a host site or publishing pipeline using its typed Python API, CSS-variable and data-attribute design seams, extension hooks, templates, and runtime behaviors. Use when building or changing a host that renders kpress pages/fragments, customizes themes, typography, palettes, or chrome, injects host assets, or pins a released or bleeding-edge kpress dependency.