claude

jet-skills

Jet's company-agnostic Claude Code stack: architect/engineering skills, role workflows, behavioral guardrails, and a per-project context bootstrap.

1 on GitHubby Jetv0.3.0MITupdated 14 days ago
/

Plugin jet-skills from marketplace jet-skills in prestarius/jet-skills-stack. Commands read from the repo's manifest — 13 days ago.

This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.

What it installs

Skills (28)

  • architect-review

    Review a design, PR, or proposal as a Staff Solution Architect — simplicity, scalability, event-driven boundaries, security, cost, compliance, operability — ending in a prioritized must/should/nice list.

  • article-writing

    Draft a long-form article, blog post, essay, or technical write-up in the author's own voice — outline first, then a full draft that reads like a person wrote it. Use whenever the user asks to "write an article", "draft a blog post", "write a long-form piece", "turn this into an essay", or wants a p

  • changelog-watch

    Diff the Claude Code changelog since this stack's verified baseline and report which skills, hooks, or docs are possibly stale. Invoke as /changelog-watch by hand or on a schedule; not model-triggered.

  • coordinator-workers

    Run a plan's issues with one subagent worker per issue, each in its own git worktree and branch, while this session stays the coordinator that briefs, reviews every diff, merges, closes issues and waits on outside events. Use when a repo has issues split from a plan (plan-to-issues) and more than on

  • cost-forecast

    Forecast token/usage cost for an LLM workload from usage signals; produce a wiki-ready table.

  • design-doc

    Author a design document (RFC) for a feature or system before the decision is locked — problem, requirements, options, proposed design, risks. Use whenever the user says "write a design doc", "draft an RFC", "write up the design", "proposal for the team", or has finished discussing an approach and n

  • document

    Generate complete, structured documentation for a feature, module, API, or project using the Diataxis framework (tutorial / how-to / reference / explanation). Use whenever the user asks to "write docs", "document this", "generate documentation", "write a tutorial", "write a how-to", or "explain this

  • ea-briefing

    Produce an Enterprise-Architecture briefing from a technical update or discussion, with governance questions; translate PL↔EN if the source and audience differ.

  • estimate

    Estimate effort for a feature, plan, or backlog with explicit assumptions and confidence ranges — never a single confident number. Use whenever the user asks "how long will this take", "estimate this", "size the backlog", "t-shirt sizes for these", or a plan/issue set needs effort attached before co

  • eval-tool

    Evaluate and recommend a tool, model, framework, or library with mandatory up-to-date web research. Use whenever the user asks "which X should I use", "is X any good", "evaluate X vs Y for us", or any tooling/model/library selection — never answer these from memory alone. This skill picks ONE winner

  • gh-tickets

    Drive GitHub tickets from the terminal with gh - create a public repo after the human says yes, open one issue per problem from a generated list or data, edit titles and bodies, close with a reason and a comment that quotes its source, and read the state back. Use when a task delivers tickets as Git

  • headless-loop

    Generate ready-to-run Claude Code automation loop scripts for unattended, headless workflows. Use when the user asks to "run Claude Code in a loop", "batch process with Claude Code", "iterate over files/tickets", build a "self-correcting" or "retry" loop, or wants an Agent SDK loop in Python. Covers

  • interview-guide

    Build a structured technical interview guide with a scoring rubric and an evaluation template, segmented by audience (e.g. engineer vs architect). Use whenever the user is preparing to interview or verify a candidate, asks for interview questions, a screening guide, or a candidate evaluation form.

  • job-supervisor

    Put every unattended job (launchd, cron) behind one wrapper that records each run as a JSON line in jobs/runs/<day>.jsonl (time with offset, job, ok or fail, exit code, seconds, last error line), so a morning check or a digest can read what ran at night. Use when a repo gains a scheduled job, when t

  • market-research

    Research a market, landscape, or set of players and produce source-attributed findings — every claim cited, recency noted. Use whenever the user asks "what's the state of X", "who are the players in Y", "competitive landscape", "market research", "survey the options for Z", or needs a grounded overv

  • meeting-notes

    Turn raw meeting notes or a transcript into structured minutes — decisions, action items with owners, open questions — and route them onward (Obsidian note, ADRs, tracker issues). Use whenever the user pastes a transcript or messy notes and says "write this up", "minutes", "notatka ze spotkania", "w

  • migration-plan

    Turn a modernization goal or architectural finding into a phased migration plan — current state to target state with coexistence, cutover criteria, and rollback per phase. Use whenever the user asks "how do we get from X to Y", "plan the migration", "phase out the legacy system", "strangler this", o

  • obsidian-note

    Generate a complete Obsidian note using Jet's frontmatter schema and section conventions. Use whenever the user wants a note for their vault, says "make an Obsidian note", "add this to my vault", or wants meeting/architecture/project notes captured. Notes from a Markdown source must be exhaustive, n

  • plan-to-issues

    Split a repo's plan file into GitHub issues with gh, one per unit of work, in dependency order, after the human has approved the split as a table and said what every issue must carry. Use when a plan is written and has no issues yet, when the user says "turn the plan into issues", "split this into t

  • postmortem

    Write a blameless incident postmortem — impact, timeline, contributing factors, what went well/poorly, concrete follow-up actions. Use whenever the user says "postmortem", "incident review", "RCA", "write up this outage", or when a diagnosing-bugs session ends on an incident that deserves a durable

  • read

    Three checks for answers that look right but are wrong - find and quote an API or form contract before sending a body, keep and count every cut before shortening a person's text, check a live maker page before naming the newest model. Use before any POST, PUT, PATCH or form submit to an unread endpo

  • release-notes

    Turn git history since a tag or date into a changelog entry or release notes grouped by change type, in the project's changelog format. Use whenever the user asks for "release notes", "changelog", "what's in this release", "write the CHANGELOG entry", or is tagging a version. For a stakeholder progr

  • skill-stocktake

    Audit a collection of Claude Code skills for overlap, stale technical references, context cost, name/trigger/scope drift, and (for third-party skills) unsafe scripts or injected instructions, then recommend keep / improve / update / hide / retire / merge for each. Use whenever the user wants to revi

  • slide-deck

    Plan and generate a training/working-session slide deck in Jet's house style (charcoal/teal) as a self-contained HTML deck, with presenter script and lab material. Use whenever the user wants slides, a deck, a training session, or a workshop. For .pptx output, defer file generation to a pptx-capable

  • status-report

    Compose a stakeholder status update from recent work — git history plus the current conversation; PL or EN to match the audience.

  • threat-model

    Quick security pass over code or a design using OWASP Top 10 + STRIDE, findings by severity with a remediation each. Use when the user asks for a threat model, a security pass, or "what could go wrong security-wise" on a design or code path. Distinct from the bundled /security-review, which diffs th

  • tradeoff-table

    Produce a side-by-side option comparison table with a clear recommendation. Use whenever the user is weighing approaches/tools/architectures ("X vs Y", "which should we use", "compare these options", "build vs buy") and would benefit from a structured tradeoff matrix rather than prose. This skill st

  • zoom-out

    Explain unfamiliar code in the context of the whole system, not just the file in front of you. Use whenever the user is onboarding to a codebase, asks "what does this do / how does this fit", or needs the big picture before changing something.

Subagents (3)

  • codex-reviewer

    Read-only code review by OpenAI's model through the Codex CLI. Use when a skill needs a second opinion from a non-Anthropic model (sol-loop, council) and asks for a subagent that runs Sol or GPT.

  • researcher

    Web-research subagent for fan-out fact gathering with mandatory citations. Use for research-heavy work (market surveys, tool evaluations, pricing lookups) that would flood the main session with fetched pages.

  • solution-architect

    Staff Solution Architect persona for design review and tradeoff analysis. Use for deep architecture work that benefits from a focused subagent. Recommends only; never edits code.

Hooks (3)

  • PreToolUse

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/command-guardrails.sh"

  • PreToolUse

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/file-guardrails.sh"

  • SessionStart

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/working-agreement.sh"

View source on GitHub prestarius.dev

Similar plugins

Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).

39 skills

mattpocock/skills 323,108

superpowers

claudecodex

Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques

15 skills · hooks

obra/superpowers 316,836

nextjs

claude

Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.

6 skills

vercel/next.js 143,495

Taste Skill

claudecodex

tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.

1 skill

Leonxlnx/taste-skill 114,391

AI-powered codebase understanding — analyze, visualize, and explain any project

9 skills · 10 agents · hooks

Egonex-AI/Understand-Anything 92,410

diagram-design

claudecodex

Editorial diagrams in your brand, as self-contained HTML and SVG. Architecture, flowcharts, sequence, state machines, ER and database schemas, timelines, swimlanes, org charts, Gantt, Wardley maps, user journeys, service blueprints, UML class, lifecycle phase maps, and charts from bar, line and scatter to Sankey, treemap and heatmap, plus many more. Redraws draw.io, Mermaid, Excalidraw and PlantUML files. Exports SVG and PNG.

1 skill · 7 commands

cathrynlavery/diagram-design 66,757

Maintain jet-skills?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex pluginslisted