By 3XADesign
Connect a Projekt organization and automate issues, docs, workloads, estimations and time tracking through the Projekt REST API with your own Personal Access Token. Token-efficient, sequential, dry-run by default. Soporta español.
Write and maintain Projekt project documentation (projekt.3xa.es) idempotently: title-keyed UPSERT of project/sprint docs from markdown into EditorJS blocks (create-or-update, never duplicate), nest pages under a parent, regenerate per-issue AI bitácora (logbook), and export issues to a PDF/markdown artifact. Use whenever the user asks to write/update project docs, a runbook, sprint notes, a wiki page, the bitácora / HdU of an issue, or to export issues as a PDF. Soporta español: documentación, página de proyecto, runbook, notas de sprint, bitácora, historia de usuario, exportar incidencias a PDF.
Estimate Projekt issues and report plan-vs-actual. Fills missing estimated_hours by asking the AI estimator (story_points only) and converting points→hours, with a median-of-siblings fallback when the AI daily quota is spent; then rolls up planned vs logged hours per assignee. Use when the user asks to estimate / estimación / estimaciones, story points / puntos de historia, capacity or plan-vs-actual, or to read/create roadmap milestones for a Projekt project. Soporta español: estimaciones, puntos, horas, planificado vs real, hoja de ruta. Requires the `projekt` skill's auth + context first.
Bulk-create and triage Projekt issues (projekt.3xa.es) from a CSV/JSON backlog, and assign-then-move issues across board columns safely. Use when the user wants to import a backlog, mass-create tasks, assign owners, or move issues to In Progress/Done. Soporta español: crear incidencias en lote, importar backlog, asignar responsables, mover tareas de columna, triaje. Enforces the assignee-required rule so unassigned issues never enter a working column.
Batch-log time on Projekt issues from a sheet, drive per-issue timers (start/stop), and roll up totals via the server's time-summary. Use whenever the user wants to record/import worked time, log hours/minutes against issues, start or stop a timer, or get a time roll-up for an issue. Soporta español: registrar/cargar tiempos, fichajes, horas trabajadas, temporizador, resumen de tiempos por incidencia/tarea.
Deterministic per-member workload & capacity report for a Projekt organization (projekt.3xa.es), read-only via the user's PAT. Pulls /workload, /workload/capacity, /capacity and /capacity/threshold, then renders a Markdown (or CSV) table of assigned / in-progress / done / hours-logged + utilization %, flagging over- and under-allocated members. The script does all the math — zero model tokens. Use when the user wants to balance the team, see who's overloaded, or report capacity for a week/range. Soporta español: cargas de trabajo, capacidad, utilización, sobreasignación, quién está saturado, informe del equipo.
Executes bash commands
Hook triggers when Bash tool is used
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A Claude Code plugin that lets you connect your Projekt organization and automate issues, documentation, workloads, estimations and time tracking through the Projekt REST API — sequentially, professionally, and with maximum token efficiency.
Un plugin de Claude Code para conectar tu organización de Projekt y automatizar incidencias, documentación, cargas de trabajo, estimaciones y tiempos vía la API REST — secuencial, profesional y con el mínimo gasto de tokens.
One plugin, six skills (namespaced projekt-skills:*):
| Skill | Does |
|---|---|
projekt | The orchestrator. Owns the full CONNECT → DISCOVER → PLAN → CREATE → ASSIGN → ESTIMATE → TIME → DOCUMENT → REPORT pipeline. The default entry point — start here. |
projekt-issues | Bulk-create and update issues (CSV/sheet/text → backlog), assign, batch status moves. |
projekt-estimate | Fill estimates, story-points→hours, roadmap & dependencies, plan-vs-actual. |
projekt-workload | Team capacity & workload reports (who's overloaded, utilization %). |
projekt-time | Batch-log time entries, timers, time roll-ups. |
projekt-docs | Create/maintain project docs, regenerate issue logbooks, export PDFs. |
/plugin marketplace add 3XADesign/Projekt-Skills
/plugin install projekt-skills@3xa-projekt
Then just ask Claude, e.g. "Connect my Projekt org and plan a sprint from this backlog" — the projekt skill auto-activates.
This plugin talks to Projekt as you, using your own PAT. It is never bundled and never committed.
pjk_live_… token (copy it — shown once).export TREXA_API_TOKEN="pjk_live_…"~/.config/3xa-projekt/auth.json
{ "token": "pjk_live_…", "api_base": "https://projekt.3xa.es/api" }
export TREXA_ORG_ID="<uuid>". Otherwise the skill uses your current organization from /me.A PAT carries your full role in one organization (no per-endpoint scoping). Treat it like a password — see Safety.
bash, curl, jq, and python3 (3.10+) on PATH. No other dependencies (pure stdlib; no yq/pyyaml needed).
--apply.admin/*, finance/*, payroll/*) require a second explicit confirmation beyond --apply..gitignore blocks auth.json, *.token, .projekt-run/)..projekt-run/.X-Org-Id; cross-org shared reads never become write targets.spec_lookup.sh prints a single endpoint block on demand; the 90% case is covered by a hand-curated cheatsheet..projekt-run/context.json for all name→id resolution.jq before Claude ever sees them.MIT © 3XA Design — see LICENSE.
npx claudepluginhub 3xadesign/projekt-skills --plugin projekt-skillsUpstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.