resolve-blockers — for Claude Code resolve-blockers, tanren, community, for Claude Code, ide skills, investigate, escalate_to_blocker, create_task(origin: User), revise_task(…), create_task

v1.0.0
GitHub

Acerca de este Skill

Escenario recomendado: Ideal for AI agents that need interactive escalation-resolution phase. triggered only after. Resumen localizado: # resolve-blockers Purpose Interactive escalation-resolution phase. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

Características

Interactive escalation-resolution phase. Triggered only after
investigate has hit its loop cap and called escalate to blocker.
Present the investigation-derived options to the user, capture the
chosen path via typed tool calls, then exit so the orchestrator
Inputs (from your dispatch)

# Temas principales

for Claude Code investigate escalate_to_blocker create_task(origin: User) revise_task(…) create_task
trevorWieland trevorWieland
[2]
[1]
Actualizado: 4/27/2026

Skill Overview

Start with fit, limitations, and setup before diving into the repository.

Escenario recomendado: Ideal for AI agents that need interactive escalation-resolution phase. triggered only after. Resumen localizado: # resolve-blockers Purpose Interactive escalation-resolution phase. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

¿Por qué usar esta habilidad?

Recomendacion: resolve-blockers helps agents interactive escalation-resolution phase. triggered only after. resolve-blockers Purpose Interactive escalation-resolution phase. This AI agent skill supports Claude Code

Mejor para

Escenario recomendado: Ideal for AI agents that need interactive escalation-resolution phase. triggered only after.

↓ Casos de uso accionables for resolve-blockers

Caso de uso: Applying Interactive escalation-resolution phase. Triggered only after
Caso de uso: Applying investigate has hit its loop cap and called escalate to blocker
Caso de uso: Applying Present the investigation-derived options to the user, capture the

! Seguridad y limitaciones

  • Limitacion: Interactive escalation-resolution phase. Triggered only after
  • Limitacion: Replacement tasks must be created first via create task.
  • Limitacion: ⚠ ORCHESTRATOR-OWNED ARTIFACT — DO NOT EDIT.

About The Source

The section below comes from the upstream repository. Use it as supporting material alongside the fit, use-case, and installation summary on this page.

Demo Labs

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

FAQ y pasos de instalación

These questions and steps mirror the structured data on this page for better search understanding.

? Preguntas frecuentes

¿Qué es resolve-blockers?

Escenario recomendado: Ideal for AI agents that need interactive escalation-resolution phase. triggered only after. Resumen localizado: # resolve-blockers Purpose Interactive escalation-resolution phase. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

¿Cómo instalo resolve-blockers?

Ejecuta el comando: npx killer-skills add trevorWieland/tanren/resolve-blockers. Funciona con Cursor, Windsurf, VS Code, Claude Code y más de 19 IDE adicionales.

¿Cuáles son los casos de uso de resolve-blockers?

Los casos de uso principales incluyen: Caso de uso: Applying Interactive escalation-resolution phase. Triggered only after, Caso de uso: Applying investigate has hit its loop cap and called escalate to blocker, Caso de uso: Applying Present the investigation-derived options to the user, capture the.

¿Qué IDE son compatibles con resolve-blockers?

Esta skill es compatible con Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer. Usa la CLI de Killer-Skills para una instalación unificada.

¿Tiene limitaciones resolve-blockers?

Limitacion: Interactive escalation-resolution phase. Triggered only after. Limitacion: Replacement tasks must be created first via create task.. Limitacion: ⚠ ORCHESTRATOR-OWNED ARTIFACT — DO NOT EDIT..

↓ Cómo instalar este skill

  1. 1. Abre tu terminal

    Abre la terminal o línea de comandos en el directorio de tu proyecto.

  2. 2. Ejecuta el comando de instalación

    Ejecuta: npx killer-skills add trevorWieland/tanren/resolve-blockers. La CLI detectará tu IDE o agente automáticamente y configurará la skill.

  3. 3. Empieza a usar el skill

    El skill ya está activo. Tu agente de IA puede usar resolve-blockers de inmediato en el proyecto actual.

! Source Notes

This page is still useful for installation and source reference. Before using it, compare the fit, limitations, and upstream repository notes above.

Upstream Repository Material

The section below comes from the upstream repository. Use it as supporting material alongside the fit, use-case, and installation summary on this page.

Upstream Source

resolve-blockers

# resolve-blockers Purpose Interactive escalation-resolution phase. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows. Interactive

SKILL.md
Readonly
Upstream Repository Material
The section below comes from the upstream repository. Use it as supporting material alongside the fit, use-case, and installation summary on this page.
Upstream Source

resolve-blockers

Purpose

Interactive escalation-resolution phase. Triggered only after investigate has hit its loop cap and called escalate_to_blocker. Present the investigation-derived options to the user, capture the chosen path via typed tool calls, then exit so the orchestrator resumes.

Inputs (from your dispatch)

  • The blocker reason and option list produced by the upstream investigate call.
  • The spec folder state at the time of escalation.
  • All prior investigation reports for this fingerprint.

Responsibilities

  1. Summarize the blocker to the user in one paragraph. Pull context from the investigation report.
  2. Present the options (at least: fix-in-place via new/revised task; abandon + replace; defer to future spec). Recommend one.
  3. Wait for the user's decision.
  4. Apply the chosen path with typed tools:
    • Fix in place: create_task(origin: User) or revise_task(…).
    • Abandon: abandon_task(task_id, reason, replacements). Replacement tasks must be created first via create_task.
    • Defer to future spec: abandon_task with an acknowledgment that no replacement will be created here; the user can spin a new spec later.
  5. Call report_phase_outcome("complete", <user-chosen path>).

Out of scope

  • Escalating further (resolve-blockers never chain-escalates; if the user cannot decide, report_phase_outcome("error", …))
  • Editing plan.md, progress.json, or orchestrator-owned files
  • Creating GitHub issues directly
  • Implementing any code change

⚠ ORCHESTRATOR-OWNED ARTIFACT — DO NOT EDIT. spec.md, plan.md, tasks.md, tasks.json, demo.md, audit.md, signposts.md, progress.json, and .tanren-projection-checkpoint.json are generated from the typed event stream. Postflight reverts unauthorized edits and emits an UnauthorizedArtifactEdit event. Use the typed tool surface (MCP or CLI) to record progress.

Use Tanren MCP tools for all structured mutations in this phase. MCP-first canonical invocation set for phase resolve-blockers: The orchestrator exports TANREN_CLI, TANREN_DATABASE_URL, TANREN_CONFIG, and TANREN_SPEC_FOLDER; use those values directly for CLI tool calls.

  • MCP create_task payload: {"schema_version":"1.0.0","spec_id":"00000000-0000-0000-0000-000000000000","title":"task title","description":"task description","origin":{"kind":"user"},"acceptance_criteria":[]}
  • CLI create_task command: "$TANREN_CLI" --database-url "$TANREN_DATABASE_URL" methodology --methodology-config "$TANREN_CONFIG" --phase resolve-blockers --spec-id <spec_uuid> --spec-folder "$TANREN_SPEC_FOLDER" task create --json '{"schema_version":"1.0.0","spec_id":"00000000-0000-0000-0000-000000000000","title":"task title","description":"task description","origin":{"kind":"user"},"acceptance_criteria":[]}'
  • MCP revise_task payload: {"schema_version":"1.0.0","task_id":"00000000-0000-0000-0000-000000000000","revised_description":"updated details","revised_acceptance":[],"reason":"clarify acceptance"}
  • CLI revise_task command: "$TANREN_CLI" --database-url "$TANREN_DATABASE_URL" methodology --methodology-config "$TANREN_CONFIG" --phase resolve-blockers --spec-id <spec_uuid> --spec-folder "$TANREN_SPEC_FOLDER" task revise --json '{"schema_version":"1.0.0","task_id":"00000000-0000-0000-0000-000000000000","revised_description":"updated details","revised_acceptance":[],"reason":"clarify acceptance"}'
  • MCP abandon_task payload: {"schema_version":"1.0.0","task_id":"00000000-0000-0000-0000-000000000000","reason":"superseded","disposition":"replacement","replacements":[]}
  • CLI abandon_task command: "$TANREN_CLI" --database-url "$TANREN_DATABASE_URL" methodology --methodology-config "$TANREN_CONFIG" --phase resolve-blockers --spec-id <spec_uuid> --spec-folder "$TANREN_SPEC_FOLDER" task abandon --json '{"schema_version":"1.0.0","task_id":"00000000-0000-0000-0000-000000000000","reason":"superseded","disposition":"replacement","replacements":[]}'
  • MCP list_tasks payload: {"schema_version":"1.0.0","spec_id":"00000000-0000-0000-0000-000000000000"}
  • CLI list_tasks command: "$TANREN_CLI" --database-url "$TANREN_DATABASE_URL" methodology --methodology-config "$TANREN_CONFIG" --phase resolve-blockers --spec-id <spec_uuid> --spec-folder "$TANREN_SPEC_FOLDER" task list --json '{"schema_version":"1.0.0","spec_id":"00000000-0000-0000-0000-000000000000"}'
  • MCP report_phase_outcome payload: {"schema_version":"1.0.0","spec_id":"00000000-0000-0000-0000-000000000000","outcome":{"outcome":"complete","summary":"phase complete"}}
  • CLI report_phase_outcome command: "$TANREN_CLI" --database-url "$TANREN_DATABASE_URL" methodology --methodology-config "$TANREN_CONFIG" --phase resolve-blockers --spec-id <spec_uuid> --spec-folder "$TANREN_SPEC_FOLDER" phase outcome --json '{"schema_version":"1.0.0","spec_id":"00000000-0000-0000-0000-000000000000","outcome":{"outcome":"complete","summary":"phase complete"}}'

Habilidades relacionadas

Looking for an alternative to resolve-blockers or another community skill for your workflow? Explore these related open-source skills.

Ver todo

openclaw-release-maintainer

Logo of openclaw
openclaw

Resumen localizado: 🦞 # OpenClaw Release Maintainer Use this skill for release and publish-time workflow. It covers ai, assistant, crustacean workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

★ 333.8k
⑂ 0
Inteligencia Artificial

widget-generator

Logo of f
f

Resumen localizado: Generate customizable widget plugins for the prompts.chat feed system # Widget Generator Skill This skill guides creation of widget plugins for prompts.chat . It covers ai, artificial-intelligence, awesome-list workflows. This AI agent skill supports Claude Code, Cursor, and

★ 149.6k
⑂ 0
Inteligencia Artificial

flags

Logo of vercel
vercel

Resumen localizado: The React Framework # Feature Flags Use this skill when adding or changing framework feature flags in Next.js internals. It covers blog, browser, compiler workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

★ 138.4k
⑂ 0
Navegador

pr-review

Logo of pytorch
pytorch

Resumen localizado: Usage Modes No Argument If the user invokes /pr-review with no arguments, do not perform a review . It covers autograd, deep-learning, gpu workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

★ 98.6k
⑂ 0
Desarrollador