Markdown to Jira

VerifiedCaution

Convert structured Markdown into Jira Cloud Epic/Task issues using MCP, with metadata and file update.

Sby Skills Guide Bot
ProductivityIntermediate
7/24/2026
Claude CodeCursorWindsurf
#jira-cloud#markdown#mcp#issue-tracking#automation

Recommended for

Automated summary

Creates Jira Cloud epics and tasks from a structured Markdown file over MCP, then writes the real issue keys and parentEpic back into the document.

Strengths

  • Enforces creation order (Epic first, then Tasks) and swaps the nominal parentEpic for the real key of the created epic
  • Validates each block's required metadata (project, type, summary, component, labels) before calling Jira
  • Fills in labels and components through jira_editJiraIssue when Jira leaves them empty on creation
  • Always rewrites the Markdown with the issueKey values and refuses to recreate an issue that already has a key without explicit confirmation

Limitations

  • Requires a very strict Markdown layout (Issue Metadata, Scenario, Acceptance Tests, Sources) and stops when it is missing
  • Depends on a configured and reachable Jira MCP server
  • Does not handle status transitions, sprints or custom fields
When to use it

Use it when a backlog is already written in Markdown in this format and you want it materialised in Jira without retyping.

When not to use it

Avoid it when the issues already exist in Jira or when the document does not follow the required block structure.

Security analysis

Caution
Quality score78/100

The skill does nothing destructive or exfiltrating: no shell, no curl|sh, no secret handling, no obfuscated payloads. However it does drive real external mutations (creating/editing Jira issues) and rewrites a local file in place, and it processes arbitrary user/third-party Markdown as trusted input. These are legitimate but powerful operations, warranting a caution rather than safe.

Findings
  • •Creates and edits issues in an external Jira Cloud instance (real side effects) with no dry-run or confirmation except when an issueKey already exists.
  • •Rewrites the source Markdown file in place to inject issueKey/parentEpic; careless writes could overwrite or corrupt the user's document, and the write mechanism/tool is never specified.
  • •Content from the Markdown (Scenario, Acceptance Tests, Sources) is treated as instructions and copied verbatim into Jira, so an untrusted markdown file could inject misleading content or prompt-injection text into the tracker.
  • •No allowed-tools are declared, so the actual capabilities (MCP jira tools, file read/write) depend entirely on the host agent and are unbounded by the skill itself.
How this analysis is made

Examples

Create a backlog from Markdown
Usa el skill markdown-to-jira con docs/backlog-checkout.md y crea en Jira el epic y las tasks descritas.
Sync and write back keys
Sincroniza este backlog markdown con Jira, crea las tasks que falten y actualiza los issue keys y el parentEpic en el archivo.
Tasks only, no epic
Crea en Jira solo las tasks de este markdown (no hay bloque Epic), aplicando labels y components.

name: markdown-to-jira description: Skill para crear issues de tipo epic y/o task en Jira Cloud a partir de un archivo Markdown y luego completar componentes, labels y issue keys. metadata: opencode: emoji: 🧩 tags: - jira-cloud - markdown - mcp - workflow mcp: preferredServer: jira

Markdown to Jira

Usa este skill cuando tengas un archivo Markdown con bloques de Epic y/o Task y quieras crear esas issues en Jira Cloud usando MCP.

Objetivo

Convertir un archivo Markdown estructurado en:

  • un Epic en Jira cuando exista un bloque Epic
  • una o varias Task en Jira cuando existan bloques Task
  • labels y components aplicados despues de la creacion
  • issue keys y parentEpic reales escritos de vuelta en el documento

Formato esperado del Markdown

Cada bloque debe incluir:

  • encabezado # Epic: o # Task:
  • seccion ## Issue Metadata
  • ## Scenario
  • ### Acceptance Tests
  • ### Sources:

Metadatos requeridos por tipo de bloque

Para cualquier bloque:

  • projectKey
  • issueType
  • summary
  • component
  • labels

Solo para bloques Task:

  • parentEpic cuando la task deba quedar vinculada a un epic

Notas:

  • Un documento puede tener solo bloques Task.
  • Un documento puede tener un bloque Epic y uno o mas bloques Task.
  • Si existe Epic y Task, el orden de creacion debe ser Epic y luego Task.

Flujo operativo

  1. Leer el archivo Markdown indicado por el usuario.
  2. Identificar si hay bloques Epic, bloques Task o ambos.
  3. Validar cada bloque segun su tipo:
    • Epic: debe incluir Issue Metadata, Scenario, Acceptance Tests y Sources, con sus metadatos requeridos.
    • Task: debe incluir Issue Metadata, Scenario, Acceptance Tests y Sources, con sus metadatos requeridos.
  4. Si existe un bloque Epic, crearlo primero con Jira MCP.
  5. Guardar el issueKey real del epic si fue creado.
  6. Crear cada Task:
    • si el documento tambien define un Epic, usar el key real del epic creado como parent
    • si el documento no define un Epic, usar el parentEpic del Markdown solo si viene informado
  7. Ejecutar jira_editJiraIssue para aplicar:
    • labels
    • components
  8. Actualizar siempre el Markdown con:
    • issueKey del epic
    • issueKey de cada task
    • parentEpic con el key real cuando corresponda

Reglas de comportamiento

  • No inventes projectKey, component ni labels.
  • Usa exactamente los valores escritos en el Markdown.
  • Valida los metadatos requeridos segun el tipo de bloque antes de crear issues.
  • Si el documento tiene Epic y Task, crea primero el Epic y luego las Task.
  • Si el documento tiene solo Task, no exijas un bloque Epic.
  • Si una Task referencia un parentEpic nominal y el documento incluye un Epic, sustituyelo por el key real del epic creado.
  • Si Jira acepta la creacion pero deja vacios components o labels, completa esos campos con jira_editJiraIssue.
  • Despues de crear las issues, actualiza siempre el Markdown con los issueKey y parentEpic reales que correspondan.
  • Si el Markdown ya contiene issueKey, no recrees la issue sin confirmacion explicita del usuario.
  • Si el archivo no tiene estructura valida, detente y explica que falta.

Payload de actualizacion validado

{
  "fields": {
    "labels": ["ai-enablement"],
    "components": [{ "name": "I+D" }]
  }
}

Tu humano puede pedirte

  • "Usa el skill markdown-to-jira con este archivo"
  • "Crea en Jira las issues descritas en este markdown"
  • "Sincroniza este backlog markdown con Jira y actualiza los issue keys"

From the file to a first result

The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.

View the source and supporting files

This download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.

1. Download the file

Download SKILL.md

From the root of a test project, save the file as .skill-downloads/markdown-to-jira-mryiqiic/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.

Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.

mkdir -p '.skill-downloads/markdown-to-jira-mryiqiic' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/markdown-to-jira-mryiqiic/download' --output '.skill-downloads/markdown-to-jira-mryiqiic/SKILL.md.part' && mv '.skill-downloads/markdown-to-jira-mryiqiic/SKILL.md.part' '.skill-downloads/markdown-to-jira-mryiqiic/SKILL.md'

2. Check prerequisites

Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.

No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.

The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.

3. Load the skill

After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.

Claude Code
test -f '.skill-downloads/markdown-to-jira-mryiqiic/SKILL.md' && test -s '.skill-downloads/markdown-to-jira-mryiqiic/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/markdown-to-jira' && cp -R '.skill-downloads/markdown-to-jira-mryiqiic' '.claude/skills/markdown-to-jira'

Cursor
test -f '.skill-downloads/markdown-to-jira-mryiqiic/SKILL.md' && test -s '.skill-downloads/markdown-to-jira-mryiqiic/SKILL.md' && mkdir -p '.cursor/skills' && test ! -e '.cursor/skills/markdown-to-jira' && cp -R '.skill-downloads/markdown-to-jira-mryiqiic' '.cursor/skills/markdown-to-jira'

OpenSkills

OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.

Official OpenSkills installation
openskills install './.skill-downloads/markdown-to-jira-mryiqiic'

openskills read 'markdown-to-jira-mryiqiic'

Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.

For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.

openskills sync

Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.

4. Try a first task

Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:

Read .skill-downloads/markdown-to-jira-mryiqiic/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.

Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.

Related skills