Skip to content
cccskills
FreePublished on GitHub

mk-jira

Routing skill — recommends the correct mk:jira-* leaf for any Jira task. Triggers: 'jira', 'jira ticket', ambiguous Jira intent. NOT an executor — every actual operation forks via a leaf skill.

The English summary is being prepared. Showing the original description.

Works withConfluenceJira
See how to install

Files included (10)

  • SKILL.md3.6 KB
  • references/cli-idioms.md8.3 KB
  • references/estimation-guide.md2.0 KB
  • references/evaluation-rubric.md2.5 KB
  • references/install-and-auth.md3.9 KB
  • references/safety-framework.md5.7 KB
  • scripts/fetch-workflow.sh5.3 KB
  • scripts/jira-as.sh1.2 KB
  • scripts/jql-sanitize.sh1.8 KB
  • scripts/requirements.txt248 B

SKILL.md (original)

Review the instructions the agent will receive before you install.

mk:jira — Routing Skill

This skill is a pure routing layer. Its sole purpose: identify the right mk:jira-* leaf for the user's Jira task, then point at it. No execution.

Routing Table

User intentLeaf skill
Get/create/update/delete a single issuemk:jira-issue
Find issues by criteria; export; filtersmk:jira-search
Transition through workflow; assign; resolvemk:jira-lifecycle
Comments, attachments, watchers, notifymk:jira-collaborate
Issue links, blockers, dependenciesmk:jira-relationships
Worklogs, time tracking, time reportsmk:jira-time
Epics, sprints, backlog, story pointsmk:jira-agile
Custom field discovery + configurationmk:jira-fields
Bulk ops (10+ issues, dry-run mandatory)mk:jira-bulk
Service Management (queues, SLAs, customers)mk:jira-jsm
Project/user/group/scheme administrationmk:jira-admin
Git/PR/branch-name integrationmk:jira-dev
Cache + project-context discoverymk:jira-ops
Evaluate ticket complexity + inconsistenciesmk:jira-evaluator
Estimate story points (heuristic)mk:jira-estimator
Analyze ticket context + media; RCAmk:jira-analyst

Setup

See references/install-and-auth.md for one-time setup (.codex/scripts/bin/setup-workflow installs jira-as into .agents/skills/.venv; populate .codex/.env with the 3 MEOW_JIRA_* vars).

Shared Resources (used by leaves)

  • scripts/jira-as.sh — env-translating wrapper (MEOW_JIRA_* → JIRA_*, sets JIRA_OUTPUT=json)
  • scripts/jql-sanitize.sh — JQL escaping for user-derived terms
  • scripts/requirements.txt — pip dependency manifest auto-discovered by .codex/scripts/bin/setup-workflow
  • references/install-and-auth.md — setup, exit codes, DC/mTLS caveats
  • references/cli-idioms.md — verified jira-as syntax + jq projection rules
  • references/safety-framework.md — 4-tier safety model
  • references/evaluation-rubric.md — used by mk:jira-evaluator
  • references/estimation-guide.md — used by mk:jira-estimator
  • ../jira-fields/references/field-discovery.md — used by mk:jira-fields (moved from jira/references/)

Handoff

  • mk:intake → recommends mk:jira-* leaf based on triage
  • mk:cook (build pipeline) → may invoke mk:jira-issue to create implementation tickets
  • mk:ship (ship pipeline) → may invoke mk:jira-dev for branch-name + PR-description
  • mk:planning-engine → consumes Jira tickets via this hub for sprint planning analysis (mk:jira-evaluator / mk:jira-estimator outputs enrich the planning report)
  • mk:confluence → sister hub for Confluence Cloud; mk:planning-engine accepts both Jira tickets (--tickets) and Confluence specs (--spec <report-path>) as input

Gotchas

  • mk:jira itself never executes; if you're in this skill thinking about jira-as commands, you're in the wrong place — forward to a leaf.
  • Escape hatch: if jira-as is unusable (mTLS, multi-profile), users may invoke Atlassian MCP directly per references/install-and-auth.md. The router does NOT auto-fallback.

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

Use this skill to generate well-branded interfaces and assets for MeowKit (AI Agent Toolkit for Claude Code), either for production or throwaway prototypes/mocks/etc. Contains essential design guidelines, colors, type, fonts, assets, and UI kit components for prototyping.

The English summary is being prepared. Showing the original description.

ngocsangyem/MeowKit15Updated Jul 28, 2026

Turn a raw idea into ONE honest recommendation: interview one question at a time until confirmed, then give a verdict with trade-offs and a checklist. Not for options or debate.

The English summary is being prepared. Showing the original description.

ngocsangyem/MeowKit15Updated Jul 28, 2026

Browser automation CLI for agents: navigate, click/fill, screenshot, extract data, test apps, Electron/Slack, cloud browsers. NOT for the user's real Chrome profile/cookies (mk:chrome-profile).

The English summary is being prepared. Showing the original description.

ngocsangyem/MeowKit15Updated Jul 28, 2026

Detects the right agent and complexity tier at Phase 0 orient; runs first in every workflow. NOT for runtime agent routing inside a single skill.

The English summary is being prepared. Showing the original description.

ngocsangyem/MeowKit15Updated Jul 28, 2026

Angular v20+ patterns: components, signals, services, forms, routing, HTTP, testing, SSR. Auto-activates on .ts files in Angular projects (angular.json detected).

The English summary is being prepared. Showing the original description.

ngocsangyem/MeowKit15Updated Jul 28, 2026

Design and review durable REST, GraphQL, RPC, or event API contracts: shape, compatibility, pagination, error semantics. Discovers existing consumers first. Not implementation, schema, or release.

The English summary is being prepared. Showing the original description.

ngocsangyem/MeowKit15Updated Jul 28, 2026

See all skills by ngocsangyem

Report a problem with this skill