github-ticket
Create, route, and inspect GitHub issues from Claude Code or Codex with gh CLI-backed defaults for DiversioTeam/monolith, repo-local execution repos, and project-board hydration.
What this skill does
# GitHub Ticket Skill
## When to Use This Skill
Use this Skill when you want to:
- create GitHub issues without opening the browser
- capture backlog work quickly with smart defaults
- fetch or list issues across `monolith` and a small repo set
- view your assigned work
- route planning work into repo-local execution issues
- add created issues to `Diversio Work` with the right board fields
- keep GitHub issue creation skill-driven instead of form-driven
This Skill is the GitHub-native replacement for the old `clickup-ticket`
workflow. Issue forms in `monolith` are a human fallback and a schema
reference, not the primary creation path.
## Prerequisites
Before doing anything else:
1. Run `gh auth status`.
2. Confirm `gh` is authenticated for the right GitHub account.
3. Confirm the token has the scopes needed for the requested action:
- `repo` for issue read/write
- `read:org` for org visibility
- `project` when project add or field hydration is expected
4. Fail fast if `gh` is missing or unauthenticated.
Preferred auth model:
- normal `gh` login
- no plugin-specific token in the common case
- if project hydration is part of the workflow and `project` scope is missing,
prefer `gh auth refresh -s project`
## Default Operating Model
Treat these defaults as the steady-state baseline unless the user overrides
them:
- planning repo: `DiversioTeam/monolith`
- execution repos:
- `DiversioTeam/Django4Lyfe`
- `DiversioTeam/Diversio-Frontend`
- `DiversioTeam/Optimo-Frontend`
- `DiversioTeam/diversio-ds`
- `DiversioTeam/infrastructure`
- `DiversioTeam/naboo`
- `DiversioTeam/diversio-serverless`
- `DiversioTeam/launchpad`
- `DiversioTeam/skiddie`
- `DiversioTeam/terraform-modules`
- `DiversioTeam/agent-skills-marketplace`
- canonical IDs: native GitHub issue numbers
- legacy ClickUp `GH-xxxx` IDs: metadata only when applicable
Routing rules:
- If you are in the monolith root and no repo is specified, prefer
`DiversioTeam/monolith`.
- If you are inside a repo checkout and no repo is specified, prefer that repo
as the execution repo after normalizing the git remote into `owner/repo`.
- If the work clearly spans repos or still needs planning, create the issue in
`DiversioTeam/monolith`.
- If the user asks for implementation work in a specific repo, create the
issue in that repo when issues are enabled there.
- If repo detection yields a GitHub repo outside the default execution list,
it is still valid to use that repo; do not reject it only because it is not
prelisted in config.
## Local Config
Default config path:
```bash
CONFIG_DIR="${XDG_CONFIG_HOME:-$HOME/.config}/github-ticket"
CONFIG_FILE="${CONFIG_DIR}/config.json"
```
Use a small JSON file with fields like:
- `planning_repo`
- `execution_repos`
- `backlog_labels`
- `quick_issue_labels`
- `project_owner`
- `project_number`
- `project_field_defaults`
- optional `path_repo_map`
See `references/config-and-body-shape.md` for a sample config and issue body.
For the current Diversio baseline, prefer organization project `#2`
(`Diversio Work`) unless the user overrides project placement.
Treat `project_field_defaults` as a display-name keyed map for stable defaults
like `Status` and `Priority`, not as a place to hard-code field or option IDs.
Prefer runtime repo detection from the current git checkout before falling back
to `path_repo_map`. In worktree-heavy setups, avoid hard-coded absolute path
maps unless there is a real non-git edge case.
## Repo Alias Map
Allow these shorthand values when the user names a repo informally:
- `monolith` -> `DiversioTeam/monolith`
- `backend` -> `DiversioTeam/Django4Lyfe`
- `frontend` -> `DiversioTeam/Diversio-Frontend`
- `optimo-frontend` -> `DiversioTeam/Optimo-Frontend`
- `design-system` -> `DiversioTeam/diversio-ds`
- `infrastructure` -> `DiversioTeam/infrastructure`
- `naboo` -> `DiversioTeam/naboo`
- `diversio-serverless` -> `DiversioTeam/diversio-serverless`
- `launchpad` -> `DiversioTeam/launchpad`
- `skiddie` -> `DiversioTeam/skiddie`
- `terraform-modules` -> `DiversioTeam/terraform-modules`
- `agent-skills-marketplace` -> `DiversioTeam/agent-skills-marketplace`
- `skills-marketplace` -> `DiversioTeam/agent-skills-marketplace`
If a repo alias is ambiguous, ask one short clarifying question.
## Command Modes
### `configure`
Goal:
- validate `gh` auth
- create or update local defaults
- keep prompts minimal
Workflow:
1. Run `gh auth status`.
2. Detect the current checkout path and repo if possible:
- prefer `git rev-parse --show-toplevel`
- then `git remote get-url origin`
- normalize SSH or HTTPS GitHub remotes into `owner/repo`
3. Create `${XDG_CONFIG_HOME:-$HOME/.config}/github-ticket/config.json` if missing.
4. Gather only the missing defaults:
- planning repo
- preferred execution repos
- backlog labels
- quick-issue labels
- project owner/number
- optional project field defaults such as `Status` and `Priority`
- only add `path_repo_map` when repo detection via git is insufficient
Use `jq` to write or update the config rather than inventing a custom format.
If project config is present but `gh auth status` shows no `project` scope,
surface that clearly instead of pretending project hydration will work.
### `get-issue`
Accepted input formats:
- `1234`
- `#1234`
- `owner/repo#1234`
- a GitHub issue URL
Behavior:
1. Resolve the issue reference to a repo plus number.
2. Use `gh issue view`.
3. Return title, state, assignees, labels, body summary, and key links.
4. If the issue is in another repo, show that clearly.
### `list-issues`
Prefer the smallest backend that matches the ask:
- one repo: `gh issue list`
- cross-repo or richer filtering: `gh search issues`
Support these filters:
- repo
- assignee
- label
- open / closed state
- `imported: clickup`
- updated recently
Keep the filter model smaller than the old ClickUp plugin.
### `my-issues`
This is the convenience view for assigned work.
Default behavior:
- search across the planning repo plus configured execution repos
- show open issues assigned to `@me`
- prefer recently updated or explicitly blocked work near the top
Use `gh search issues --assignee @me --state open` when a cross-repo query is
needed.
### `create-issue`
This is the full interactive creation path.
Gather:
- title
- work type
- target repo
- problem or request
- success criteria
- optional constraints or non-goals
- optional supporting links
- optional legacy ClickUp metadata
Then:
1. Choose the repo using the routing rules.
2. Build the canonical issue body.
3. Apply labels:
- always include `triage` unless the user says otherwise
- map work type to `type:*` labels when available
4. Create the issue with `gh issue create`.
5. If project config exists, or the current Diversio baseline applies, add the
issue to the project with `gh project item-add`.
6. If the project add succeeds, hydrate the common project fields immediately:
- `Status`
- `Target Repo`
- optional `Priority`
7. For `Status`, prefer:
- `Ready` for scoped, actionable work
- `Blocked` when the issue depends on incomplete upstream work
- `Inbox` only for intentionally rough capture
8. For `Target Repo`, map the destination repository to the matching project
option when that field exists. If there is no exact option for that repo,
use `other` instead of leaving the field blank.
9. Never block issue creation on project assignment or field hydration, but do
report the failure clearly so the user is not left with invisible board
items.
10. If project hydration fails because of missing `project` scope, say that
explicitly and point at `gh auth refresh -s project`.
### `quick-issue`
This should stay under three prompts.
Required input:
- title
Preferred flow:
1. Infer repo from current directory or config.
2. Use default quick-issue labels.
3. Create a minimal but useful body.
4. If the result is still intentionallyRelated in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.