alias-creator
This skill should be used when the user wants to create a custom agent alias theme, edit an existing theme, preview theme mappings, or manage alias configurations. Triggers on phrases like "create a theme", "new alias theme", "custom theme", "edit theme", "preview theme", "show themes", "list themes", "alias", "character theme", "personality theme", "add a theme".
What this skill does
# Alias Theme Creator
Create, edit, preview, and manage agent alias themes for the delivery team pipeline.
## What Are Alias Themes?
Alias themes give each delivery team role a themed character name and personality. When a theme is active, every sub-agent speaks in character — Gandalf gives wise product advice, Gimli builds code with directness, Legolas catches bugs with elven precision.
Built-in themes are in `delivery-flow/references/aliases/`. Custom themes are stored per-repo in `.delivery/aliases/`.
---
## Creating a Custom Theme
### Interactive Creation
Walk the user through creating a theme step by step:
1. **Theme identity**: Ask for theme name (kebab-case), display name, and personality strength (light/moderate/full)
2. **For each of the 13 roles**, ask:
- Character name
- Personality description (1-2 sentences)
- Catchphrase (or "none")
- Communication style (free text)
- 2 example voice lines (how this character talks about delivery work)
3. **Validate**: All 13 roles mapped, all required fields present
4. **Write**: Save to `.delivery/aliases/<theme-name>.yml`
### Quick Creation from Description
If the user provides a theme concept (e.g., "Harry Potter theme"), generate all 13 role mappings automatically:
1. Map each role to the best-fitting character based on traits
2. Write personality notes that match the character's known behavior
3. Generate catchphrases adapted from source material
4. Present the full mapping for user review before saving
5. User can edit individual roles before finalizing
### Partial Themes
Themes don't need all 13 roles. Unmapped roles fall back to the Business theme. Mark partial themes:
```yaml
theme: my-partial-theme
display_name: "My Partial Theme"
personality_strength: moderate
min_roles_version: 13
partial: true # indicates not all roles are mapped
```
---
## The 13 Delivery Team Roles
Every theme maps these roles:
| Role ID | Role Name | What They Do |
|---------|-----------|-------------|
| `product-owner` | Product Owner | Business value, user stories, PRDs, backlogs |
| `scrum-master` | Scrum Bag | Process facilitation, retros, velocity, ceremonies |
| `data-analyst` | Data Analyst | Metrics, analytics, A/B testing, dashboards |
| `developer` | Developer | Code implementation across 14 languages |
| `architect` | Architect | System design, ADRs, decomposition, C4 models |
| `qa-engineer` | QA Engineer | Test strategy, test cases, quality metrics |
| `devops` | DevOps Engineer | CI/CD, deployment, infrastructure, monitoring |
| `release-manager` | Release Manager | Release planning, versioning, rollback, feature flags |
| `tech-writer` | Technical Writer | API docs, user guides, runbooks, release notes |
| `ux-designer` | UX Designer | User flows, wireframes, usability, research |
| `ui-designer` | UI Designer | Design systems, components, accessibility, interactions |
| `game-ui-designer` | Game UI Designer | HUD, menus, inventory UI, game accessibility |
| `user-feedback` | User Feedback | Feedback facilitator (personas keep their own identities) |
---
## Theme File Format
```yaml
theme: my-theme # kebab-case, used in config
display_name: "My Custom Theme" # human-readable name
personality_strength: moderate # light | moderate | full
min_roles_version: 13 # current number of roles
roles:
product-owner:
character: "Character Name"
personality: "1-2 sentence personality description."
catchphrase: "Signature line or none"
style: "communication style, free text"
examples:
- "Example of how this character talks about delivery work"
- "Another example showing their voice"
scrum-master:
character: "..."
personality: "..."
catchphrase: "..."
style: "..."
examples:
- "..."
- "..."
# ... repeat for all 13 roles
```
### Personality Strength
| Level | What It Means | Prompt Impact |
|-------|-------------|--------------|
| **light** | Name + occasional flavor | Character name used, personality note minimal, no examples injected |
| **moderate** | Consistent voice | Full personality note + style + 1 example injected |
| **full** | Deep character commitment | Full personality + catchphrase + 2 examples + "do not break character" |
### Style Examples
Style is free text. Good examples:
- "wise, measured, occasionally cryptic"
- "blunt, direct, uses construction metaphors"
- "sardonic, dry humor, references coffee addiction"
- "enthusiastic, uses exclamation points, sports metaphors"
- "calm, methodical, speaks in numbered steps"
---
## Theme Management Commands
| Command | Action |
|---------|--------|
| `create theme` | Start interactive theme creation |
| `create theme from [concept]` | Auto-generate theme from a concept description |
| `edit theme [name]` | Edit an existing custom theme |
| `preview theme [name]` | Show all 13 role mappings for a theme |
| `list themes` | List all available themes (built-in + custom) |
| `validate theme [name]` | Check theme for completeness and quality |
| `delete theme [name]` | Delete a custom theme (cannot delete built-ins) |
---
## Built-In Themes
These ship with the delivery-team plugin (in `delivery-flow/references/aliases/`):
| Theme | Display Name | Vibe |
|-------|-------------|------|
| `business` | Business | Professional defaults (current behavior) |
| `funny` | Funny | Comedy aliases (Scrum Bag, Code Monkey, Bug Hunter) |
| `lotr` | Lord of the Rings | Fellowship of the Delivery Team |
| `marvel` | Marvel (MCU) | Avengers assemble for shipping |
| `mtg` | Magic: The Gathering | Planeswalkers of the pipeline |
| `dilbert` | Dilbert | Office comic dysfunction |
| `bulls-jordan` | Chicago Bulls 1991-1998 | Dynasty-era basketball legends |
| `nfl` | NFL All-Time Greats | Football hall of famers |
| `snl` | Saturday Night Live | Live from the sprint review |
| `star-wars` | Star Wars | A long time ago in a codebase far away |
| `mandalorian` | The Mandalorian | This is the Way (of delivering software) |
| `breaking-bad` | Breaking Bad | Say my name (it's in the config) |
| `the-office` | The Office | Dunder Mifflin delivery team |
To activate: set `aliases.theme: lotr` in `.delivery/config.yml`.
---
## Validation Checklist
When validating a theme (built-in or custom):
- [ ] All 13 role IDs present (or marked as `partial: true`)
- [ ] Every mapped role has: character, personality, style (catchphrase and examples optional for light themes)
- [ ] No role mapped to a non-sentient object (must be a character/person)
- [ ] Character-role fit makes sense (character traits align with role function)
- [ ] For `full` personality strength: examples must be present for every role
- [ ] `min_roles_version` matches current role count (13)
- [ ] Theme name is kebab-case
- [ ] `user-feedback` note about facilitator-only applies
## Cross-Skill References
| File | Owner Skill | Purpose |
|------|-------------|---------|
| `delivery-team/skills/delivery-flow/references/aliases/*.yml` | delivery-flow | Built-in alias theme definitions. 13 themes (lotr, star-wars, marvel, etc.). Read-only from alias-creator's perspective. |
> Path stability: these paths are contracts. Renaming the owner skill's directory is a breaking change.
## References
- `references/theme-format.md` — Detailed theme file format documentation with field-by-field spec
Related 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.