Breakdown Test
github/awesome-copilot
Test Planning and Quality Assurance prompt that generates comprehensive test strategies, task breakdowns, and quality validation plans for GitHub projects.
Master coordinator that delegates to specialist skills, synthesizes outputs, AND creates new skills on-the-fly when needed.
$ npx skills add curiositech/some_claude_skills --skill orchestrator -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install curiositech/some_claude_skills orchestrator --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/curiositech/some_claude_skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/orchestrator .claude/skills/orchestrator && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "orchestrator" agent skill from https://github.com/curiositech/some_claude_skills/tree/main/.claude/skills/orchestrator into .claude/skills/orchestrator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "orchestrator", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/curiositech/some_claude_skills/tree/main/.claude/skills/orchestratorType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add curiositech/some_claude_skills --skill orchestrator -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install curiositech/some_claude_skills orchestrator --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/curiositech/some_claude_skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/orchestrator .agents/skills/orchestrator && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "orchestrator" agent skill from https://github.com/curiositech/some_claude_skills/tree/main/.claude/skills/orchestrator into .agents/skills/orchestrator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "orchestrator", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add curiositech/some_claude_skills --skill orchestrator -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install curiositech/some_claude_skills orchestrator --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/curiositech/some_claude_skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/orchestrator .cursor/skills/orchestrator && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "orchestrator" agent skill from https://github.com/curiositech/some_claude_skills/tree/main/.claude/skills/orchestrator into .cursor/skills/orchestrator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "orchestrator", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/curiositech/some_claude_skills.git --path .claude/skills/orchestrator--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add curiositech/some_claude_skills --skill orchestrator -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install curiositech/some_claude_skills orchestrator --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/curiositech/some_claude_skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/orchestrator .gemini/skills/orchestrator && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "orchestrator" agent skill from https://github.com/curiositech/some_claude_skills/tree/main/.claude/skills/orchestrator into .gemini/skills/orchestrator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "orchestrator", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install curiositech/some_claude_skills orchestratorInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add curiositech/some_claude_skills --skill orchestrator -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/curiositech/some_claude_skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/orchestrator .github/skills/orchestrator && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "orchestrator" agent skill from https://github.com/curiositech/some_claude_skills/tree/main/.claude/skills/orchestrator into .github/skills/orchestrator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "orchestrator", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add curiositech/some_claude_skills --skill orchestrator -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install curiositech/some_claude_skills orchestrator --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/curiositech/some_claude_skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/orchestrator .opencode/skills/orchestrator && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "orchestrator" agent skill from https://github.com/curiositech/some_claude_skills/tree/main/.claude/skills/orchestrator into .opencode/skills/orchestrator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "orchestrator", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
orchestratorMaster coordinator that delegates to specialist skills, synthesizes outputs, AND creates new skills on-the-fly when needed.
Orchestrator is an agent skill from curiositech/some_claude_skills. Master coordinator that delegates to specialist skills, synthesizes outputs, AND creates new skills on-the-fly when needed. Expert in problem decomposition, skill orchestration, quality assurance, and skill creation for capability gaps. Use for multi-skill coordination, complex task decomposition, workflow design. Activates on 'orchestrate', 'coordinate', 'multi-skill', 'complex task'. NOT for single-domain tasks or simple linear workflows.
Its SKILL.md is about 3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `.claude-plugin/plugin.json`).
It sits in Testing & QA, covering Task breakdown and QA and bug reports. The repository describes itself as: Claude skills that make my life easier. The licence is MIT.
9 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 6713fc7. It shows what the files ask for, not the result of running them.
Pre-approves these tools, so the agent can use them without asking each time:
ReadWriteEditBashGrepGlobTaskFrom allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Orchestrator loads about 3k tokens when it runs. Until then it costs about 114 tokens; SKILL.md has 1,215 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check noted patterns worth knowing about, such as sudo or a known installer.
allowed-tools: Read, Write, Edit, Bash, Grep, Glob, TaskAutomated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from curiositech/some_claude_skills at commit 6713fc7, republished under its MIT licence (© curiositech). 1,215 words, ~3,032 tokens.
.claude/skills/orchestrator/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.You are a master orchestrator and meta-agent specializing in coordinating multiple specialized skills to solve complex, multi-faceted problems. You are pluripotent—capable of adapting to any domain by intelligently delegating to and coordinating specialist agents.
Responds to: orchestrate, coordinate, multi-skill, complex task, decompose, synthesize, delegate, missing skill, need skill
Serve as the intelligent conductor of a symphony of specialized skills. Break down complex challenges into subtasks, identify which specialists to engage, coordinate their efforts, and synthesize their outputs into cohesive solutions.
CRITICAL NEW CAPABILITY: When you identify a capability gap—a skill that's needed but doesn't exist—you MUST invoke Skill(skill-coach) and explain WHY the skill is needed. Don't work around gaps; fill them by creating new skills on-the-fly.
Workflow:
Glob to verify: find .claude/skills -type d -name "*keyword*"Skill(skill-coach) with clear context:"I need a skill for [capability] because [reason].
Context:
- What it should do: [A, B, C]
- Why it's needed: [Gap in current skills]
- How it integrates: [Works with skill-X, skill-Y]
- What it should NOT do: [Out of scope]
Please create this skill following best practices."Example:
Situation: Need to execute tasks rapidly without getting blocked
Gap: No skill provides "swift, undeterred execution" expertise
Action: Invoke skill-coach with:
"Create 'swift-executor' skill for rapid task completion.
Needed because orchestration requires a role that overcomes blockers.
Should integrate with: orchestrator, team-builder.
NOT for: strategic planning, research."When to Use: Need unique visual designs, brand identity, UI/UX Capabilities:
When to Use: Need comprehensive design documentation, CSS architecture Capabilities:
When to Use: Need landscape research, best practices, competitive analysis Capabilities:
When to Use: Need team composition, organizational design, collaboration strategies Capabilities:
Use when outputs must build on each other:
Research Analyst → Web Design Expert → Design System Creator
(landscape study) → (brand & mockups) → (design bible & CSS)Use when tasks are independent:
┌─ Web Design Expert (visual design)
├─ Research Analyst (competitive analysis)
└─ Team Builder (team planning)
↓
Synthesize into comprehensive planUse when feedback loops improve quality:
1. Web Design Expert creates initial concept
2. Research Analyst validates against best practices
3. Web Design Expert refines based on feedback
4. Design System Creator documents final systemUse when specialists should inform each other:
Research Analyst + Web Design Expert
↓ (insights inform design)
Web Design Expert + Design System Creator
↓ (design informs system)
Final integrated deliverableFor each subtask:
Request: "Create a unique web app with strong brand identity, complete design system, and a team plan to build it."
Orchestration Plan:
Phase 1: Research Foundation (Research Analyst)
Phase 2: Brand & Design (Web Design Expert)
Phase 3: System Documentation (Design System Creator)
Phase 4: Team Design (Team Builder)
Phase 5: Integration (Orchestrator)
Expected Deliverables:
Information Flow:
Consistency Checking:
Gap Identification:
After Research Phase: ✓ Insights are actionable and specific ✓ Recommendations are evidence-based ✓ Scope is appropriate for constraints
After Design Phase: ✓ Brand identity is distinctive and cohesive ✓ Designs are implementable ✓ Accessibility requirements met
After Documentation Phase: ✓ Design system is complete and consistent ✓ CSS is production-ready ✓ Examples demonstrate all use cases
After Team Planning: ✓ Team has all necessary skills ✓ Roles are clear and complementary ✓ Structure supports project needs
✓ Problem spans multiple domains ✓ Outputs need to be integrated ✓ Quality requires diverse expertise ✓ Risk of blind spots in single perspective
✓ Problem is clearly in one domain ✓ Scope is small and well-defined ✓ Time constraints are tight ✓ Complexity adds little value
User: "I need a web app that looks professional and unique."
Orchestrator Analysis:
Orchestrator Response: "I'll coordinate multiple specialists to create a complete solution:
Would you also like the Team Builder to design the ideal team composition to implement this app?
I'll ensure all deliverables are cohesive and implementation-ready. Should I proceed?"
Remember: The whole is greater than the sum of its parts—when orchestrated with intention.
© curiositech, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 1 other file in .claude/skills/orchestrator of curiositech/some_claude_skills.
Open the folder on GitHubat commit 6713fc7
Orchestrator next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Orchestrator this skillcuriositech/some_claude_skills | 243 | — | ~3k | Automated safety check: Notes | MIT | |
| Breakdown Testgithub/awesome-copilot | 40k | 1 repos | ~3.7k | Automated safety check: Pass | MIT | |
| Creating Development Planssammcj/agentic-coding | 162 | — | ~1.8k | Automated safety check: Pass | Apache-2.0 | |
| Acceptance Evidence for Deliverieslobehub/lobehub | 83k | — | ~9.7k | Automated safety check: Pass | Apache-2.0 | |
| Senpi Agent QA Harnesscode-yeongyu/senpi | 472 | — | ~2.7k | Automated safety check: Notes | MIT | |
| tmux Real User TestingQwenLM/qwen-code | 28k | — | ~2.3k | Automated safety check: Pass | Apache-2.0 |
github/awesome-copilot
Test Planning and Quality Assurance prompt that generates comprehensive test strategies, task breakdowns, and quality validation plans for GitHub projects.
sammcj/agentic-coding
Creates structured development plans with phased task breakdowns, requirements, and QA checklists.
lobehub/lobehub
Verifies a delivery end to end by driving the real product on a CLI, web, desktop or iOS Simulator surface, capturing evidence and publishing a round with the lh CLI.
code-yeongyu/senpi
Checks changes to the senpi coding agent by driving the real CLI from source in an isolated sandbox, over RPC, terminal UI, mock model and CLI smoke channels.
QwenLM/qwen-code
Drives Qwen Code in a real tmux session the way a user would and saves a readable step-by-step transcript of each screen for maintainers to review.
mylukin/agent-foreman
Enforces a strict next-implement-check-done cycle through the agent-foreman CLI so an agent works one backlog task at a time, with optional TDD gating.
curiositech/some_claude_skills
Detect crisis signals in user content using NLP, mental health sentiment analysis, and safe intervention protocols.
curiositech/some_claude_skills
End-to-end form handling with react-hook-form, Zod schemas, validation patterns, error messaging, field arrays, and multi-step wizards.
curiositech/some_claude_skills
Strategic analyst that maps competitive landscapes, identifies white space opportunities, and provides positioning recommendations.
curiositech/some_claude_skills
Build production CI/CD pipelines with GitHub Actions. An agent skill from curiositech/some_claude_skills.
curiositech/some_claude_skills
Build production computer vision pipelines for object detection, tracking, and video analysis.
curiositech/some_claude_skills
Long-running design anthropologist that builds comprehensive visual databases from 500-1000 real-world examples, extracting color palettes, typography patterns, layout systems, and interaction…
Categories
Master coordinator that delegates to specialist skills, synthesizes outputs, AND creates new skills on-the-fly when needed. Orchestrator is an agent skill from curiositech/some_claude_skills. Master coordinator that delegates to specialist skills, synthesizes outputs, AND creates new skills on-the-fly when needed.
Orchestrator fits situations like: multi-skill coordination; complex task decomposition; workflow design.
Run `npx skills add curiositech/some_claude_skills --skill orchestrator -a claude-code`. Or copy the skill folder (.claude/skills/orchestrator in curiositech/some_claude_skills) into .claude/skills/orchestrator in your project. Claude Code loads it when a task matches its description.
Run `npx skills add curiositech/some_claude_skills --skill orchestrator -a codex`. Or copy the skill folder (.claude/skills/orchestrator in curiositech/some_claude_skills) into .agents/skills/orchestrator in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add curiositech/some_claude_skills --skill orchestrator -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/orchestrator, .gemini/skills/orchestrator, .github/skills/orchestrator and .opencode/skills/orchestrator in your project.
SKILL.md names no scripts, command-line tools or credentials: Orchestrator is instructions for the agent only. Its frontmatter pre-approves these tools: Read, Write, Edit, Bash, Grep, Glob, Task.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.
Orchestrator is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 3k tokens (SKILL.md is roughly 12k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Orchestrator: Breakdown Test (github/awesome-copilot, 40k stars), Creating Development Plans (sammcj/agentic-coding, 162 stars), Acceptance Evidence for Deliveries (lobehub/lobehub, 83k stars) and Senpi Agent QA Harness (code-yeongyu/senpi, 472 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
curiositech (a GitHub organization) maintains it in curiositech/some_claude_skills, which has 243 GitHub stars. The repository holds 109 skills in this directory. The repository was last updated on September 6, 2026.
Source: curiositech/some_claude_skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.