faglo/remotion_service
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docs initial

Browse Source
This commit is contained in:
Daniil
2026-04-06 01:44:58 +03:00
parent 2a344ad588
commit 694b8bc77c
84 changed files with 6922 additions and 298 deletions
Download Patch File Download Diff File Expand all files Collapse all files
CLAUDE.md
+33 -31
View File
@@ -118,12 +118,14 @@ All user-facing UI text **must be in Russian**. The only exception is the brand
## Agent Team
This project has a team of 20 agents organized in a 4-tier hierarchy: 1 orchestrator, 3 leads, 14 specialists, and 2 staff.
This project has a team of 19 specialist agents: 3 leads, 14 specialists, and 2 staff.
Agent files: `.claude/agents/`. Shared protocol: `.claude/agents-shared/team-protocol.md`.
**You (Claude) ARE the tech lead / orchestrator.** You select and dispatch agents directly.
### Team Hierarchy
Orchestrator (Tech Lead)
You (Tech Lead)
├── Architecture Lead → Backend Architect, Frontend Architect, DB Architect, Remotion Engineer, Sr. Backend Engineer, Sr. Frontend Engineer
├── Quality Lead → Frontend QA, Backend QA, Security Auditor, Design Auditor, Performance Engineer
├── Product Lead → UI/UX Designer, Technical Writer, ML/AI Engineer
@@ -136,47 +138,47 @@ Agent files: `.claude/agents/`. Shared protocol: `.claude/agents-shared/team-pro
**Engineers** (Senior Backend Engineer, Senior Frontend Engineer) implement production code from architect specs. They receive designs and produce working code.
This separation ensures architectural decisions are made before implementation begins. Architects and engineers may both be dispatched within the same task — the Architecture Lead sequences them.
This separation ensures architectural decisions are made before implementation begins.
### Developer Team Consultation
For ANY non-trivial task, you MUST consult with the developer team:
For ANY non-trivial task, dispatch specialist agents directly. Do NOT solve domain-specific
tasks yourself. Use leads for multi-specialist coordination, or dispatch specialists directly
for focused tasks (e.g., `devops-engineer` for Docker, `security-auditor` for security).
**CRITICAL: Never edit files yourself for domain-specific work — dispatch the specialist first.** Reading files to understand the problem is fine; editing them is not.
### Dispatch Loop
1. **Announce**: "Consulting with the developer team to [task summary]"
2. Dispatch the `orchestrator` agent with your analysis — it selects the right leads and dispatches them
3. The orchestrator handles everything: dispatches leads, leads dispatch specialists, results bubble up with audit trails
4. **Credit specialists** in your final response — state which agents contributed
2. **Identify affected files** using Glob/Read (read-only — do NOT edit yet)
3. **Dispatch agents in parallel** — pass file paths and task description (NOT file contents)
4. **Collect results** from all agents
5. Present results to user, **crediting which specialists contributed**
### When to Use the Orchestrator
For ANY non-trivial task (feature, bug fix, audit, optimization, research, infrastructure,
review, documentation), you MUST:
1. Think about the task yourself first — understand scope, affected areas, risks
2. Dispatch the `orchestrator` agent with your analysis as context
3. Receive the orchestrator's synthesized results (includes full audit trail)
4. Present results to the user
Skip the Orchestrator ONLY for trivial tasks: rename a variable, fix a typo, answer a
quick factual question.
### Dispatch Loop (Simplified)
1. Dispatch orchestrator with task context
2. Orchestrator handles everything internally (dispatches leads, collects results, resolves conflicts)
3. Receive orchestrator's final synthesis (includes recursive audit trail of all agent calls)
4. Present results to user with team credit summary
You no longer need to: process handoffs, track chain history, enforce depth limits,
re-invoke agents in continuation mode, dispatch individual specialists, or manage phasing.
The orchestrator → lead → specialist hierarchy handles all of this.
Skip agents ONLY for: rename a variable, fix a typo, fix a single-line syntax
error, answer a quick factual question, run a command the user explicitly asked for.
### Conflict Handling
If the orchestrator reports unresolved conflicts between leads:
If dispatched agents report conflicting recommendations:
- Present both perspectives to the user with your analysis
- Let the user decide on trade-offs that affect their product
## Available ECC Skills
The `everything-claude-code` plugin provides skills invocable via `/skill-name`. Key ones for this project:
| Skill | When to use |
|-------|-------------|
| `/plan` | Before implementing multi-step features — creates step-by-step plan |
| `/tdd` | When writing new features or fixing bugs — test-first workflow |
| `/docs` | Look up current library docs via Context7 (Next.js, FastAPI, Remotion, etc.) |
| `/security-review` | After writing auth, user input handling, API endpoints, or file uploads |
| `/search-first` | Before writing custom code — check for existing libraries/patterns |
Use `superpowers:verification-before-completion` to enforce running verification commands before claiming work is done.
## Compact Instructions
When compacting, always preserve: