downshift-squad
Skill4 starsChanged 9 days agoApache-2.0View on GitHub
Invoke Downshift agent squads for coordinated multi-agent work. Use when the user says "squad", "time", "convoca", or wants to delegate to specialized agents. For "downshift full power", "força total" or "downshift shift <squad>", use the downshift-orchestrator skill.
In this repository12 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- llms.txtllms.txt
- downshift-layeringSkill
- architecture-coverageSkill
- downshift-auditSkill
- downshift-effortSkill
- downshift-orchestratorSkill
- downshift-setupSkill
- downshift-tuneSkill
- harness-engineerSkill
- ponytailSkill
The file
We split this skill into the rules it gives an agent
7 rules. About 0 are common, 0 are distinctive, and 7 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
7
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 60
Load config: Read agents/config.toml for [routing], [domains], [escalation], and [tiers]
- Very specific: line 62
Check escalation first: If the task matches any escalation.always_escalate pattern, route through the escalation target before …
- Very specific: line 72
Pick tier: Use [tiers] to assign small/mid/frontier per agent
- Very specific: line 73
Spawn workers: Use downshift delegate with agent prompts
- Very specific: line 131
When no keyword matches, [defaults] applies: unknown_task = "researcher" (understand first), and multi-file work routes to complex_task = …
- Very specific: line 155
When a task matches an always_escalate pattern, the orchestrator routes it to the escalation target FIRST, then lets the implementer …
- Very specific: line 195
Call downshift providers before spawning to see available models.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Squad — Downshift Agent Orchestration
Invoke specialized agent squads for coordinated work. The squad system routes tasks to the right agents based on domain expertise.
Syntax
squad <target> "<task>"Or in natural language:
- "squad core fix the race condition"
- "chama o time de qualidade pra revisar"
- "convoca o coder pra implementar"
Targets
| Target | Agents | Best for |
downshift | all 14 agents | Full project: feature + tests + docs + review |
core | coder, coder-back, coder-front, refactor, researcher | Implementation, refactoring, analysis |
quality | tester, debugger, reviewer | Testing, debugging, review |
security | security | Security audit, threat modeling |
performance | performance | Profiling, optimization |
docs | documenter | README, API docs, guides |
leadership | architect, platform, ai | Design, infra, AI decisions |
<agent> | one specific | Focused single-agent task |
Agent Catalog (14 agents)
| Agent | Domain | Mode | Tier | Specialty |
| coder | core | write | mid | Full-Stack Integrator, vertical slices, E2E |
| coder-back | core | write | mid | Backend specialist: Go/Node/PHP/APIs, DB, concurrency |
| coder-front | core | write | mid | Frontend & visual swarm: React 19, Next, Tailwind 4, Canvas 2D |
| refactor | core | write | mid | Code restructuring, cleanup |
| researcher | core | read | small | Code analysis, dependency tracing |
| tester | quality | read | small | Run tests, coverage analysis |
| debugger | quality | read | mid | Test failures, flaky tests |
| reviewer | quality | read | mid | Code review, quality gates |
| security | security | read | frontier | Security audit, threat modeling |
| performance | performance | read | mid | Profiling, bottlenecks |
| documenter | support | write | small | Documentation |
| architect | leadership | read | frontier | System design, cross-layer |
| platform | leadership | read | frontier | Infra, DevOps, CI/CD |
| ai | leadership | read | frontier | AI/LLM, model routing, FinOps |
How it works
Routing is driven by agents/config.toml — the single source of truth for which
agent handles each task. The orchestrator reads this file so harnesses without
native memory (Claude Code, Cursor, Codex) route consistently.
- Load config: Read
agents/config.tomlfor[routing],[domains],[escalation], and[tiers] - Check escalation first: If the task matches any
escalation.always_escalatepattern, route through the escalation target before implementation (see below) - Parse target: Match task keywords against
[routing](first match wins); if none match, fall back to[defaults](unknown_task,complex_task) - Resolve domain: For
squad <domain>commands, expand the domain to its agents via[domains] - Select topology:
- Single agent → direct delegation
- Single domain → star (coordinator + workers)
- Multi-domain → mesh (parallel with shared state)
- Pick tier: Use
[tiers]to assign small/mid/frontier per agent - Spawn workers: Use
downshift delegatewith agent prompts - Coordinate: Poll results, integrate outputs
Examples
Single agent
squad coder "Fix the nil pointer in pool.go line 42"→ Spawns one coder agent with the task
Domain squad
squad quality "Full review of PR #758"→ Spawns tester + debugger + reviewer in star topology → Each runs their specialty, coordinator integrates
Leadership decision
squad architect "Design the new payment module"→ Spawns architect with frontier tier for design work
Full squad
squad downshift "Add rate limiting to /api/users endpoint"→ architect designs the approach → coder implements → tester/debugger verify → reviewer checks quality → security audits → documenter updates docs
Routing rules (from config.toml)
Keyword → agent mapping lives in the [routing] table of agents/config.toml.
The FIRST matching keyword wins, so more specific patterns are listed first.
Below is a summary; agents/config.toml is authoritative.
| Task keyword (examples) | Routed to |
backend, api, endpoint, database, sqlite, mysql, concurrency, idempotency | coder-back |
frontend, ui, canvas, visual swarm, swarm visual, css, tailwind, pwa, web worker | coder-front |
vertical slice, end to end, full stack, integration, implement, add feature, bug fix | coder |
refactor, cleanup, restructure | refactor |
analyze, investigate, find where, trace | researcher |
test, coverage, run tests | tester |
debug, failing test, flaky | debugger |
review, code review, PR review | reviewer |
document, readme, api docs | documenter |
security, audit, vulnerability, authentication, authorization, access control | security |
performance, slow, optimize, profile, profiling | performance |
architecture, design, system design, cross-module | architect |
deploy, ci/cd, infrastructure, devops | platform |
llm, model routing, embedding, machine learning, ai agent, ai model | ai |
When no keyword matches, [defaults] applies: unknown_task = "researcher"
(understand first), and multi-file work routes to complex_task = "architect"
for decomposition.
Domains (from config.toml)
squad <domain> expands via the [domains] table. Keep the skill and config in
sync — these are the groups defined in agents/config.toml:
squad core "..." → coder, coder-back, coder-front, refactor, researcher
squad quality "..." → tester, debugger, reviewer
squad security "..." → security
squad performance "..." → performance
squad support "..." → documenter
squad leadership "..." → architect, platform, aiEscalation protocol (sensitive tasks)
Some tasks ALWAYS go through leadership before any implementation. The
[escalation] section of agents/config.toml lists the always_escalate
patterns and the routing targets.
When a task matches an always_escalate pattern, the orchestrator routes it to
the escalation target FIRST, then lets the implementer proceed only after the
review clears.
always_escalate patterns include:
authentication, authorization, oauth, payment, billing,
database schema, migration, breaking change, api contract,
security, encryption, secrets, credentials.
Escalation targets ([escalation.targets]):
| Pattern type | Target | Covers |
security_patterns | security | auth, encryption, secrets |
data_patterns | architect | database, migration, api contract |
default | architect | everything else sensitive |
Escalation examples
squad downshift "Add OAuth login to the API"→ matches auth (always_escalate) → security reviews the design first
→ only then coder implements, with security verifying the result
squad coder "Add a migration to rename the users table"→ matches migration (always_escalate) → architect reviews schema impact first
→ then coder applies the migration
Tier selection (from config.toml)
The [tiers] table recommends a model tier per agent:
small→ researcher, tester, documenter (mechanical work)mid→ coder, coder-back, coder-front, refactor, reviewer, debugger, performance (most work)frontier→ architect, security, platform, ai (complex decisions)
An explicit [tier=...] in the task overrides the config default.
Call downshift providers before spawning to see available models.
Downshift by Tiago Vilas Boas · https://github.com/tiagovilasboas/downshift-ai
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

