ecosystem-orchestration
Skill7 starsChanged 43 days agoMITView on GitHub
Hub for all fth-skills ecosystems and the agent-orchestration domain: decomposing complex work, executing repository changes, recovering from failures, carrying state across sessions, and connecting external agents. Use when a task spans several domains, when the user asks how the skills work together or which ecosystem to use, or for multi-phase agent execution.
In this repository83 other files it gives its agents.
- AGENTS.mdAGENTS.md
- accessibility-enforcerSkill
- access-policy-designerSkill
- adaptive-guardSkill
- agent-reviewerSkill
- anti-ai-slop-designSkill
- api-mock-designerSkill
- api-observability-plannerSkill
- app-store-reviewerSkill
- ask-first-act-laterSkill
- assumption-checkerSkill
- auth-flow-designerSkill
- b2b-founder-roadmapSkill
- brand-name-labSkill
- breaking-change-detectorSkill
- changelog-generatorSkill
- checkpoint-guardianSkill
- claude-style-codingSkill
- claw-integration-designSkill
- context-compressorSkill
- contract-first-designerSkill
- coolify-orchestratorSkill
- crash-analystSkill
- data-lineage-tracerSkill
- data-maskerSkill
- deep-link-architectSkill
- design-intelligenceSkill
- design-md-enforcerSkill
- ecosystem-apiSkill
- ecosystem-databaseSkill
- ecosystem-mobileSkill
- ecosystem-productSkill
- ecosystem-reasoningSkill
- ecosystem-securitySkill
- ecosystem-webSkill
- error-recoverySkill
- fth-design-crafterSkill
- geo-auditorSkill
- geo-optimizerSkill
- index-advisorSkill
- jev-orchestratorSkill
- mastermind-loggerSkill
- memory-ledgerSkill
- migration-strategistSkill
- mobile-perf-auditorSkill
- mobile-security-auditorSkill
- multi-brain-debateSkill
- multi-brain-expertsSkill
- multi-brain-scoreSkill
- multi-brainSkill
- offline-sync-designerSkill
- onboarding-designerSkill
- output-criticSkill
- parallel-plannerSkill
- pgbouncer-architectSkill
- plan-hardenerSkill
- plan-implement-verify-recoverSkill
- proje-analizcisiSkill
- project-analyzerSkill
- project-focus-firstSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 2 are distinctive, and 4 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 60
Follow this protocol whenever this ecosystem is invoked.
- Very specific: line 66
Execute: Run steps in order. Steps that share a parallel group are independent and may run concurrently (@parallel-planner).
- Very specific: line 67
Gates: Before any destructive, irreversible, or production-impacting action, stop at @checkpoint-guardian, or ask for explicit confirmation …
- Very specific: line 68
Failures: When a step misses its *Done when*, hand off to @error-recovery.
- Very specific: line 69
State: Keep a run log (workflow id, step, status, artifact).
- Distinctive: line 72
Skip this protocol: when the user names one specific skill (invoke it directly) or asks a quick factual question that needs no workflow.
≈ “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
🤖 Orchestration Hub
This skill is the entry point of its ecosystem. It chooses a workflow, checks which member skills are installed, runs them in order with explicit handoffs, and degrades gracefully when a member is missing. The workflow map lives in references/workflows.json; the handoff format lives in references/handoff-contract.md.
Ecosystem Index
This skill is the hub of all fth-skills ecosystems. Route cross-domain requests from here.
<!-- BEGIN GENERATED: ecosystem-index (generated from the ecosystem workflow map by build_ecosystems.py — do not edit by hand) -->| Ecosystem | Domain | Use for | Workflows |
@ecosystem-orchestration | Agent Orchestration | Plan, execute, recover, remember, and review multi-step agent work; connect external agents safely. | orch-complex-task, orch-code-change, orch-resilience, orch-agent-connectivity, orch-knowledge |
@ecosystem-reasoning | Reasoning, Planning Gates & Prompting | Clarify intent, stress-test plans, compare perspectives, and craft prompts, without stacking redundant question gates. | reason-clarify, reason-decision, reason-plan-review, reason-prompting |
@ecosystem-api | API Domain | Design, secure, scale, and evolve REST, GraphQL, gRPC, and event-driven APIs with a contract-first workflow. | api-design, api-security-scale, api-evolution, api-production-readiness |
@ecosystem-database | Database Domain | Model, secure, optimize, migrate, and operate SQL databases (PostgreSQL, MySQL, SQLite) with data integrity first. | db-new-schema, db-performance, db-evolution, db-compliance, db-scaling |
@ecosystem-mobile | Mobile App Domain | Architect, audit, release, and monitor iOS, Android, React Native, and Flutter apps. | mobile-pre-release-audit, mobile-release, mobile-feature-architecture, mobile-post-launch |
@ecosystem-web | Web, Design & Delivery | Design product-grade web interfaces, keep design systems consistent, make sites visible to search and AI answer engines, and deploy them. | web-foundations, web-build-page, web-visibility, web-review, web-de-slop, web-deploy |
@ecosystem-product | Product & Growth | Take a product from focus to market: B2B go-to-market, naming, creative content, and discoverability. | product-launch, product-naming, product-content |
@ecosystem-security | Security | Audit skills before deployment, guard agent runtimes against injection and exfiltration, and learn from incidents. | sec-skill-audit, sec-runtime-guard, sec-full-lifecycle |
Pick the ecosystem whose domain matches the request and follow its workflow map. If the ecosystem skill is not installed, use the workflow ids above as the plan skeleton and run each member skill directly, or install it with npx skills add fatih-developer/fth-skills --skill <ecosystem> after the user agrees. Never invent skills that are not listed.
<!-- END GENERATED: ecosystem-index -->Catalog
<!-- BEGIN GENERATED: ecosystem-catalog (generated from the ecosystem workflow map by build_ecosystems.py — do not edit by hand) -->Domain: Agent Orchestration — Plan, execute, recover, remember, and review multi-step agent work; connect external agents safely.
Philosophy: Agents fail in unexpected ways. Decompose before acting, gate irreversible steps, recover from errors deliberately, keep durable state, and review the outcome before calling work done.
| Skill | Role | Handoff artifact |
@task-decomposer | Breaks large goals into subtasks with a dependency map. | inline handoff block |
@parallel-planner | Finds steps that can run concurrently and detects conflicts. | inline handoff block |
@tool-selector | Chooses the minimal tool set and call order. | inline handoff block |
@plan-implement-verify-recover | Executes repository changes with risk-adaptive planning and verification. | inline handoff block |
@checkpoint-guardian | Gates destructive or irreversible actions behind confirmation. | inline handoff block |
@error-recovery | Classifies failures and applies bounded recovery strategies. | inline handoff block |
@context-compressor | Compresses long context while keeping decisions and errors. | inline handoff block |
@memory-ledger | Keeps an in-task ledger of decisions, status, and failed approaches. | inline handoff block |
@session-transfer | Writes and resumes cross-session, cross-agent handoffs. | inline handoff block |
@mastermind-logger | Maintains a cross-referenced project knowledge wiki. | inline handoff block |
@output-critic | Scores outputs against type-specific criteria before handoff. | inline handoff block |
@agent-reviewer | Runs a post-task retrospective across six dimensions. | inline handoff block |
@jev-orchestrator | Routes bounded semantic judgments to the TypeSafe Jev runtime. | inline handoff block |
@claw-integration-design | Designs secure APIs and tool manifests for external agents. | inline handoff block |
@project-analyzer | Produces evidence-based codebase analysis reports. | docs/analyze/01-project-overview.md |
@proje-analizcisi | Deprecated alias — use @project-analyzer. | inline handoff block |
@skill-comparator | Compares skills and recommends adopt, adapt, or build. | docs/skill-report/skill-analysis-report.md |
<!-- END GENERATED: ecosystem-catalog -->Router Protocol
<!-- BEGIN GENERATED: ecosystem-router (generated from the ecosystem workflow map by build_ecosystems.py — do not edit by hand) -->Follow this protocol whenever this ecosystem is invoked.
- Match. Compare the request with each workflow's When phrases. Pick one workflow, or route straight to a single member skill when the request is narrow. If two workflows fit equally, ask one question to choose. If the request belongs to another domain, use the ecosystem index in
@ecosystem-orchestration. - Preflight. Find out which step skills are installed: check the skills your host lists, or run
python <skill-dir>/scripts/install_all.py --status --workflow <id>(<skill-dir>is the folder containing thisSKILL.md). Show a short plan: step, skill, installed or missing, condition, expected artifact. - Missing skills never block. Offer once: (a) install them —
install_all.py --workflow <id>prints the commands and only runs them with--executeafter the user agrees; or (b) continue in fallback mode — perform the step yourself using its Does and Done when columns and label that outputfallback. - Conditions. Skip optional steps whose condition does not hold, and say which steps you skipped and why.
- Execute. Run steps in order. Steps that share a parallel group are independent and may run concurrently (
@parallel-planner). Pass artifacts as described inreferences/handoff-contract.md. Check each step's Done when before moving on. - Gates. Before any destructive, irreversible, or production-impacting action, stop at
@checkpoint-guardian, or ask for explicit confirmation when it is not installed. - Failures. When a step misses its Done when, hand off to
@error-recovery. Without it, retry once with a changed approach, then report the blocker with evidence instead of guessing. - State. Keep a run log (workflow id, step, status, artifact). Record it with
@memory-ledgerwhen installed, and write a@session-transferhandoff if the run will continue in another session. - Finish. Summarize artifacts, skipped steps, open risks, and the most relevant next workflow.
Skip this protocol when the user names one specific skill (invoke it directly) or asks a quick factual question that needs no workflow.
<!-- END GENERATED: ecosystem-router -->Workflows
<!-- BEGIN GENERATED: ecosystem-workflows (generated from the ecosystem workflow map by build_ecosystems.py — do not edit by hand) -->1. Complex Task Execution Flow (orch-complex-task)
When: “build this end to end”; “multi-phase task”; “plan and execute the project”
| # | Skill | Does | Done when | Condition | Parallel group |
| 1 | @task-decomposer | Break the goal into subtasks, consulting the matching domain ecosystem. | Every subtask has an owner skill, dependency, and success criterion. | — | — |
| 2 | @parallel-planner (optional) | Group independent subtasks and flag write conflicts. | Execution plan with parallel groups and conflict warnings. | Three or more independent subtasks | — |
| 3 | @tool-selector (optional) | Choose the minimal tool sequence per subtask. | No redundant or blocked tool calls in the plan. | — | — |
| 4 | @memory-ledger | Record decisions, status, and failed approaches as work proceeds. | Ledger reflects the latest completed step. | — | — |
| 5 | @output-critic (optional) | Score each deliverable before it is handed to the next step. | Deliverable meets the acceptance threshold. | — | — |
| 6 | @agent-reviewer (optional) | Run a retrospective once the task is complete. | Action items for the next task are recorded. | — | — |
2. Repository Change Flow (orch-code-change)
When: “fix this bug”; “implement the feature”; “refactor this module”
| # | Skill | Does | Done when | Condition | Parallel group |
| 1 | @project-analyzer (optional) | Map the codebase when it is unfamiliar. | Architecture and risk hotspots are known. | Unfamiliar or large codebase | — |
| 2 | @plan-implement-verify-recover | Plan, implement, verify, and recover within a bounded loop. | Change is verified by tests or a reproducible check. | — | — |
| 3 | @checkpoint-guardian (optional) | Confirm destructive steps (force push, data deletion, deploy). | Every HIGH RISK action was approved. | Change includes an irreversible action | — |
3. Failure & Context Pressure Flow (orch-resilience)
When: “the step failed”; “context is getting full”; “continue in a new session”
| # | Skill | Does | Done when | Condition | Parallel group |
| 1 | @error-recovery (optional) | Classify the failure and apply the matching recovery strategy. | Step succeeded or was escalated with evidence. | A step failed | — |
| 2 | @context-compressor (optional) | Compress history before it crowds out the task. | Critical decisions and errors survive compression. | Context is near its limit | — |
| 3 | @session-transfer (optional) | Write an immutable handoff so a new session can resume. | Handoff validates and is indexed. | Work must continue in another session or agent | — |
4. Agent Connectivity Flow (orch-agent-connectivity)
When: “let an external bot use our app”; “design a tool manifest”; “give an agent API access”
| # | Skill | Does | Done when | Condition | Parallel group |
| 1 | @claw-integration-design | Design agent-facing endpoints, scopes, and the tools manifest. | Every tool has a scope, auth method, and rate limit. | — | — |
| 2 | @auth-flow-designer (optional) | Harden token lifecycle and scopes for bot clients. | Bot tokens are scoped and revocable. | — | — |
| 3 | @security-auditor | Audit the integration surface before exposure. | No STRICT REJECT findings. | — | — |
5. Knowledge Capture Flow (orch-knowledge)
When: “save what we learned”; “update the project wiki”; “document this session”
| # | Skill | Does | Done when | Condition | Parallel group |
| 1 | @memory-ledger | Close the task ledger with final status. | Ledger is closed. | — | — |
| 2 | @mastermind-logger | Merge durable learnings into the project wiki. | Index and log are updated. | — | — |
Direct handoffs
@jev-orchestrator→@checkpoint-guardian: A Jev decision would trigger an irreversible side effect.@jev-orchestrator→@error-recovery: Jev invocation fails and no project fallback exists.@jev-orchestrator→@output-critic: An open-ended critique is needed beyond a bounded quality gate.@skill-comparator→@security-auditor: A candidate skill will be adopted.@memory-ledger→@session-transfer: The task will continue in a new session.@session-transfer→@memory-ledger: A resumed session needs an in-task ledger again.
<!-- END GENERATED: ecosystem-workflows -->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.