Echo-ScionEcho-Scion/orioncortex/.agents/skills/app-lifecycle/SKILL.md

app-lifecycle

Skill2 starsChanged 7 days agoMITView on GitHub

Use when scaffolding new projects, migrating legacy codebases, building end-to-end features, or sunsetting deprecated components.

1 other project uses a version of this.

Adopted by

Most recently taken up by

Echo-Scion/portable-brainvibingword for word, first seen Oct 15, 2026

Other versions1 project uses a version of this.
Word for word · 1
Echo-Scion/portable-brainvibing★ 2100% same
Edited · 0
None found.
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository21 other files it gives its agents.
- AGENTS.mdAGENTS.md
- ai-engineerSkill
- api-contractSkill
- brain-graphSkill
- code-reviewSkill
- cost-optimizerSkill
- data-logicSkill
- feature-discoverySkill
- frontend-experienceSkill
- integrity-sentinelSkill
- meta-agent-adminSkill
- paletteSkill
- project-architectSkill
- project-operatorSkill
- saas-strategistSkill
- self-evolveSkill
- session-offloadSkill
- strict-tddSkill
- systematic-debuggingSkill
- ui-finishSkill
- worker-delegateSkill

The file

We split this skill into the rules it gives an agent

12 rules. About 0 are common, 3 are distinctive, and 9 are very specific to this project.

≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
9
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Distinctive:
Entry Protocol: Do not blindly start at Phase 0.
line 28
Very specific:
If the project is empty -> Start at Phase 0 with .agents/skills/app-lifecycle/references/project-init.md.
line 29
Very specific:
If context/03_Tech/ARCHITECTURE.md exists but no tests -> Jump to Phase 3.
line 30
Distinctive:
If tests pass but UI is missing -> Jump to Phase 4.
line 31
Very specific:
Action: Create or overwrite .orion/task.md with the checklist of this workflow.
line 34
Very specific:
Rule (Hardware Constraints): Check for resource-heavy default configs.
line 36
Very specific:
Action: Read relevant context/ files generated in Phase 1 before planning architecture.
line 49
Distinctive:
Mandatory Interview: Ask user 1-3 clarifying questions about edge cases, state management, and UI states.
line 50
Very specific:
Output Required: Write Architecture Blueprint to context/03_Tech/ARCHITECTURE.md.
line 51
Very specific:
Output Required: Test execution logs showing [PASS].
line 57
Very specific:
Next Phase: After logic tests pass, transition to Phase 4 (UI Polish) via .agents/skills/ui-finish/SKILL.md.
line 58
Very specific:
Output Required: Verify with python .agents/scripts/orion.py verify --fast.
line 68

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.

Files

SKILL.md

🔄 Full Lifecycle Pipeline (`/full-lifecycle` / `/app-lifecycle`)

This is the standard engineering pipeline. It operates as a State Machine, not a rigid linear script.

🧭 Lifecycle Discipline Routing Matrix

Operational Task	Target Skill / Playbook	Core Mechanism
Session Cold-Start / Bootstrap	.agents/skills/app-lifecycle/references/session-bootstrap.md	Orientation, 4-pillar doctor check, handoff resumption
Feature Discovery & Requirements Intake	.agents/skills/feature-discovery/SKILL.md	Socratic elicitation, Goldfish zero-trust inquiry, 1-question rule
New Project / Scaffolding	.agents/skills/app-lifecycle/references/project-init.md	Requirements intake, context/ scaffold, DESIGN.md generation
Legacy Migration / Brownfield	.agents/skills/app-lifecycle/references/project-migrate.md	Onboard existing project, inventory, architecture extraction
Feature Construction (Surgical)	.agents/skills/app-lifecycle/references/app-builder.md	Shape Spec, UI layout, logic models, Thompson sampling loop
Testing & TDD Verification	.agents/skills/strict-tdd/SKILL.md	RED-GREEN-REFACTOR cycle with mechanical rollback
Code Review & Offensive Audit	.agents/skills/code-review/SKILL.md	Security scan, offensive stress-tests & Lessword review format
Feature Sunsetting & Deprecation	.agents/skills/app-lifecycle/references/feature-sunset.md	4-Phase deprecation, expand-contract & dead code purge

⚡ The Full Lifecycle Pipeline

Entry Protocol: Do not blindly start at Phase 0. Assess the current state of the workspace.
If the project is empty -> Start at Phase 0 with .agents/skills/app-lifecycle/references/project-init.md.
If context/03_Tech/ARCHITECTURE.md exists but no tests -> Jump to Phase 3.
If tests pass but UI is missing -> Jump to Phase 4.

Phase 0: State Initialization (MANDATORY)

Action: Create or overwrite .orion/task.md with the checklist of this workflow.
Rule: At the start of every phase below, mark its checkbox as [/] (in-progress) in .orion/task.md. At the end of every phase, mark it [x] (done).
Rule (Hardware Constraints): Check for resource-heavy default configs. For Flutter/Android: cap Gradle memory in gradle.properties (see canons/ecosystems/flutter/flutter-workflow-commands.md). For Node: check for memory-hungry webpack configs. Recommend lightweight IDE and physical device testing on constrained hardware.

Phase 1: Context & Strategy

Trigger: Run python .agents/scripts/orion.py brain sync "init strategy"
Output Required: Identify the correct Domain File within context/ based on PROJECT_SCAFFOLD.template.md (e.g., context/01_Product/ROADMAP.md). Write strategy into that file.
Next Phase: On completion, transition to Phase 2 (Architecture Blueprint) via .agents/skills/project-architect/SKILL.md.

Phase 1.5: Brain Graph Compilation (If `.orion/` exists)

Trigger: view_file .agents/skills/brain-graph/SKILL.md
Action: Ingest newly created/modified context/ files into .orion/ by creating cross-reference nodes and ensuring orion_refs are injected.

Phase 2: Architecture Blueprint (Shape Spec)

Trigger: Run python .agents/scripts/orion.py brain sync "generate architecture blueprint"
Action: Read relevant context/ files generated in Phase 1 before planning architecture.
Mandatory Interview: Ask user 1-3 clarifying questions about edge cases, state management, and UI states. Do not guess.
Output Required: Write Architecture Blueprint to context/03_Tech/ARCHITECTURE.md.
Next Phase: On blueprint approval, transition to Phase 3 (TDD) via .agents/skills/strict-tdd/SKILL.md.

Phase 3: Test-Driven Development (TDD)

Trigger: The Agent MUST execute view_file on .agents/skills/strict-tdd/SKILL.md or .agents/skills/app-lifecycle/references/app-builder.md.
Action: Implement domain logic following strict RED-GREEN-REFACTOR cycles.
Output Required: Test execution logs showing [PASS].
Next Phase: After logic tests pass, transition to Phase 4 (UI Polish) via .agents/skills/ui-finish/SKILL.md.

Phase 4: Aesthetic & UI Polish (Visual Engineering)

Trigger: The Agent MUST execute view_file on .agents/skills/ui-finish/SKILL.md.
Action: Load DESIGN.md for project aesthetic direction and tokens. Enforce purposeful visual hierarchy, touch target ergonomics, and complete state triad (Loading/Empty/Error). Verify contrast via python .agents/evals/audit_aesthetics.py --contrast "<fg_hex>" "<bg_hex>".
Next Phase: On UI completion, transition to Phase 5 (Security Audit) via .agents/skills/integrity-sentinel/SKILL.md.

Phase 5: Security & Optimization Audit

Trigger: The Agent MUST execute view_file on .agents/skills/code-review/SKILL.md and .agents/skills/integrity-sentinel/SKILL.md.
Action: Perform adversarial review and static AST security verification.
Output Required: Verify with python .agents/scripts/orion.py verify --fast.
Next Phase: On green audit, transition to Phase 6 (Session Offload) via .agents/skills/session-offload/SKILL.md.

Phase 6: Session Offload

Trigger: The Agent MUST execute view_file on .agents/skills/session-offload/SKILL.md.
Action: Clean up worktree, compress memory, and generate session handoff state.

📚 Mandatory Knowledge Routing (JIT References)

If your current task intersects with these domains, you MUST execute view_file on the target BEFORE writing code:

If User Prompt/Task Relates To...	Immediately Load (view_file)
Session Cold-Start / Bootstrap	.agents/skills/app-lifecycle/references/session-bootstrap.md
New Project / Scaffolding	.agents/skills/app-lifecycle/references/project-init.md
Legacy Migration / Brownfield	.agents/skills/app-lifecycle/references/project-migrate.md
Feature Construction	.agents/skills/app-lifecycle/references/app-builder.md
Feature Sunsetting	.agents/skills/app-lifecycle/references/feature-sunset.md
Platform Capabilities / Slash Tools	.agents/skills/app-lifecycle/references/platform-superpowers.md

Download now (ZIP)

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

What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free