Source profileQuality 86/100Review permissions

notque/vexjoy-agent/skills/process/feature-lifecycle/SKILL.md

feature-lifecycle

Feature lifecycle: design, plan, implement, validate, release. Phase-gated workflow.

Source repository stars
413
Declared platforms
0
Static risk flags
2
Last source update
2026-07-25
Source checked
2026-08-04

Decision brief

What it does—and where it fits

Phase-gated feature workflow: DESIGN PLAN IMPLEMENT VALIDATE RELEASE. Each phase must pass its gate before the next begins.

Best for

    Not for

    • Tasks that require unconfirmed production actions or broad system permissions.
    • Environments where the pinned source and install steps cannot be inspected.

    Compatibility matrix

    Platform support, with evidence labels

    PlatformStatusEvidenceWhat to check
    CodexNot declaredNo explicit evidencePortability before use
    Claude CodeNot declaredNo explicit evidencePortability before use
    CursorNot declaredNo explicit evidencePortability before use
    Gemini CLINot declaredNo explicit evidencePortability before use
    Open the compatibility checker

    Installation

    Inspect first. Install second.

    The source command is displayed only when detected. A safe inspection prompt is always available so your agent can explain every action before execution.

    Source-detected install commandSource
    npx skills add https://github.com/notque/vexjoy-agent --skill "skills/process/feature-lifecycle"
    Safe inspection promptEditorial

    Inspect the Agent Skill "feature-lifecycle" from https://github.com/notque/vexjoy-agent/blob/b19dacd072f5befd29b525b25dbecc7a1cd86d92/skills/process/feature-lifecycle/SKILL.md at commit b19dacd072f5befd29b525b25dbecc7a1cd86d92. List every install step, command, network request, credential, file read/write, external action, and rollback step. Explain whether it fits my task. Do not install or execute anything until I approve.

    Workflow

    What the source asks the agent to do

    1. 01

      Phase Routing

      Determine which phase to execute based on feature state:

      If .feature/ exists, check current phase:If no feature state exists, determine entry point from user intent:"design", "think through", "explore approaches" - DESIGN
    2. 02

      Phase Ordering

      Each phase produces an artifact consumed by the next. Skipping phases is not supported because downstream phases depend on artifacts from earlier phases.

      Each phase produces an artifact consumed by the next. Skipping phases is not supported because downstream phases depend on artifacts from earlier phases.
    3. 03

      State Conventions

      Read references/shared.md for directory structure, state management commands, context loading rules, and naming conventions. All state operations go through python3 /.claude/scripts/feature-state.py -- never manipulate state files directly.

      Read references/shared.md for directory structure, state management commands, context loading rules, and naming conventions. All state operations go through python3 /.claude/scripts/feature-state.py -- never manipulate…
    4. 04

      Reference Loading Table

      Review the “Reference Loading Table” section in the pinned source before continuing.

      Review and apply the “Reference Loading Table” source section.
    5. 05

      Error Handling

      Review the “Error Handling” section in the pinned source before continuing.

      Review and apply the “Error Handling” source section.

    Permission review

    Static risk signals and limitations

    Runs scripts

    medium · line 12

    The documentation asks the agent to run terminal commands or scripts.

    python3 ~/.claude/scripts/feature-state.py status

    Reads files

    low · line 36

    The documentation asks the agent to read local files, directories, or repositories.

    Read `references/shared.md` for directory structure, state management commands, context loading rules, and naming conventions. All state operations go through `python3 ~/.claude/scripts/feature-state.py` -- never manipulate state files dire

    Evidence record

    Why each signal appears

    EvidenceSourceComputedTestedEditorial
    SignalValueEvidence typeMeaning
    Quality score86/100ComputedDocumentation, specificity, maintenance, and trust rules
    Repository stars413SourceRepository attention, not individual Skill quality
    Compatibility0 platformsSourceDeclared in the catalog source record
    Usage guideautomated source guideEditorialGenerated or reviewed according to the visible evidence level

    Pinned source

    Provenance and original SKILL.md

    Repository
    notque/vexjoy-agent
    Skill path
    skills/process/feature-lifecycle/SKILL.md
    Commit
    b19dacd072f5befd29b525b25dbecc7a1cd86d92
    License
    MIT
    Collected
    2026-08-04
    Default branch
    main
    View the original SKILL.md

    Feature Lifecycle Skill

    Phase-gated feature workflow: DESIGN > PLAN > IMPLEMENT > VALIDATE > RELEASE. Each phase must pass its gate before the next begins.

    Phase Routing

    Determine which phase to execute based on feature state:

    1. If .feature/ exists, check current phase:

      python3 ~/.claude/scripts/feature-state.py status
      

      Route to the phase indicated by the state machine.

    2. If no feature state exists, determine entry point from user intent:

      • "design", "think through", "explore approaches" -> DESIGN
      • "plan", "break down", "create tasks" -> PLAN (requires completed design)
      • "implement", "execute plan", "start building" -> IMPLEMENT (requires completed plan)
      • "validate", "quality gates", "check feature" -> VALIDATE (requires completed implementation)
      • "release", "merge", "ship it" -> RELEASE (requires passed validation)
      • "end to end", "full lifecycle", "from scratch" -> DESIGN (start from beginning)
    3. Load the phase reference for the current phase:

      • DESIGN: Read references/design.md
      • PLAN: Read references/plan.md
      • IMPLEMENT: Read references/implement.md
      • VALIDATE: Read references/validate.mdrun quality gate commands, do not reason about whether they would pass. Paste exit codes and output.
      • RELEASE: Read references/release.md
      • END-TO-END: Read references/pipeline.md
    4. Follow the loaded reference exactly. Each reference contains the full phase instructions, gates, and checkpoints.

    State Conventions

    Read references/shared.md for directory structure, state management commands, context loading rules, and naming conventions. All state operations go through python3 ~/.claude/scripts/feature-state.py -- never manipulate state files directly.

    Phase Ordering

    DESIGN -> PLAN -> IMPLEMENT -> VALIDATE -> RELEASE
      |         |         |           |          |
      v         v         v           v          v
    design.md plan.md  impl.md   report.md  PR merged
    

    Each phase produces an artifact consumed by the next. Skipping phases is not supported because downstream phases depend on artifacts from earlier phases.

    Reference Loading Table

    SignalLoad These FilesWhy
    Phase 1 DESIGN: idea to design documentdesign.mdLoads detailed guidance from design.md.
    errors, error handlingerror-handling.mdLoads detailed guidance from error-handling.md.
    Phase 3 IMPLEMENT: dispatching task waves to domain agentsimplement.mdLoads detailed guidance from implement.md.
    running the full design-to-release pipelinepipeline.mdLoads detailed guidance from pipeline.md.
    Phase 2 PLAN: decomposing design into wave-ordered tasksplan.mdLoads detailed guidance from plan.md.
    Phase 5 RELEASE: PR merge, tagging, worktree cleanuprelease.mdLoads detailed guidance from release.md.
    feature state directory layout, naming, write protectionshared.mdLoads detailed guidance from shared.md.
    Phase 4 VALIDATE: running quality gatesvalidate.mdLoads detailed guidance from validate.md.

    Error Handling

    ErrorCauseSolution
    Phase mismatchUser requests phase N but state is at phase MReport current state, suggest correct next phase
    Missing artifactPrevious phase did not produce expected outputRoute back to previous phase
    Gate failurePhase requirements not metReport what failed, suggest fixes

    References

    Task SignalLoad
    Phase routing (design/plan/implement/validate/release)Phase reference (design.md, plan.md, implement.md, validate.md, release.md)
    End-to-end or full pipelinereferences/pipeline.md
    State commands, directory structure, namingreferences/shared.md
    Error, failure, blocked, gate fail, retry, deviationreferences/error-handling.md
    • references/design.md -- Design phase: explore requirements, discuss trade-offs
    • references/plan.md -- Plan phase: break design into wave-ordered tasks
    • references/implement.md -- Implement phase: dispatch tasks to domain agents
    • references/validate.md -- Validate phase: run quality gates
    • references/release.md -- Release phase: merge, tag, cleanup
    • references/pipeline.md -- End-to-end orchestration across all phases
    • references/shared.md -- State conventions shared across all phases
    • references/error-handling.md -- Recovery patterns for phase errors, gate failures, agent dispatch failures

    Alternatives

    Compare before choosing

    Computed 9618,447

    teng-lin/notebooklm-py

    notebooklm

    Complete API for Google NotebookLM - full programmatic access including features not in the web UI. Create notebooks, add sources, generate all artifact types, download in multiple formats. Activates on explicit /notebooklm or intent like "create a podcast about X"

    Computed 9614,225

    wanshuiyin/Auto-claude-code-research-in-sleep

    grant-proposal

    Use it for deployment and design tasks; the detail page covers purpose, installation, and practical steps.

    Computed 9610,895

    huggingface/skills

    huggingface-lora-space-builder

    Build and publish a Gradio demo on Hugging Face Spaces for a user-provided LoRA. Use when someone asks to create, generate, ship, or publish a Space, demo, Gradio app, or playground for a LoRA — including LoRAs for Qwen-Image, Qwen-Image-Edit, LTX-Video, Wan, FLUX, SDXL, or other diffusion base models. Also triggers when someone describes a LoRA they trained or hosts on the Hub and wants to share it. Covers picking the right base pipeline and `diffusers` inference recipe, designing a UI tailored

    Computed 961,066

    TencentCloudBase/CloudBase-AI-Toolkit

    cloudbase-agent-python

    Build production-ready AI agent backends using the CloudBase Agent Python SDK — create agents with LangGraph/CrewAI/LlamaIndex, serve them via FastAPI with AG-UI protocol streaming + OpenAI-compatible endpoints, add tools (bash, filesystem, MCP, code execution), memory (in-memory, TDAI, MySQL, MongoDB), observability (OpenTelemetry/Langfuse), and middleware (auth, logging). Use this skill when the user wants to create an AI agent server, build a chatbot backend, set up human-in-the-loop workflow