skills.rest
zMynxx
zMynxxCOMMUNITY
Explore all skills by this author →
GitHub

_shared

Provides shared SDD reference documents for persistence, conventions, and phase protocols.

Updated Jun 5, 2026
Search Tags:#reference#orchestration#persistence#conventions#sdd#openspec#engram
One-click install
npx skills add https://github.com/zMynxx/bifrost-with-opencode --skill shared-zmynxx
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: _shared
Source: https://github.com/zMynxx/bifrost-with-opencode/tree/main/.opencode/skills/_shared
Command: npx skills add https://github.com/zMynxx/bifrost-with-opencode --skill shared-zmynxx

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? SDD phase skills each need identical boilerplate for artifact persistence, naming conventions, status contracts, and skill resolution; duplicating that content in every skill causes drift and inconsistency. ## Core Features & Use Cases - Persistence Contract: Defines the four artifact store modes (engram, openspec, hybrid, none) with read/write behavior, state recovery, and sub-agent context rules. - Naming Conventions: Standardizes Engram topic keys and OpenSpec directory layouts so artifacts are recoverable by deterministic search. - Status & Phase Protocols: Supplies the shared SDD status schema, return envelope format, and skill-resolution protocol used by orchestrators and sub-agents. - Use Case: When the sdd-propose skill saves a proposal, it follows the shared engram-convention rules so sdd-spec can later retrieve the exact same artifact by topic key. ## Quick Start Read the shared reference files in this package before invoking any SDD phase skill so artifact persistence and recovery follow the common contract.

Frequently Asked Questions about _shared

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do SDD skills persist artifacts across sessions?▼

SDD skills persist artifacts using one of four modes: engram, openspec, hybrid, or none. Engram mode saves to working memory with deterministic topic keys, openspec writes files under openspec/changes/, and hybrid writes to both for recovery plus team sharing.

What is the difference between engram and openspec artifact stores?▼

Engram provides cross-session recovery and compaction survival but overwrites on upsert with no history. OpenSpec stores files in the repo with full git history and team shareability, but cannot survive context compaction on its own.

Can the _shared skill be invoked directly?▼

No, _shared is a support package only and is explicitly marked not invokable with disable-model-invocation and user-invocable set to false. It exists solely as reference documentation consumed by real SDD phase skills.

Why does mem_search not return full artifact content?▼

mem_search returns only 300-character previews by design. You must call mem_get_observation with the observation ID from the search result to retrieve complete artifact content before using it.

When should I use hybrid persistence mode?▼

Use hybrid mode when you need both cross-session recovery through Engram and version-controlled files for team collaboration. It consumes more tokens per operation since every artifact is written to both stores.

Related Skills

Explore More Software Engineering Skills→
josemartinrodriguezmortalonijosemartinrodriguezmortaloni

sdd-init

Initialize Spec-Driven Development directories and generate a tailored openspec/config.yaml.

Community
Intermediate
Gentleman-ProgrammingGentleman-Programming
6.1k

sdd-onboard

Guides users through a complete Spec-Driven Development cycle on their real codebase.

Official
Advanced
aroca89aroca89

skill-registry

Scan skill directories and write a resolved registry to .atl/skill-registry.md.

Community
Advanced
DalomeveDalomeve
3

phoenix-loop

Generate validated recovery playbooks from recurring failure signatures.

Community
Advanced