SkillCurated by metahubEval warningsagents

system-overview

Name: system-overview
Author: parcadei

Show users how Continuous Claude works - the opinionated setup with hooks, memory, and coordination

pinned to #d07ff4bupdated last month

6/11Verified publisherCurated by MetaHubLicensedDocumentedStructuredClean repo

Ask your AI client: “install skills/system-overview”.

Requires the metahub MCP server installed in your client. Set up MCP.

mh install skills/system-overview

metahub onboarded this repo on the author's behalf.

If you own github.com/parcadei/Continuous-Claude-v3 on GitHub, claim the listing to take over publishing. Your claim preserves the existing eval history and badges; only the curator label is replaced with verified-publisher on your next publish.

Claim this repo

Stars

3,883

Last commit

last month

d07ff4b

Latest release

published

last month

#agents
#claude-code
#claude-code-cli
#claude-code-hooks
#claude-code-mcp
#claude-code-skills
#claude-code-subagents
#claude-skills
#mcp

About this skill

Pulled from SKILL.md at publish time.

Show users how Continuous Claude works - the opinionated setup with hooks, memory, and coordination.

Evaluation report

WarningsView full report

Automated checks the publisher passed at publish time — structure, docs, safety, and whether the artifact behaves as claimed.d07ff4b· last month

Behavioral checks ran but aren't published for this artifact; the static checks above ran at publish time.

Documentation

8 passed1 warning

Homepage or repository declaredwarn
No homepage or repository declared.
Add a "homepage" or "repository" field to SKILL.md.
Description quality
15 words · 99 chars — "Show users how Continuous Claude works - the opinionated setup with hooks, memor…"
README is present and substantial
45,577 chars · 22 sections · 38 code blocks
Tags / topics declared
9 total — agents, claude-code, claude-code-cli, claude-code-hooks, claude-code-mcp, claude-code-skills (+3)
README has usage / example sections
found: Quick Start · Installation · Installation (+1)
Homepage / docs URL declared
no homepage declared (registry will use the repo URL) — info-only, not blocking
Description is substantive
Description is 15 words.
Documentation present and substantive
Documentation present (SKILL.md, 335 words).
Documentation shows usage
Documentation includes 1 code example.

Release history

releasecurrentd07ff4bwarnlast month

View on GitHub

Show users how Continuous Claude works - the opinionated setup with hooks, memory, and coordination.

When to Use

User asks "how does this work?"
User asks "what can you remember?"
User asks "what's different about this setup?"
User runs /system_overview

Response

CONTINUOUS CLAUDE SYSTEM OVERVIEW
=================================

MEMORY LAYER (PostgreSQL + pgvector)
------------------------------------
- 78,000+ temporal facts from past sessions
- Learnings extracted automatically at session end
- Semantic search with embeddings

RECALL: uv run python opc/scripts/recall_temporal_facts.py --query "your topic"

HOOKS (9 event types registered)
--------------------------------
SessionStart    → Load continuity ledger, rebuild symbol index
UserPromptSubmit → Skill activation check, context injection
PreToolUse      → Smart search routing (Grep → TLDR for code)
PostToolUse     → File claims, compiler feedback
PreCompact      → Save state before context compaction
Stop            → Extract learnings, create handoffs
SubagentStart   → Register spawned agents
SubagentStop    → Coordination, handoff creation
SessionEnd      → Cleanup

CONTINUITY SYSTEM
-----------------
Ledger:   thoughts/ledgers/CONTINUITY_CLAUDE-{session}.md
Handoffs: thoughts/shared/handoffs/{session}/*.yaml

Commands:
  /resume_handoff <path>  - Continue from handoff
  /create_handoff         - Create snapshot for transfer

TLDR CODE INTELLIGENCE
----------------------
5-layer analysis: AST → Call Graph → CFG → DFG → PDG
95% token savings vs reading raw files
Auto-intercepts Grep for .py/.ts/.go/.rs files

Pre-built index: /tmp/claude-symbol-index/symbols.json

SETUP
-----
Run: uv run python opc/scripts/setup/wizard.py

Options:
  [1] SQLite only (simple, offline)
  [2] PostgreSQL + pgvector (semantic search)

Key Files

Component	Location
Hook registration	`.claude/settings.json`
Hook implementations	`.claude/hooks/src/*.ts`
Rules (auto-injected)	`.claude/rules/*.md`
Skills	`.claude/skills/*/SKILL.md`
Setup wizard	`opc/scripts/setup/wizard.py`
Recall script	`opc/scripts/recall_temporal_facts.py`
Store learning	`opc/scripts/core/store_learning.py`
Symbol index builder	`opc/scripts/build_symbol_index.py`

Environment Variables

Variable	Purpose
`CONTINUOUS_CLAUDE_DB_URL`	PostgreSQL connection
`VOYAGE_API_KEY`	Embeddings (optional)
`BRAINTRUST_API_KEY`	Tracing (optional)
`CLAUDE_PROJECT_DIR`	Auto-set by Claude Code

Reviews

No reviews yet. Be the first.

Skill

Verification Before Completion

Evidence before assertions, always

#f2cbfbeActiveCode Review, Testing & QualityMIT+6

obra

253,04922,600Shell

verificationqualityworkflow

Skill

Writing Plans

Turn specs into phased implementation plans

#f2cbfbeActiveProductivity & WorkflowsMIT+5

obra

253,04922,600Shell

planningarchitectureworkflow

Skill

Test-Driven Development

Red → green → refactor discipline for any feature or bugfix

#f2cbfbeActiveCode Review, Testing & QualityMIT+6

obra

253,04922,600Shell

tddtestingworkflow+1

mh install skills/system-overview

Response

CONTINUOUS CLAUDE SYSTEM OVERVIEW ================================= MEMORY LAYER (PostgreSQL + pgvector) ------------------------------------ - 78,000+ temporal facts from past sessions - Learnings extracted automatically at session end - Semantic search with embeddings RECALL: uv run python opc/scripts/recall_temporal_facts.py --query "your topic" HOOKS (9 event types registered) -------------------------------- SessionStart → Load continuity ledger, rebuild symbol index UserPromptSubmit → Skill activation check, context injection PreToolUse → Smart search routing (Grep → TLDR for code) PostToolUse → File claims, compiler feedback PreCompact → Save state before context compaction Stop → Extract learnings, create handoffs SubagentStart → Register spawned agents SubagentStop → Coordination, handoff creation SessionEnd → Cleanup CONTINUITY SYSTEM ----------------- Ledger: thoughts/ledgers/CONTINUITY_CLAUDE-{session}.md Handoffs: thoughts/shared/handoffs/{session}/*.yaml Commands: /resume_handoff <path> - Continue from handoff /create_handoff - Create snapshot for transfer TLDR CODE INTELLIGENCE ---------------------- 5-layer analysis: AST → Call Graph → CFG → DFG → PDG 95% token savings vs reading raw files Auto-intercepts Grep for .py/.ts/.go/.rs files Pre-built index: /tmp/claude-symbol-index/symbols.json SETUP ----- Run: uv run python opc/scripts/setup/wizard.py Options: [1] SQLite only (simple, offline) [2] PostgreSQL + pgvector (semantic search)

Key Files

Component

Location

Hook registration

.claude/settings.json

Hook implementations

.claude/hooks/src/*.ts

Rules (auto-injected)

.claude/rules/*.md

Skills

.claude/skills/*/SKILL.md

Setup wizard

opc/scripts/setup/wizard.py

Recall script

opc/scripts/recall_temporal_facts.py

Store learning

opc/scripts/core/store_learning.py

Symbol index builder

opc/scripts/build_symbol_index.py

Variable

Purpose

CONTINUOUS_CLAUDE_DB_URL

PostgreSQL connection

VOYAGE_API_KEY

Embeddings (optional)

BRAINTRUST_API_KEY

Tracing (optional)

CLAUDE_PROJECT_DIR

Auto-set by Claude Code

system-overview

About this skill

Evaluation report

Documentation

Release history

Contents

When to Use

Response

Key Files

Environment Variables

Reviews

Related

Verification Before Completion

Writing Plans

Test-Driven Development

system-overview

About this skill

Evaluation report

Documentation

Release history

Contents

When to Use

Response

Key Files

Environment Variables

Reviews

Related

Verification Before Completion

Writing Plans

Test-Driven Development