소스 정보
- 저장소
- huytieu/COG-second-brain
- 최근 소스 활동
- 2026년 6월 22일 03:03
- 감지된 SKILL.md 언어
- 영어
- 스타
- 1,145
- 포크
- 131
설치 방법
기본적으로 소스를 먼저 확인하는 Prompt가 선택됩니다. 직접 명령으로 전환하거나 로컬 사본을 다운로드할 수도 있습니다.
소스 파일 검토
설치 여부를 결정하기 전에 SKILL.md와 SkillsMP에 표시된 보조 파일을 읽어 보세요.
메뉴
기본적으로 소스를 먼저 확인하는 Prompt가 선택됩니다. 직접 명령으로 전환하거나 로컬 사본을 다운로드할 수도 있습니다.
설치 여부를 결정하기 전에 SKILL.md와 SkillsMP에 표시된 보조 파일을 읽어 보세요.
SOC 직업 분류 기준
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
직접 명령은 검토 Prompt를 거치지 않습니다. 실행하기 전에 소스를 확인하세요.
npx skills add https://github.com/huytieu/COG-second-brain --skill weekly-checkin명령은 한 줄로 유지됩니다. 복사하기 전에 가로로 스크롤해 전체 내용을 확인하세요.
로컬 사본을 원하시나요? SkillsMP에서 현재 제공할 수 있는 파일을 다운로드하세요.
SKILL.md 표시 중
Run one task through the V-model verification loop: CP-2 plan → CP-3 build → CP-3v component verify → CP-4 integration verify (full lane) → CP-5 acceptance. The worker never grades its own homework; evidence rows trace back to AC-n. Opt-in: invoke with /closed-loop or by asking for the closed loop, proper verification, or an evidence trail. Ordinary work does not run this.
Run a large, multi-session goal (e.g. shipping a whole side product) through the full V-model closed loop, one phase at a time, with cross-session state and a final north-star acceptance gate. Ultragoals never downgrade the lane: every phase runs CP-1→CP-6 with adversarial verification. Opt-in: invoke with /ultragoal or by calling something a long-running goal. Ordinary work does not run this.
Run one task through the V-model verification loop: CP-2 plan → CP-3 build → CP-3v component verify → CP-4 integration verify (full lane) → CP-5 acceptance. The worker never grades its own homework; evidence rows trace back to AC-n. Opt-in: invoke with /closed-loop or by asking for the closed loop, proper verification, or an evidence trail. Ordinary work does not run this.
| name | weekly-checkin |
| description | Cross-domain pattern analysis and strategic reflection for weekly review |
| roles | ["all"] |
| integrations | [] |
Comprehensive weekly review and analysis integrating insights across all domains (personal, professional, projects) with pattern recognition and strategic planning.
Check agent_mode in 00-inbox/MY-PROFILE.md frontmatter:
agent_mode: team — delegate domain-specific analysis to sub-agents (e.g., one for personal patterns, one for professional review, one per active project). Each agent scans relevant braindumps/briefs and returns insights. Combine into the weekly synthesis.agent_mode: solo (default) — handle all scanning and analysis directly in the conversation. No delegation.Check for user profile (optional but enhances experience):
00-inbox/MY-PROFILE.md in the vaultGet current timestamp (REQUIRED before generating any files):
date '+%Y-%m-%d %H:%M' using Bash to get the actual current date and timecreated: frontmatter fielddate commandScan recent files from the past week:
01-daily/briefs/02-personal/braindumps/, 03-professional/braindumps/, 04-projects/*/braindumps/01-daily/checkins/If MY-PROFILE.md available:
Lead user through reflection questions in a warm, conversational tone:
Ask:
Listen for:
Personal Domain: Ask:
Professional Domain: Ask:
Projects Domain (if applicable): For each active project from MY-PROFILE.md: Ask:
Ask:
Help identify:
Ask:
Help with:
Based on the conversation, create a structured check-in document:
---
type: "weekly-checkin"
domain: "integrated"
date: "YYYY-MM-DD"
week_of: "YYYY-MM-DD"
created: "YYYY-MM-DD HH:MM"
tags: ["#weekly-checkin", "#reflection", "#planning"]
domains_analyzed: ["personal", "professional", "projects"]
rating: [1-5]
braindumps_reviewed: [count]
briefs_reviewed: [count]
---
# Weekly Check-in - Week of [Date]
## Executive Summary
**Week Rating:** [1-5] ⭐ - [User's reasoning in their words]
**In Three Words:** [word1], [word2], [word3]
**Key Highlights:**
- [Win 1 - specific and celebratory]
- [Win 2 - acknowledge effort and outcome]
- [Win 3 if applicable]
**Main Challenges:**
- [Challenge 1 - honest and clear]
- [Challenge 2 - what made it difficult]
---
## Domain Reviews
### 💭 Personal
**Wellness & Self-Care:**
[User's reflection on personal wellness, relationships, health]
**Energy Patterns:**
- [Observations about energy levels throughout the week]
- [What energized them]
- [What drained them]
**Personal Growth:**
- [Insights or realizations]
- [New habits or changes]
**Rating:** [1-5] ⭐
---
### 💼 Professional
**Accomplishments:**
[User's reflection on work accomplishments, projects completed, milestones reached]
**Team & Collaboration:**
[Insights about team dynamics, meetings, relationships]
**Challenges & Learnings:**
[What was difficult and what they learned]
**Professional Development:**
[Skills developed, knowledge gained]
**Rating:** [1-5] ⭐
---
### 🎯 Projects
[For each active project:]
#### [Project Name]
**Progress This Week:**
- [What moved forward - be specific]
[Milestones achieved]
[Decisions made]
[On track | Needs attention | Blocked | Pivoting]
[What's in the way - if any]
[Dependencies waiting on]
[Any strategic insights or direction changes]
[ ] [Specific next action 1] 📅 [YYYY-MM-DD = date of next Monday]
[ ] [Specific next action 2] 📅 [YYYY-MM-DD = date of next Friday]
[ ] [Specific next action 3] 📅 [YYYY-MM-DD = date +1 week from today]
[1-5] ⭐
---
[Themes identified across all braindumps and activities this week:]
[Description and significance]
[Description and significance]
[Description and significance]
[When they were most productive/energized]
[When energy dipped]
[What influenced energy - sleep, meetings, deep work, etc.]
[Connections between personal, professional, and project domains:]
[Connection 1 - e.g., "Personal stress affecting project focus"]
[Connection 2 - e.g., "Professional wins boosting personal confidence"]
[Connection 3 - e.g., "Project learning applying to work"]
[How their thinking or approach evolved during the week:]
[Evolution 1]
[Evolution 2]
---
[Priority 1 - specific and actionable]
[Priority 2 - specific and actionable]
[Priority 3 - specific and actionable]
[Brief explanation of strategic importance]
[ ] [Unresolved item from this week - with context] 📅 [YYYY-MM-DD = date of next Monday]
[ ] [Ongoing task - with next action] 📅 [YYYY-MM-DD = mid-next-week]
[ ] [Follow-up needed - with who/what] 📅 [YYYY-MM-DD = date +1 week from today]
[Experiment 1 - be specific about what and why]
[Experiment 2 - what you hope to learn]
[Practice 1 that's working well]
[Habit 2 to maintain]
[Thing 1 that's not serving you]
[Practice 2 to eliminate]
[Measurable outcome 1]
[Measurable outcome 2]
[Qualitative measure 3]
---
[X] braindumps reviewed
[X] daily briefs reviewed
[X] previous check-ins referenced
Braindumps: [count] across [domains]
Most active domain: [domain name]
Dominant themes: [top 2-3 themes]
[Overall emotional trajectory of the week - growing, stable, declining, mixed]
---
[Higher-level observations about trajectory, patterns, or strategic direction]
[Question 1 that emerged during review]
[Question 2 for future consideration]
[Optional - what they're grateful for or who they want to acknowledge]
---
Save to: 01-daily/checkins/weekly-checkin-YYYY-MM-DD.md
After creating the check-in:
The weekly check-in pairs a per-domain scan loop with a human-in-the-loop reflection, gated by a coverage checklist. See .claude/skills/loop-engineering/SKILL.md for the shared vocabulary.
The scan loop (gather phase): scan each domain's recent files → aggregate candidate themes → run the coverage check → if a domain or active project is thin, scan it more deeply before moving on. In agent_mode: team, fan this out as one worker per domain (orchestrator-workers); each returns its themes only.
The reflection loop (guided phase): this is human-in-the-loop by design. Ask, listen, reflect back, ask the targeted follow-up. The loop continues until the coverage checklist is satisfied or the user signals they are done. Do not rush it and do not force positivity.
The verifier (deterministic checklist):
MY-PROFILE.md has a Projects section addressed.Termination conditions (layered):
Patterns: orchestrator-workers (team-mode domain scans) + human-in-the-loop (reflection) + completeness checklist (the verifier).
In-loop context: capture answers into the check-in structure as the conversation goes, so a long reflection does not lose early answers.
Review multiple weekly check-ins to:
Weekly check-ins provide:
Check-ins feed into:
The weekly check-in skill embodies COG's integrated intelligence approach: