Agent Skillsparcadei/Continuous-Claude-v3 › continuity-ledger

continuity-ledger

GitHub

用于在会话清除时创建或更新状态交接文档,确保上下文连续性。通过生成特定格式的YAML文件记录目标、成果、决策及下一步计划,实现跨会话的状态保留与知识传承。

.claude/skills/continuity_ledger/SKILL.md parcadei/Continuous-Claude-v3

Trigger Scenarios

需要保存当前工作进度以便后续继续 会话结束前需移交上下文信息 用户请求创建状态交接文档

Install

npx skills add parcadei/Continuous-Claude-v3 --skill continuity-ledger -g -y
More Options

Non-standard path

npx skills add https://github.com/parcadei/Continuous-Claude-v3/tree/main/.claude/skills/continuity_ledger -g -y

Use without installing

npx skills use parcadei/Continuous-Claude-v3@continuity-ledger

指定 Agent (Claude Code)

npx skills add parcadei/Continuous-Claude-v3 --skill continuity-ledger -a claude-code -g -y

安装 repo 全部 skill

npx skills add parcadei/Continuous-Claude-v3 --all -g -y

预览 repo 内 skill

npx skills add parcadei/Continuous-Claude-v3 --list

SKILL.md

Frontmatter
{
    "name": "continuity-ledger",
    "description": "Create or update continuity ledger for state preservation across clears"
}

Continuity Ledger

Note: This skill is now an alias for /create_handoff. Both output the same YAML format.

Create a YAML handoff document for state preservation across /clear. This is the same as /create_handoff.

Process

1. Filepath & Metadata

First, determine the session name from existing handoffs:

ls -td thoughts/shared/handoffs/*/ 2>/dev/null | head -1 | xargs basename

This returns the most recently modified handoff folder name (e.g., open-source-release). Use this as the handoff folder name.

If no handoffs exist, use general as the folder name.

Create your file under: thoughts/shared/handoffs/{session-name}/YYYY-MM-DD_HH-MM_description.yaml, where:

  • {session-name} is from existing handoffs (e.g., open-source-release) or general if none exist
  • YYYY-MM-DD is today's date
  • HH-MM is the current time in 24-hour format (no seconds needed)
  • description is a brief kebab-case description

Examples:

  • thoughts/shared/handoffs/open-source-release/2026-01-08_16-30_memory-system-fix.yaml
  • thoughts/shared/handoffs/general/2026-01-08_16-30_bug-investigation.yaml

2. Write YAML handoff (~400 tokens)

CRITICAL: Use EXACTLY this YAML format. Do NOT deviate or use alternative field names.

The goal: and now: fields are shown in the statusline - they MUST be named exactly this.

---
session: {session-name from ledger}
date: YYYY-MM-DD
status: complete|partial|blocked
outcome: SUCCEEDED|PARTIAL_PLUS|PARTIAL_MINUS|FAILED
---

goal: {What this session accomplished - shown in statusline}
now: {What next session should do first - shown in statusline}
test: {Command to verify this work, e.g., pytest tests/test_foo.py}

done_this_session:
  - task: {First completed task}
    files: [{file1.py}, {file2.py}]
  - task: {Second completed task}
    files: [{file3.py}]

blockers: [{any blocking issues}]

questions: [{unresolved questions for next session}]

decisions:
  - {decision_name}: {rationale}

findings:
  - {key_finding}: {details}

worked: [{approaches that worked}]
failed: [{approaches that failed and why}]

next:
  - {First next step}
  - {Second next step}

files:
  created: [{new files}]
  modified: [{changed files}]

Field guide:

  • goal: + now: - REQUIRED, shown in statusline
  • done_this_session: - What was accomplished with file references
  • decisions: - Important choices and rationale
  • findings: - Key learnings
  • worked: / failed: - What to repeat vs avoid
  • next: - Action items for next session

DO NOT use alternative field names like session_goal, objective, focus, current, etc. The statusline parser looks for EXACTLY goal: and now: - nothing else works.

3. Mark Session Outcome (REQUIRED)

IMPORTANT: Before responding to the user, you MUST ask about the session outcome.

Use the AskUserQuestion tool with these exact options:

Question: "How did this session go?"
Options:
  - SUCCEEDED: Task completed successfully
  - PARTIAL_PLUS: Mostly done, minor issues remain
  - PARTIAL_MINUS: Some progress, major issues remain
  - FAILED: Task abandoned or blocked

After the user responds, mark the outcome:

# Mark the most recent handoff (works with PostgreSQL or SQLite)
PROJECT_ROOT=$(git rev-parse --show-toplevel 2>/dev/null || echo "${CLAUDE_PROJECT_DIR:-.}")
cd "$PROJECT_ROOT/opc" && uv run python scripts/core/artifact_mark.py --latest --outcome <USER_CHOICE>

4. Confirm completion

After marking the outcome, respond to the user:

Handoff created! Outcome marked as [OUTCOME].

Resume in a new session with:
/resume_handoff path/to/handoff.yaml

When to Use

  • Before running /clear
  • Context usage approaching 70%+
  • Multi-day implementations
  • Complex refactors you pick up/put down
  • Any session expected to hit 85%+ context

When NOT to Use

  • Quick tasks (< 30 min)
  • Simple bug fixes
  • Single-file changes

Why Clear Instead of Compact?

Each compaction is lossy compression—after several compactions, you're working with degraded context. Clearing + loading the handoff gives you fresh context with full signal.

Version History

  • d07ff4b Current 2026-08-20 12:46

Same Skill Collection

.claude/plugins/braintrust-tracing/skills/trace-claude-code/SKILL.md
.claude/skills/agentica-claude-proxy/SKILL.md
.claude/skills/agentica-infrastructure/SKILL.md
.claude/skills/agentica-prompts/SKILL.md
.claude/skills/agentica-sdk/SKILL.md
.claude/skills/agentica-server/SKILL.md
.claude/skills/archive/leann-search/SKILL.md
.claude/skills/ast-grep-find/SKILL.md
.claude/skills/braintrust-tracing/SKILL.md
.claude/skills/cli-reference/SKILL.md
.claude/skills/commit/SKILL.md
.claude/skills/compound-learnings/SKILL.md
.claude/skills/create_handoff/SKILL.md
.claude/skills/dead-code/SKILL.md
.claude/skills/debug-hooks/SKILL.md
.claude/skills/debug/SKILL.md
.claude/skills/describe_pr/SKILL.md
.claude/skills/discovery-interview/SKILL.md
.claude/skills/explore/SKILL.md
.claude/skills/firecrawl-scrape/SKILL.md
.claude/skills/fix/SKILL.md
.claude/skills/github-search/SKILL.md
.claude/skills/help/SKILL.md
.claude/skills/hook-developer/SKILL.md
.claude/skills/implement_plan_micro/SKILL.md
.claude/skills/implement_plan/SKILL.md
.claude/skills/implement_task/SKILL.md
.claude/skills/loogle-search/SKILL.md
.claude/skills/math-help/SKILL.md
.claude/skills/math-router/SKILL.md
.claude/skills/math-unified/SKILL.md
.claude/skills/math/abstract-algebra/fields/SKILL.md
.claude/skills/math/abstract-algebra/groups/SKILL.md
.claude/skills/math/abstract-algebra/rings/SKILL.md
.claude/skills/math/category-theory/categories-functors/SKILL.md
.claude/skills/math/category-theory/limits-colimits/SKILL.md
.claude/skills/math/category-theory/natural-transformations/SKILL.md
.claude/skills/math/complex-analysis/analytic-functions/SKILL.md
.claude/skills/math/complex-analysis/contour-integrals/SKILL.md
.claude/skills/math/complex-analysis/residues/SKILL.md
.claude/skills/math/functional-analysis/banach-spaces/SKILL.md
.claude/skills/math/functional-analysis/hilbert-spaces/SKILL.md
.claude/skills/math/functional-analysis/operator-theory/SKILL.md
.claude/skills/math/graph-number-theory/graph-algorithms/SKILL.md
.claude/skills/math/graph-number-theory/modular-arithmetic/SKILL.md
.claude/skills/math/graph-number-theory/prime-numbers/SKILL.md
.claude/skills/math/information-theory/channel-capacity/SKILL.md
.claude/skills/math/information-theory/entropy/SKILL.md
.claude/skills/math/information-theory/source-coding/SKILL.md

Metadata

Files
0
Version
d07ff4b
Hash
76114515
Indexed
2026-08-20 12:46

Главная - Вики-сайт
Copyright © 2011-2026 iteam. Current version is 2.155.2. UTC+08:00, 2026-08-21 07:42
浙ICP备14020137号-1 $Гость$