Skills context-persistence
📦

context-persistence

Content revision r1 Safe ⚙️ External commands

在 AI 程式開發工作階段之間保留專案脈絡

長時間的 AI 程式開發工作階段可能會在重設後遺失決策、進度與下一步。此技能定義了 waypoint files，用於為 Claude、Codex 和 Claude Code 保留脈絡。

Supports: Claude Codex Code(CC)
Maintain this Skill? Claim it 🥉 77 Bronze

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request
Review the Skillstore skill "context-persistence" from https://skillstore.io/skills/dojocodinglabs-context-persistence.md and its manifest at https://skillstore.io/api/skills/dojocodinglabs-context-persistence/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.

Your Agent should still show its plan and request any confirmation required by the security policy.

Agent-readable resources

Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.

Markdown detail GET /skills/dojocodinglabs-context-persistence.md Signed manifest GET /api/skills/dojocodinglabs-context-persistence/manifest Signed lockfile GET /api/skills/dojocodinglabs-context-persistence/lockfile

Test it

Using "context-persistence". 開發者要求開始一項可能需要多個工作階段的付款整合。

Expected outcome:

助手會建立包含策略計畫、工作階段進度區段，以及具備驗收標準之任務階段的 waypoint。

Using "context-persistence". 使用者在脈絡重設後回來，並要求繼續 authentication 工作。

Expected outcome:

助手會讀取脈絡筆記，回報已完成項目，指出目前檔案，並恢復已記錄的下一步行動。

Using "context-persistence". 團隊成員需要接手一項中斷的 refactor。

Expected outcome:

助手會摘要決策、阻礙、修改過的檔案與剩餘任務，讓交接直接且可執行。

Security Audit

Safe
v8 • 7/6/2026 Open versioned report

All 55 static findings are false positives caused by Markdown inline code, fenced examples, and prose examples in SKILL.md. I found no executable script, real shell execution, network behavior, or prompt-injection attempt in the reviewed file. The remaining concern is operational: stale waypoint notes could mislead a future session if users do not refresh them.

1
Files scanned
623
Lines analyzed
0
Review items
0
False positives ignored

Risk Factors

⚙️ External commands (51)
SKILL.md:42 SKILL.md:44 SKILL.md:59-86 SKILL.md:86-88 SKILL.md:88-103 SKILL.md:103-180 SKILL.md:180-182 SKILL.md:182-195 SKILL.md:195-247 SKILL.md:247-257 SKILL.md:257-274 SKILL.md:274-310 SKILL.md:310-327 SKILL.md:327-361 SKILL.md:361-379 SKILL.md:379-385 SKILL.md:385-388 SKILL.md:388-389 SKILL.md:389-390 SKILL.md:390-399 SKILL.md:399-400 SKILL.md:400-401 SKILL.md:401-404 SKILL.md:404-405 SKILL.md:405-406 SKILL.md:406-414 SKILL.md:414-427 SKILL.md:427-433 SKILL.md:433-437 SKILL.md:437-444 SKILL.md:444-446 SKILL.md:446-448 SKILL.md:448-452 SKILL.md:452-461 SKILL.md:461-463 SKILL.md:463-467 SKILL.md:467-478 SKILL.md:478-517 SKILL.md:517-528 SKILL.md:528-536 SKILL.md:536-545 SKILL.md:545-549 SKILL.md:549-563 SKILL.md:563-567 SKILL.md:567-573 SKILL.md:573-577 SKILL.md:577-587 SKILL.md:587-591 SKILL.md:591-598 SKILL.md:598-618 SKILL.md:618
No confirmed security findings were detected by the latest completed static and semantic audit. This does not prove the skill has no side effects.
Audited by: codex View Audit History →
Share & cite this report

Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.

Open versioned report
Security Assessment

Copy report link

https://skillstore.io/skills/dojocodinglabs-context-persistence/audits/8?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/dojocodinglabs-context-persistence/security.svg)](https://skillstore.io/skills/dojocodinglabs-context-persistence?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/dojocodinglabs-context-persistence?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/dojocodinglabs-context-persistence/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/dojocodinglabs-context-persistence.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>
Academic citations (APA · BibTeX · CFF)

APA citation

DojoCodingLabs. (2026). context-persistence security audit report (audit version 8) [Author version unspecified]. Skillstore. https://skillstore.io/skills/dojocodinglabs-context-persistence/audits/8

BibTeX citation

@techreport{dojocodinglabs-dojocodinglabs-context-persistence-2026, author = {DojoCodingLabs}, title = {context-persistence security audit report (audit version 8)}, institution = {Skillstore}, year = {2026}, number = {8}, url = {https://skillstore.io/skills/dojocodinglabs-context-persistence/audits/8}, note = {Author version unspecified} }

CITATION.cff

cff-version: 1.2.0 message: "If you use this Skill, cite its author and this versioned security audit report." title: "context-persistence security audit report (audit version 8)" version: "unspecified" type: report authors: - name: "DojoCodingLabs" date-released: "2026-07-06" url: "https://skillstore.io/skills/dojocodinglabs-context-persistence/audits/8" identifiers: - type: other value: "skillstore:dojocodinglabs-context-persistence:audit:8" description: "Skillstore immutable audit report identifier"

Skillstore Score

Why this score Evidence Confidence: High
55
Architecture
85
Maintainability
87
Content
71
Community
78
Spec Compliance

What You Can Build

恢復長期功能開發

為跨多個工作階段的實作任務，保留已完成工作、目前檔案與下一步的清楚紀錄。

交接專案狀態

記錄決策、阻礙與進行中的任務，讓另一位貢獻者能以較少的設定時間接續工作。

在脈絡重設後復原

在歷史紀錄遺失或長時間中斷後，給 AI 助手一條簡潔路徑回到任務中。

Try These Prompts

建立基本 Waypoint 
為此任務建立 waypoint 計畫。包含策略計畫、目前脈絡，以及可執行的任務檢查清單。
更新目前進度 
使用已完成事項、進行中事項、阻礙、已變更檔案，以及確切的下一步行動來更新 waypoint 脈絡。
從現有脈絡恢復 
讀取作用中的 waypoint files，摘要目前狀態，確認下一步行動，並從已記錄的位置繼續。
稽核過時的 Waypoint 狀態 
將 waypoint 脈絡與目前 repository 狀態進行檢視，找出過時假設，更新任務清單，並提出下一個安全步驟。

Best Practices

  • 在重要里程碑、決策、阻礙或任務切換後更新工作階段進度。
  • 讓下一步行動具體明確，包含相關檔案、function 與預期後續動作。
  • 如果筆記已超過三天，恢復前先刷新過時脈絡。

Avoid

  • 不要為瑣碎的單行變更或純機械式清理建立 waypoint 計畫。
  • 不要留下省略目前檔案或下一個具體行動的模糊進度筆記。
  • 不要在 waypoint 文件中儲存憑證、API keys 或其他機密。

Frequently Asked Questions

這個技能解決什麼問題？
它透過保留結構化專案筆記，幫助 AI 程式開發工作承受脈絡重設、中斷與交接。
我應該何時使用它？
將它用於橫跨多個工作階段、影響許多檔案，或需要清楚交接文件的工作。
它建議哪些檔案？
它建議為每個作用中任務準備一個計畫檔案、一個脈絡檔案和一個任務檔案。
它會執行 commands 嗎？
不會。此技能是文件指引。任何 command 範例都是工作流程範例，不是此技能中的可執行程式碼。
它可以取代議題追蹤嗎？
不能。它透過保留本機實作脈絡與下一步行動來補足議題追蹤工具。
應如何處理敏感資訊？
不要在 waypoint files 中記錄機密。可以參照安全儲存位置，但不要複製敏感值。

Developer Details

License

MIT

Skillstore revision

r1

Version notice

The author did not declare a version.

Repository

https://github.com/DojoCodingLabs/claude-code-waypoint/tree/main/.claude/skills/context-persistence

Ref

72d5025b022c77f7a51bdf5c1637c689c80e89d1

Maintenance freshness

7/21/2026

Usage

3 downloads · 294 views

File structure

📄 SKILL.md

More from DojoCodingLabs

View all

Related Skills

View all