Skills chat-compactor
📦

chat-compactor

Content revision r1 Low Risk ⚙️ External commands

Compact AI Coding Sessions

Long coding chats lose decisions, blockers, and file state. This skill creates concise handoff summaries for Claude, Codex, and Claude Code.

Supports: Claude Codex Code(CC)
📊 76 Adequate

Install with my Agent

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

Agent request
Review the Skillstore skill "chat-compactor" from https://skillstore.io/skills/zhanlincui-chat-compactor.md and its manifest at https://skillstore.io/api/skills/zhanlincui-chat-compactor/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/zhanlincui-chat-compactor.md Signed manifest GET /api/skills/zhanlincui-chat-compactor/manifest Signed lockfile GET /api/skills/zhanlincui-chat-compactor/lockfile

Test it

Using "chat-compactor". User asks to wrap up after implementing an authentication refactor.

Expected outcome:

A markdown session note with the refactor goal, completed changes, rejected approaches, current blockers, and next validation step.

Using "chat-compactor". User reaches a long debugging conversation about failing tests.

Expected outcome:

A compact handoff listing symptoms, tried fixes, useful files, dead ends, and the next test to run.

Using "chat-compactor". User switches from Claude to Codex during a feature build.

Expected outcome:

A continuity summary that names the feature state, decisions, modified areas, environment notes, and prioritized follow-up work.

Security Audit

Low Risk
v4 • 7/8/2026 Open versioned report

All four static command execution findings are false positives caused by markdown fences and inline filename examples in SKILL.md. No prompt injection or malicious command execution intent was found. A low risk privacy concern remains because saved summaries may preserve sensitive project context.

1
Files scanned
100
Lines analyzed
0
Review items
0
False positives ignored

Confirmed security concerns (1)

Low
SKILL.md:65SKILL.md:98
Sensitive Context Persistence
The workflow asks agents to save session summaries to project root or /home/claude/sessions. Those summaries can contain decisions, file paths, blockers, and environment details.
The save instructions are explicit at both cited lines, but exposure depends on summary contents and repository practices.

Risk Factors

⚙️ External commands (4)
SKILL.md:24-58 SKILL.md:58-65 SKILL.md:65 SKILL.md:98-99
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/zhanlincui-chat-compactor/audits/4?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/zhanlincui-chat-compactor/security.svg)](https://skillstore.io/skills/zhanlincui-chat-compactor?utm_source=security_passport_badge)

HTML badge

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

Embed card

<iframe src="https://skillstore.io/embed/skills/zhanlincui-chat-compactor.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

ZhanlinCui. (2026). chat-compactor security audit report (audit version 4) [Author version unspecified]. Skillstore. https://skillstore.io/skills/zhanlincui-chat-compactor/audits/4

BibTeX citation

@techreport{zhanlincui-zhanlincui-chat-compactor-2026, author = {ZhanlinCui}, title = {chat-compactor security audit report (audit version 4)}, institution = {Skillstore}, year = {2026}, number = {4}, url = {https://skillstore.io/skills/zhanlincui-chat-compactor/audits/4}, 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: "chat-compactor security audit report (audit version 4)" version: "unspecified" type: report authors: - name: "ZhanlinCui" date-released: "2026-07-08" url: "https://skillstore.io/skills/zhanlincui-chat-compactor/audits/4" identifiers: - type: other value: "skillstore:zhanlincui-chat-compactor:audit:4" description: "Skillstore immutable audit report identifier"

Skillstore Score

Why this score Evidence Confidence: High
55
Architecture
85
Maintainability
87
Content
69
Community
91
Spec Compliance

What You Can Build

End a Coding Session

Create a concise handoff before stopping work on an implementation or debugging task.

Transfer Context Between Agents

Give a new Claude, Codex, or Claude Code session the decisions, files, blockers, and next actions.

Record Debugging History

Capture failed approaches and current state so the team avoids repeating costly investigation paths.

Try These Prompts

Basic Wrap-Up 
Use chat-compactor to summarize this session for the next AI agent. Include current state, completed work, blockers, and next steps.
Focused Debugging Handoff 
Use chat-compactor for this debugging session. Emphasize symptoms, hypotheses tested, failed approaches, useful files, and the next experiment.
Implementation Handoff 
Use chat-compactor to create a handoff for this feature. Include design decisions, modified files, validation status, risks, and prioritized follow-up work.
Multi-Session Continuity Plan 
Use chat-compactor to prepare a durable project handoff. Separate confirmed facts, assumptions, unresolved questions, environment notes, and actions for the next session.

Best Practices

  • Ask for compaction before the context window becomes difficult to review.
  • Review the summary for secrets before saving it to a project directory.
  • Include validation status and remaining uncertainty, not only completed work.

Avoid

  • Do not use vague progress notes without file names, blockers, or next actions.
  • Do not include secrets, credentials, private tokens, or unreleased customer data.
  • Do not treat the handoff as a substitute for commits or issue updates.

Frequently Asked Questions

When should I use this skill?
Use it near the end of a long coding, debugging, or planning session.
Does it run commands?
No. The skill is written guidance for producing a markdown handoff. Any tool use depends on the hosting agent.
Can it save the summary to a file?
It recommends saving a markdown note, but the agent or user must perform the file write.
Does it work with Claude Code and Codex?
Yes. The handoff format is plain markdown and suits Claude, Codex, and Claude Code workflows.
Will it recover context that is not in the chat?
No. It summarizes visible conversation context unless the agent separately inspects files or tools.
How should I handle sensitive information?
Remove secrets and private data before saving or sharing the summary.

Developer Details

Author

ZhanlinCui

License

MIT

Skillstore revision

r1

Version notice

The author did not declare a version.

Repository

https://github.com/ZhanlinCui/Ultimate-Agent-Skills-Collection/tree/main/chat-compactor

Ref

64ca8af0f54a325752f08bd54e52151061ea659a

Maintenance freshness

7/20/2026

Usage

58 downloads · 156 views

File structure

📄 SKILL.md

More from ZhanlinCui

View all

Related Skills

View all