← Back to Skills Marketplace
Time Capsule
by
John DeVere Cooley
· GitHub ↗
· v1.0.0
278
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install time-capsule
Description
Write messages to your future self — or your future team — that unlock when specific code conditions are met. "Dear future me: if you're reading this, someon...
Usage Guidance
This skill's idea is reasonable, but the instructions are vague about exactly what the agent will read and write. Before installing: 1) Request the full SKILL.md runtime steps showing any git/CI operations. 2) Require the skill to operate read-only or to propose changes as pull requests (not direct commits). 3) Refuse or closely review any added CI/workflow files — these can run with repo permissions and exfiltrate secrets. 4) Confirm whether any credentials (e.g., GITHUB_TOKEN, CI secrets) are needed and why; prefer short-lived tokens and explicit consent. 5) If you allow it, run the skill in a sandboxed repository and review all created files and commits before merging to main. If the author cannot provide concrete, minimal runtime steps and clear safeguards, treat the skill as untrusted.
Capability Analysis
Type: OpenClaw Skill
Name: time-capsule
Version: 1.0.0
The 'time-capsule' skill bundle is a conceptual tool designed to help teams preserve institutional knowledge by triggering messages based on codebase events (e.g., file edits, date reaches, or dependency updates). The SKILL.md file contains only descriptive documentation and templates for the agent to follow, with no executable code, suspicious network calls, or malicious instructions. All behaviors described are consistent with the stated purpose of improving documentation and team onboarding.
Capability Assessment
Purpose & Capability
The skill claims to embed messages in a codebase and surface them on triggers (file edits, dependency upgrades, first contributor, dates). Achieving that legitimately requires read/write access to the repository, access to git history, and likely CI/webhook integration or scheduled runners. The package declares no required credentials, tokens, or config paths that would be needed for remote hooks/CI setup, so there's a mismatch between the claimed capabilities and the declared requirements.
Instruction Scope
SKILL.md is instruction-only and largely descriptive; it does not show concrete, constrained runtime steps. A real runtime implementation would need to (a) scan the repo and commit history, (b) add or modify files (capsule payloads), and (c) possibly add CI workflows or webhook listeners to detect triggers. Those actions involve reading potentially sensitive files and writing persistent code into the repository; the instructions are open-ended and grant broad discretion without detailing safeguards (e.g., making changes via PRs, code review, or read-only discovery).
Install Mechanism
No install spec and no code files are present, so the skill itself won't drop binaries or archives on disk. This lowers supply-chain risk relative to skills that download and execute external code.
Credentials
The skill declares no required environment variables or credentials, but the described features (detecting new contributors, watching for dependency upgrades, integrating with CI or scheduled triggers) typically require access to repository metadata and/or CI tokens (e.g., GITHUB_TOKEN), or at least a mechanism to run on a scheduled basis. The absence of declared credentials is disproportionate to the capability and leaves unclear whether the skill will request or create secrets at runtime.
Persistence & Privilege
The skill does not set always:true, but its intended behavior implies writing persistent artifacts into the repository (capsule files, annotations, or CI/workflow files). That persistence can create long-lived functionality (e.g., workflows that run on push) and thus raises privilege concerns if the agent is allowed to commit or create workflow files without review. The SKILL.md does not describe safeguards (e.g., making changes via PRs rather than direct pushes).
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install time-capsule - After installation, invoke the skill by name or use
/time-capsule - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release
Metadata
Frequently Asked Questions
What is Time Capsule?
Write messages to your future self — or your future team — that unlock when specific code conditions are met. "Dear future me: if you're reading this, someon... It is an AI Agent Skill for Claude Code / OpenClaw, with 278 downloads so far.
How do I install Time Capsule?
Run "/install time-capsule" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Time Capsule free?
Yes, Time Capsule is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Time Capsule support?
Time Capsule is cross-platform and runs anywhere OpenClaw / Claude Code is available (darwin, linux, win32).
Who created Time Capsule?
It is built and maintained by John DeVere Cooley (@jcools1977); the current version is v1.0.0.
More Skills