Automated summary
This skill describes how to hand a task off to one or more subagents so that context in the main Cathode thread stays small.
Strengths
- Clearly splits the work: the subagent does all code exploration, while the main thread only supplies the problem statement and relevant context
- Names concrete orientation entry points (`/generic_context`, `backend_schema.yaml`, `frontend_schema.yaml`) so subagents avoid re-reading the whole repo
- Provides a well-scoped example use case: delegating test writing after a feature is implemented
- Defaults to a named model (Composer 2.5) while still allowing a different one to be chosen
Limitations
- Tightly coupled to the Cathode environment and its schema files, so it does not transfer cleanly to other projects
- Only runs when the user explicitly invokes it; there is no automatic triggering
- It is purely a method guideline — no tooling, script, or check verifies that delegation actually happened
Use it when a task can be isolated and handed to a subagent to keep the main thread from bloating, such as writing tests or exploring code.
Avoid it for tasks that need tight back-and-forth with the user or deep awareness of the main thread, since the context passed to the subagent would then be too partial.
Security analysis
SafeThe skill only provides guidance for delegating work to subagents and referencing internal schema/context files. It does not instruct destructive commands, network calls, secret exfiltration, or safety bypasses.
No concerns found
How this analysis is madeExamples
Use save_context_task: I've just implemented the invoice export endpoint — have a subagent write the unit tests so my main thread stays lean.save_context_task — delegate exploring how the checkout flow handles refunds to a subagent, pointing it at /generic_context and backend/backend_schema.yaml.Use save_context_task to have a subagent trace where the order status badge is rendered, starting from cathode-frontend/frontend_schema.yaml.name: save_context_task description: Instructions for creating a subtask in a way that saves context in Cathode
When to Use
- Use this skill only when invoked by the user
Instructions
- When invoked, the user wants you to complete the task using subagent(s) (Composer 2.5 unless otherwise specified) to save context in the main thread.
- All code exploration should be done by the subagent. Provide the problem description and relevant context from your thread.
- Point subagents at
/generic_contextor the relevant schema file (backend/backend_schema.yaml,cathode-frontend/frontend_schema.yaml) so they orient quickly without re-reading the whole repo. - Example: after implementing a feature, delegate writing tests to a subagent — narrow scope, but setup exploration would bloat the main thread.
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/save-context-via-subagent-mrwakcvr/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/save-context-via-subagent-mrwakcvr' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/save-context-via-subagent-mrwakcvr/download' --output '.skill-downloads/save-context-via-subagent-mrwakcvr/SKILL.md.part' && mv '.skill-downloads/save-context-via-subagent-mrwakcvr/SKILL.md.part' '.skill-downloads/save-context-via-subagent-mrwakcvr/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
This file does not provide a usable name/description header for this native procedure. It remains available to download and inspect; use the manual method below.
Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/save-context-via-subagent-mrwakcvr/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
PDF Reader
Productivity
Read and extract text from PDF files, including documents, reports, contracts, and spreadsheets. Works with local files, URLs, and WhatsApp attachments. Use whenever PDF content is needed, even if not explicitly requested.
Discord Messaging Workflows
Productivity
Use the message tool to send, edit, and moderate Discord messages with interactive components.
Interactive Verdict Preview
Productivity
Generate an interactive HTML preview of keep/drop verdicts for maintainer review, then process the pasted feedback JSON.