Automated summary
Guides the creation of a new Relay investigation skill pack made of a strictly read-only probe.sh and a SKILL.md documenting frontmatter, inputs, and an interpretation guide.
Strengths
- Requires a grep check proving the probe contains no mutating AWS calls (create/update/delete/put/start/stop).
- Mandates that each probe section be independently wrapped so one failure does not abort the rest of the collection.
- Frames interpretation as evidence-backed hypotheses rather than confirmed root causes, leaving the decision to the human.
- Scopes every time-range parameter to RELAY_WINDOW_MINUTES (default 60) instead of unbounded queries.
Limitations
- Relies on an external prompts/author-skill.md file whose contents are not included.
- Assumes solid bash skills and familiarity with AWS CLI describe/list/get commands.
- Read-only compliance is only checked by a manual grep, with no automated validation.
Use it when you need to add a new runtime investigation skill pack to a Relay node's skills/ directory.
Do not use it to edit an existing skill, to run a probe against real infrastructure, or for non-AWS resources.
Security analysis
SafeThe skill instructs authoring a read-only probe script and SKILL.md, explicitly forbids mutating AWS CLI calls, requires graceful degradation, bounded time windows, and no PII. It does not execute destructive commands, exfiltrate secrets, or disable safety controls.
No concerns found
How this analysis is madeExamples
Add a new Relay investigation skill for ECS service health: probe running vs desired task count, recent deployment events, and task stop reasons using only read-only AWS CLI calls, with an interpretation guide framed as hypotheses.Create a Relay skill for RDS incidents that probes instance status, recent events, and pending maintenance scoped to RELAY_WINDOW_MINUTES, and write the SKILL.md frontmatter, inputs, and interpretation section.Write a new read-only probe.sh plus SKILL.md that helps triage Lambda error spikes: list recent invocations and errors within RELAY_WINDOW_MINUTES, wrap each section independently, and verify no mutating AWS calls remain.description: Add a new Relay AI investigation skill — write a read-only probe.sh and a SKILL.md with frontmatter, inputs, and interpretation guide.
You are helping the user add a new runtime AI investigation skill pack to the skills/ directory. Each skill is a directory with a SKILL.md (frontmatter + when-to-use + inputs + probe invocation + interpretation guide) and a read-only probe.sh (bash script wrapping AWS CLI describe/list/get calls). Skills are mounted into the node's headless AI triage agent at incident time.
Read and follow prompts/author-skill.md in this repo for the exact structure, script skeleton, and verification steps.
Relay-specific reminders:
probe.shmust be strictly read-only: onlydescribe*/list*/get*/lookup-events/filter-log-eventsAWS CLI calls. Never a mutating call. Verify withgrepfor create/update/delete/put/start/stop patterns.- Each section of the probe must be independently wrapped so one failing section does not abort the rest — degrade gracefully.
- The
SKILL.mdinterpretation section must frame findings as hypotheses with evidence, never as confirmed root causes. The human decides. - Use
RELAY_WINDOW_MINUTES(default 60) for all time-range parameters — never fan out to unbounded time ranges. - Skills probe infrastructure state only — no PII in probe output or in
SKILL.mdexamples.
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/relay-ai-investigation-skill-pack-mrx3y08s/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/relay-ai-investigation-skill-pack-mrx3y08s' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/relay-ai-investigation-skill-pack-mrx3y08s/download' --output '.skill-downloads/relay-ai-investigation-skill-pack-mrx3y08s/SKILL.md.part' && mv '.skill-downloads/relay-ai-investigation-skill-pack-mrx3y08s/SKILL.md.part' '.skill-downloads/relay-ai-investigation-skill-pack-mrx3y08s/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/relay-ai-investigation-skill-pack-mrx3y08s/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.
React Hook Form Best Practices
Development
Master React Hook Form: avoid anti-patterns, manage subscriptions, and handle reset, dirty state, and controlled inputs correctly.
Emotion to Mantine Migration
Development
Migrate Emotion styled-components to Mantine components with style props and CSS modules. Use when converting .styled.tsx files or removing @emotion imports.
Scope Creep Detector
Development
Analyzes git diffs against a stated intent to detect scope creep, unrelated files, broad PRs, and oversized changes, then suggests keep, split, or justify actions.