Automated summary
Guides the creation or editing of an agent skill stored as a YAML file embedded under pkg/agent/skills/ in a Go repository.
Strengths
- Recalls repository conventions (name, sections, auto_activation, priority) before any writing
- Requires reading existing skills and prompt.go first, which prevents duplication and drift
- Explains the deterministic port/service section filtering, the easiest detail to get wrong
- Ends with a concrete verification step using go build ./pkg/agent/
Limitations
- Tightly coupled to one repository layout, so it is not portable as-is
- Gives no guidance on the actual prose of sections or on phrasing for the LLM
- Assumes the agent can already read Go code and understands //go:embed
Use it when adding or revising a YAML skill in pkg/agent/skills/ while matching the project's format and filtering rules.
Skip it when authoring a skill for another framework or when documenting code that is not an embedded skill registry.
Security analysis
SafeThe skill is a repository-specific authoring guide for creating/editing YAML skill definitions. It references reading files and running `go build`, but contains no destructive commands, credential access, network exfiltration, obfuscation, or safety-disabling instructions.
No concerns found
How this analysis is madeExamples
Create a new skill in pkg/agent/skills/ that activates on the 'database' discovery category and covers Postgres port 5432. Read the existing skills first to avoid overlap.Our new skill's section never shows up. Check how sections are filtered by port/service in pkg/agent/prompt.go and fix the YAML patterns.Add a disk override for the existing 'http-probe' skill in pkg/agent/skills/ and confirm it still builds with go build ./pkg/agent/.Create or edit an agent skill: $ARGUMENTS
Context
Agent skills live in pkg/agent/skills/ as YAML files embedded at build time via //go:embed.
Disk skills in the same directory override embedded ones by name for customization.
Before Writing
- Read existing skills in
pkg/agent/skills/to understand the format and conventions. - Read
pkg/agent/prompt.goto understand how skills are referenced in the agent prompt. - Check how skills are loaded and filtered — skills have sections filtered by port/service (deterministic string match).
Skill YAML Structure
Key fields to understand:
- name — unique identifier, referenced by LLM
- sections — filtered by port/service match
- auto_activation — triggers on discovery categories
- priority — lower number = higher priority
Guidelines
- Skills should be generic enough to apply across target types where possible.
- Section filtering is deterministic string matching — be precise with service/port patterns.
- Auto-activation triggers should map to discovery categories from
report_discoverytool. - Test that the skill loads correctly:
go build ./pkg/agent/ - Read the 14 existing skills before creating a new one to avoid overlap.
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/create-or-edit-an-agent-skill-mts7ilbw/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/create-or-edit-an-agent-skill-mts7ilbw' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/create-or-edit-an-agent-skill-mts7ilbw/download' --output '.skill-downloads/create-or-edit-an-agent-skill-mts7ilbw/SKILL.md.part' && mv '.skill-downloads/create-or-edit-an-agent-skill-mts7ilbw/SKILL.md.part' '.skill-downloads/create-or-edit-an-agent-skill-mts7ilbw/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/create-or-edit-an-agent-skill-mts7ilbw/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.