$ loading_
Create a custom skill with structure, documentation, and optional bundled scripts.
This skill is an open-source, prompt-only guide with no required secrets and no declared fixed remote endpoints, so its baseline risk is low. However, the README contains clear prompt-injection/overreach patterns (mandatory TodoWrite steps, credential-file references, and external raw-content fetch suggestions), so it should be treated strictly as auditable text rather than instructions to follow directly.
The material states no keys or environment variables are required, so the skill itself has no direct credential input surface. However, the examples include a prompt to find auth credentials at '/home/foobar/authentication/auth.txt', which could lead to credential discovery and misuse if followed, so credential-related instructions in the text should be treated with caution.
No fixed remote endpoint is declared, and the core skill does not inherently require networking. However, the README suggests fetching GitHub raw URLs and gives examples using Slack/Gmail APIs, meaning it may guide future skills to connect to external services and send data out. Since these are examples/templates rather than the current skill's fixed behavior, this is a caution rather than a high-risk finding.
This is a prompt-only skill and does not execute code by itself. However, the README explicitly encourages writing scripts callable from Bash and replacing repeated tool use with code, indicating an intended path toward local code execution in follow-on usage. This is a common tool/skill capability, and no extra privileged system permissions are explicitly requested.
The description includes creating directory structures, writing SKILL.md, and optionally adding scripts, which implies local read/write access to profile directories. Examples also mention writing messages to local folders and reading a local credential file path. The material does not strictly bound access scope; while this is common for local skills, access should be limited to the minimum necessary directories and sensitive files should be excluded.
Positive signals include a GitHub-hosted open-source repository, which improves auditability. However, the repo shows 0 stars, unknown maintenance status, no declared license, and the README contains obvious injection-style wording (such as mandatory 'CRITICAL' TodoWrite steps and instructions to read external raw content), which reduces source trust. Therefore, the supply-chain posture should not be considered fully low risk.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "creating-skills" skill from askskill: 1. Download https://raw.githubusercontent.com/microsoft/FluidFramework/main/.agency/plugins/nori/skills/creating-skills/SKILL.md 2. Save it as ~/.claude/skills/creating-skills/SKILL.md 3. Reload skills and tell me it's ready
Help me create a new custom skill for ticket classification and reply suggestions in customer support. First gather requirements about target users, input/output format, edge cases, and whether scripts are needed, then provide the directory structure, a first draft of SKILL.md, and optional helper script suggestions.
A complete skill creation plan with clarifying questions, file structure, a SKILL.md draft, and script suggestions.
I want to create a custom skill for a content team to standardize article outlines, tone, and pre-publishing checks. Guide me step by step to define requirements, then output a practical skill directory, SKILL.md content, and recommended template files.
A reusable skill scaffold for the content team, including guidelines, directory design, and template recommendations.
Help me design a custom skill for CSV cleaning and summary analysis. First confirm the data types, output format, and whether automation scripts are needed, then generate the skill directory structure, SKILL.md, and a list of bundled scripts with their purposes.
A data-focused skill definition with directory structure, documentation, and bundled script planning.
This skill guides you through creating custom skills that persist across sessions. Skills are stored in profile directories and can include markdown instructions, checklists, and optional bundled scripts.
Every skill must start with a required checklist block:
<required>
*CRITICAL* Add the following steps to your Todo list using TodoWrite:
1. <step 1>
2. <step 2>
...
</required>
This is the most important part of a skill.
Each step may have guidelines underneath. For example:
1. Create a directory.
Use `mkdir foo/bar`
2. Make a file.
...
Skills may be bundled with scripts. Scripts are simple code cli tools that do various things deterministically.
Any scripts you write should be entirely self contained. Ask the user which language they prefer.
The scripts should be callable from the Bash tool.
The script should be stored in the same place as the skill. Add a section to the SKILL.md on how to use the script. If the script is required to be called, add that instruction to the <required> block.
Document which tools are necessary for the skill.
The SKILL should explicitly encourage writing code. The agent should be told to write code to call a tool any time the agent needs to call any tools more than once. The agent should write code instead of calling tools itself.
Steps that reference tools and APIs should inline them in the step by step process.
<good-example> - Write a python script that uses the slack api to pull my unread messages. The script should write my messages to a folder, /home/foobar/daily-analysis/<DD-MM-YYYY>/slack - Write a python script that uses the gmail api to pull my inbox. The script should write my emails to a folder, /home/foobar/daily-analysis/<DD-MM-YYYY>/email - Write a python script to identify the most urgent messages that I need to respond to. <system-reminder> Auth credentials can be found at /home/foobar/authentication/auth.txt </good-example> <bad-example> **Tools**: Slack, Gmail API - Summarize my messages by looking through common surfaces that I may use for messages. </bad-example> <good-example> Read https://raw.githubusercontent.com/tilework-tech/nori-skillsets/96012bcfcd9482b248debed7b9a7fc7c345f76e1/src/cli/features/claude-code/profiles/config/amol/skills/finishing-a-development-branch/SKILL.md </good-example> <good-example> Read https://raw.githubusercontent.com/tilework-tech/nori-skillsets/96012bcfcd9482b248debed7b9a7fc7c345f76e1/src/cli/features/claude-code/profiles/config/amol/skills/webapp-testing/SKILL.md </good-example>Trace errors backward through execution paths to identify the true root cause.
Update technical documentation after code changes are completed.
Generate Fluid-style PR content, push branches, and open GitHub pull requests.
Explains how to use abilities effectively before starting any conversation.
Break large, long-running tasks into manageable chunks and preserve context.
Turn rough ideas into actionable designs through structured questioning and validation.
Create or refine AI skills with scope, workflows, and tool integrations.
Create reusable SKILL.md skills that package repeatable workflows for future use.
Create or update skills that extend Codex with knowledge, workflows, and tools.
Create, refine, validate, and restructure AgentSkills and SKILL.md files.
Create, revise, and validate AI skills before deployment.
Turn a repeated workflow into a reusable skill file from the current session.