$ ~/registry/skill/microsoft-skillify

SKILL

skillify

Name: skillify
Author: microsoft

Turn a repeated workflow into a reusable skill file from the current session.

Stars

★ 9

Source

GitHub

Updated

2026-07-09

// securityCaution

Prompt only, no code
Open source

Summary

This appears to be an open-source prompt-only skill with no required secrets and no declared remote endpoints. Its main capability is to analyze the current session and write a skill file to disk, so overall risk is low, with minor caution around local file writes and the session content being captured.

CredentialsLow risk

The material explicitly states that no keys or environment variables are required. There is no request for API tokens, account credentials, or other sensitive authentication data, so credential exposure and misuse risk is low.

Network egressLow risk

No remote endpoints or external service calls are declared. Based on the material, it mainly analyzes the current session locally and generates a SKILL.md file, with no factual indication of user data being sent to third parties.

Code executionLow risk

The system checks classify it as prompt-only. The documentation does not show it starting local processes, executing scripts, or requesting extra system capabilities. `load_skill("skills-assist")` appears to be an internal skill reference rather than arbitrary code execution.

Data accessCaution

This skill analyzes the current conversation and writes the generated SKILL.md to disk. That is within its stated purpose, but it still means it handles session content and creates local files, so the save path and written content should be reviewed.

Supply chainCaution

The source is an open-source GitHub repository, which improves auditability, and its placement under microsoft/amplifier-bundle-skills is a positive trust signal. However, the license is unspecified, community adoption is 0 stars, and maintenance status is unknown, so supply-chain confidence is only moderate and the repository should be reviewed before production use.

Recommendations

Confirm the output directory before use to avoid overwriting existing project files.
Review the generated SKILL.md to ensure it does not preserve sensitive session content, internal paths, or private context.
Inspect the linked GitHub repository and commit history before adopting it in a workflow.
For team or production use, verify the license status and maintenance activity first.

Audited by: gpt-5.4 · 2026-06-17

// install

Copy the install command and let the AI configure it · recommended for beginners

Please install the "skillify" skill from askskill:
1. Download https://raw.githubusercontent.com/microsoft/amplifier-bundle-skills/main/skills/skillify/SKILL.md
2. Save it as ~/.claude/skills/skillify/SKILL.md
3. Reload skills and tell me it's ready

// download

Download SKILL.mdInstall manifest ↗

// examples

Capture the current workflow as a skill

Prompt

Please turn the requirement breakdown and weekly report workflow we just completed into a reusable skill and save it as SKILL.md.

Expected

A complete skill file describing triggers, steps, inputs, outputs, and usage instructions.

Convert a repetitive process into a skill

Prompt

I want to make this customer research synthesis process into a skill. Extract the steps from this conversation, confirm the structure with me, then write the skill file.

Expected

It first drafts and confirms the workflow, then produces a skill definition file ready to save.

Create a new automation skill

Prompt

skillify: Save the document proofreading process we just repeated as a new skill so I can reuse it later.

Expected

A reusable skill file generated from the session, enabling faster execution of the same task later.

// docs

Skillify

Create a well-structured, reusable Amplifier SKILL.md skill file that captures a repeatable process from the current session so it can be invoked again later via /skill-name. The skill must conform to the Agent Skills specification with Amplifier extensions.

Inputs

$ARGUMENTS: (Optional) Description of the process to capture as a skill.

Steps

1. Consult Skills-Assist

Before writing any skill content, load the authoritative skills reference:

load_skill("skills-assist")

Ask skills-assist about:

Current frontmatter field reference and best practices
Fork vs inline decision criteria
Step annotation conventions
Testing patterns for the type of skill being created

skills-assist is the source of truth for Amplifier skill conventions. The examples in this skill are illustrative samples — consult skills-assist for the complete and up-to-date specification.

Success criteria: You have loaded and consulted skills-assist for the latest skill authoring conventions.

2. Analyze the Session

Before asking the user anything, analyze the conversation history to identify:

What repeatable process was performed
What the inputs and parameters were
The distinct steps in order
The success criteria and artifacts for each step (not just "writing code" but "an open PR with CI passing")
Where the user corrected or steered you — these are important design signals
What tools were used (read_file, write_file, bash, glob, grep, delegate, etc.)
What agents were delegated to
What the goals and measurable outcomes were

Success criteria: You have a clear mental model of the process, its steps, inputs, outputs, and success criteria.

3. Interview the User

Output density rule: Group related decisions into natural clusters — not one question per turn (tedious) and not everything at once (overwhelming). Present your analysis first, let the user absorb it, then ask related questions together. For example, present identity/routing decisions as one cluster, execution model decisions as another.

Calibrate interview depth to the complexity of the process. A simple 2-step workflow needs 1-2 rounds. A complex multi-step workflow with parallel tasks and irreversible actions needs the full treatment.

Round 1: High-level confirmation

Suggest a name and description for the skill based on your analysis. Ask the user to confirm or rename.
Suggest high-level goals and specific success criteria.
Present the high-level steps you identified as a numbered list.

Round 2: Details and arguments

If the skill needs arguments, suggest them based on what you observed.
Ask whether this skill should run inline (in the current conversation) or forked (context: fork) as an isolated subagent. Forked is better for self-contained tasks that don't need mid-process user input; inline is better when the user wants to steer mid-process.
Ask where the skill should be saved:
- This project (.amplifier/skills/<name>/SKILL.md) — project-specific
- Personal (~/.amplifier/skills/<name>/SKILL.md) — follows you across projects
- The skills bundle (amplifier-bundle-skills/skills/<name>/SKILL.md) — if contributing to the curated collection