How to turn X bookmarks into Claude Code skills

Use this process to turn a saved technical workflow into a Claude Code skill that you can inspect before installation. The process qualifies the bookmark, verifies its material claims, packages the supported procedure, tests its activation boundary, and requires approval for the exact version.

Qualify the bookmark

A bookmark is a good candidate when it contains a repeatable workflow, names a concrete outcome, and provides enough evidence to reconstruct the steps safely. A product announcement, opinion, news item, or isolated tip is normally not enough. XSkills skips those instead of manufacturing a process the source did not support.

A sequence another person could repeat.
Inputs, constraints, or tools that can be identified.
An outcome that can be checked rather than merely admired.
Claims that can be traced to the post or supporting sources.

Apply the complete X bookmark qualification rubric before you compile a candidate.

Turn the bookmark into a skill

Discover newly saved bookmarks through read-only X access. XSkills cannot post, reply, or alter the connected account.
Qualify each bookmark as a reusable AI or developer workflow. Stop processing low-signal saves.
Inspect relevant linked material and record the evidence for each instruction. State missing requirements instead of guessing.
Compile and grade the supported process as a Claude Code package with triggers, steps, guardrails, references, and evaluation queries.
Review the complete package and approve its exact checksum in Telegram or the dashboard. The macOS connector verifies every file before writing it to ~/.claude/skills.

Inspect the Claude Code package

Claude Code skills are filesystem artifacts centered on a SKILL.md file. Claude discovers skill metadata and loads the full content when the request matches. The official Claude Code guide describes the same file-based model and user/project skill locations. Read the Claude Code skills documentation.

multi-agent-review/
├── SKILL.md
├── manifest.json
├── eval_queries.json
└── references/
    ├── source.md
    └── research.md

SKILL.md defines when the skill should be used, the workflow, expected outputs, guardrails, and recovery behavior. The references keep the source and research attached. Evaluation queries record realistic prompts that should and should not activate the skill. The manifest binds the target harness, install root, and file hashes into one package.

Review a worked example

Imagine bookmarking a post that outlines a multi-agent review pattern: one planner, specialist reviewers, and a final judge using a shared rubric. The useful idea is not the post's engagement count or headline. It is the repeatable coordination pattern.

XSkills separates the pattern from unsupported performance claims, checks linked sources for the missing rubric and handoff details, and compiles only the instructions the evidence supports. The resulting skill can tell Claude Code when to use the pattern, what each role receives, how reviews are reconciled, and when the workflow should stop. You still decide whether that exact package belongs on your machine.

Approve the exact version

Approval is not a reusable permission for a skill name. It applies to the exact package you reviewed. If any instruction or file changes, the checksum changes and the revision needs a new approval. This prevents a later edit from silently inheriting trust granted to an earlier version.

Check the package before installation

Confirm the following requirements before you approve a skill:

The description states when the skill should and should not run.
Every material instruction traces to the bookmark or a reliable source.
The package labels assumptions, prerequisites, and unresolved claims.
The workflow includes expected outputs and stopping conditions.
The files do not contain unrelated commands, secrets, or hidden writes.
The displayed checksum matches the package you reviewed.

Inspect the sample X bookmark review skill to see a complete, instruction-only example.

See the full XSkills security model, learn what makes an agent skill different from a saved prompt, review the setup documentation, or compare the available plans.