ワンクリックで
markdown-to-skill
Convert Markdown files from a directory into agent skills.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
メニュー
Convert Markdown files from a directory into agent skills.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Write an implementation plan to docs/plans/. ALWAYS use this skill — never hand-roll a plan by mimicking files in docs/. Use when the user wants to create a project/implementation plan, when a plan discussed in chat should be persisted, or says /project-plan. Guarantees a spec exists, invoking to-spec if absent. Decomposes into vertical slices with Blocked-by edges, points to the spec for acceptance criteria, and extracts ADRs via to-adr.
Parse test failure output and diagnose root causes in a read-only background subagent, then fix the failures interactively in the main thread. Use when the user shares test output or says "tests fail". Default output path is /tmp/output.
Surface systemic patterns from an investigation as codified conventions or anti-patterns.
Architect a change from idea to actionable artifacts — bootstrap project instructions, research deeply, write a spec, then an implementation plan, each delegated to its skill. Use when the user wants to research a topic, explore a repo, write a spec, create a project plan, or says /architect.
Research a topic or repository deeply and produce a reference document under `docs/research/`. Handles two modes: code research (repo by URL, `org/repo`, or bare name — e.g. "check the spotless repo", "look at github.com/fastly/spotless") and topic research (concepts, technologies, patterns). Use when the user wants to research something, explore a repo, or says /research.
Elicit the user's intent before starting work. Use when a request is vague, when kicking off a new task, when another skill hits a vague request and needs to clarify it, or when the user says "help me with this", "I need something", "let's work on...", "draft a task", or /task.
| name | markdown-to-skill |
| description | Convert Markdown files from a directory into agent skills. |
| disable-model-invocation | true |
Convert Markdown files from a user-specified directory into valid agent skills, written to one of two locations:
~/.agents/skills/
or ~/.claude/skills/); available in all projects..agents/skills/ or
.claude/skills/); available only in this project.Ask the user:
.), docs/, or other
(let the user specify).Before scanning, use ls/Glob to check the source for
website-scoped subdirectories: top-level dirs that look like domain
names (contain ., e.g. docs.example.com). If found, skill names get
a scope prefix derived from the domain (see Step 5).
Glob for **/*.md recursively. Exclude files that are already
SKILL.md.
Show a table of source path, proposed skill name (with scope prefix if applicable), and conflict status. Ask the user to confirm before proceeding.
| Source File | Skill Name | Status |
|--------------------------------------------|-------------------------|-------------------------|
| guides/my-guide.md | my-guide | Will create |
| setup.md | setup | Conflict: skill exists |
| docs.fastly.com/guides/getting-started.md | fastly-docs:getting-started | Will create |
Skip conflicts unless the user confirms overwrite. For each file:
Derive skill name. Strip .md, lowercase, replace spaces and
underscores with hyphens (My_Guide File.md -> my-guide-file).
guides/setup.md -> setup).<scope>:<filename>
(docs.fastly.com/guides/getting-started.md ->
fastly-docs:getting-started). Scope derivation:
docs.X.com or X.docs.com -> X-docswww.X.com -> X-wwwdeveloper.X.org -> X-developerapi.github.com -> github-apiExtract description. Prefer an existing frontmatter
description. Otherwise use the first # Heading (or, if none, the
first non-empty paragraph) as the basis, truncated to ~100 chars. If
empty, default to Skill converted from <original-filename>.
Strip existing frontmatter (if the file starts with ---) and
replace with skill frontmatter.
Create the skill directory under the chosen destination:
<skills-dir>/<skill-name>/.
Write SKILL.md:
---
name: <skill-name>
description: <extracted-description>
---
<original content, minus old frontmatter>
Report the destination, count of skills created, files skipped (with
reasons, e.g. conflicts), errors, and the list of new skills (invokable
as /<skill-name>, e.g. /fastly-docs:getting-started).
| Source | Skill property |
|---|---|
Filename (my-guide.md) | name: my-guide |
| Domain dir + filename | name: scope:filename (e.g. fastly-docs:my-guide) |
First # Heading or first paragraph | description (max ~100 chars) |
| Full file content (minus old frontmatter) | Body of SKILL.md |
fastly-docs:api vs fastly-www:api).Skill converted from <original-filename>.Source docs/deployment-guide.md:
---
author: Jane Doe
date: 2024-01-15
---
# Deploying to Production
This guide covers the steps to deploy our application to production.
...
Output <skills-dir>/deployment-guide/SKILL.md:
---
name: deployment-guide
description: Deploying to Production - This guide covers the steps to deploy our application to production.
---
# Deploying to Production
This guide covers the steps to deploy our application to production.
...
With website scoping, docs.fastly.com/guides/getting-started.md
becomes <skills-dir>/fastly-docs:getting-started/SKILL.md with
name: fastly-docs:getting-started, invoked as
/fastly-docs:getting-started.