loading-addressable-markdown — Claude Code skill: addressable
Pulls exactly one Markdown section out of a filesystem tree by an address like file.md#h2-slug. Handy when a task points at a spec section instead of a whole file.
npx skills add mvschwarz/openrig --skill loading-addressable-markdown -a claude-codeWhat loading-addressable-markdown does
The skill parses file.md#h2-slug or file.md#h2-slug/h3-slug and returns the full heading span, child sections included. Slugs are lowercased, emphasis and code markers are stripped from the heading, and every other non-alphanumeric run collapses to -. Headings inside fenced code blocks are skipped, so examples in triple backticks will not confuse the parse.
It runs the bundled scripts/resolve-markdown.mjs. Relative paths resolve from --root, and without it from the current directory. Duplicate or missing paths fail loudly rather than silently returning something. Quote the address in your shell, or the # starts a comment.
rig context get is the wrong tool for an arbitrary disk path — that command resolves context-library refs. Hand-slicing headings with sed or line numbers is out too, since the resolver owns span and fence behavior.
What it helps with
- pull a single SPEC.md section by heading slug
- read an H3 nested in an H2 without opening the whole file
- point an agent task at one spec section
- catch a duplicated or missing address before it spreads
- parse headings without tripping over fenced code examples
Example prompts for the agent
- load the section
slices/09-source-cleanup/SPEC.md#proposal - read
docs/SPEC.md#api/errorsand show me what's there - resolve
SPEC.md#proposalfrom the mission root
How to install loading-addressable-markdown
1Skills CLI (Vercel)
npx skills add mvschwarz/openrig --skill loading-addressable-markdown -a claude-code2Manually: put the files in place
~/.claude/skills/loading-addressable-markdown/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/loading-addressable-markdown/
1Skills CLI (Vercel)
npx skills add mvschwarz/openrig --skill loading-addressable-markdown -a codex2Manually: put the files in place
.agents/skills/loading-addressable-markdown/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add mvschwarz/openrig --skill loading-addressable-markdown -a cursor2Manually: put the files in place
.cursor/skills/loading-addressable-markdown/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install mvschwarz/openrig loading-addressable-markdown2Manually: put the files in place
.github/skills/loading-addressable-markdown/SKILL.md1Skills CLI (Vercel)
npx skills add mvschwarz/openrig --skill loading-addressable-markdown -a gemini-cli2Platform CLI
gemini skills install https://github.com/mvschwarz/openrig --path packages/daemon/assets/plugins/openrig-core/skills/loading-addressable-markdownManually: put the files in place
.devin/skills/loading-addressable-markdown/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add mvschwarz/openrig --skill loading-addressable-markdown -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about loading-addressable-markdown
How do I install loading-addressable-markdown in Claude?
Run npx skills add mvschwarz/openrig --skill loading-addressable-markdown -a claude-code. The skill lands in ~/.claude/skills/loading-addressable-markdown/SKILL.md.
What does loading-addressable-markdown do?
It loads one addressed Markdown section from any filesystem tree using the H2/H3 grammar, without requiring the file to live in the OpenRig context library.
How is it different from rig context get?
rig context get resolves context-library refs. For an arbitrary disk path you want this resolver, which owns span and fence behavior itself.
Source text
SKILL.md · Apache-2.0
--- name: loading-addressable-markdown description: Use when a mission, slice, dashboard, or task references Markdown as path#h2-slug or path#h2-slug/h3-slug outside the OpenRig context-pack library. --- # Loading Addressable Markdown ## Overview Load exactly one addressed Markdown section from any filesystem tree. The resolver mirrors OpenRig's shipped H2/H3 grammar without requiring the file to live in the context library. ## Use Run the bundled script. Relative file references resolve from `--root`; without it they resolve from the current directory. ```bash node ~/.agents/skills/loading-addressable-markdown/scripts/resolve-markdown.mjs \ --root /path/to/mission \ 'slices/09-source-cleanup/SPEC.md#proposal' ``` The accepted forms are: - `file.md` — whole file - `file.md#h2-slug` — full H2 span, including child sections - `file.md#h2-slug/h3-slug` — full H3 span Slugs are lowercase; Markdown emphasis/code markers are removed; each other non-alphanumeric run becomes `-`. Duplicate or missing paths fail loudly. Headings inside fenced code blocks are ignored. ## Common mistakes - Do not use `rig context get` for an arbitrary filesystem path; that command resolves context-library refs. - Do not hand-slice headings with `sed` or line numbers; the bundled resolver owns span and fence behavior. - Quote addresses in shell commands.
© mvschwarz · Apache-2.0 · mvschwarz/openrig
