Custom Element Accessibility
thedaviddias/Front-End-Checklist
A skill your agent uses when reviewing custom element class definitions or Web Component source code to check for missing ARIA reflection, keyboard handling, and form association.
Understand and manipulate Unstructured Element classes, metadata, coordinates, data-source metadata, staging conversions, and bundled inspection helpers.
Apache-2.0Auto-check passed
Install Elements And Metadata
$ npx skills add VectorSpaceLab/AREX-Skill --skill elements-and-metadata -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill elements-and-metadata --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/repositories/repo-skills/unstructured/sub-skills/elements-and-metadata .claude/skills/elements-and-metadata && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "elements-and-metadata" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/unstructured/sub-skills/elements-and-metadata into .claude/skills/elements-and-metadata/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "elements-and-metadata", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/unstructured/sub-skills/elements-and-metadataType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add VectorSpaceLab/AREX-Skill --skill elements-and-metadata -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill elements-and-metadata --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/repositories/repo-skills/unstructured/sub-skills/elements-and-metadata .agents/skills/elements-and-metadata && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "elements-and-metadata" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/unstructured/sub-skills/elements-and-metadata into .agents/skills/elements-and-metadata/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "elements-and-metadata", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add VectorSpaceLab/AREX-Skill --skill elements-and-metadata -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill elements-and-metadata --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/repositories/repo-skills/unstructured/sub-skills/elements-and-metadata .cursor/skills/elements-and-metadata && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "elements-and-metadata" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/unstructured/sub-skills/elements-and-metadata into .cursor/skills/elements-and-metadata/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "elements-and-metadata", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/VectorSpaceLab/AREX-Skill.git --path skills/repositories/repo-skills/unstructured/sub-skills/elements-and-metadata--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add VectorSpaceLab/AREX-Skill --skill elements-and-metadata -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill elements-and-metadata --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/repositories/repo-skills/unstructured/sub-skills/elements-and-metadata .gemini/skills/elements-and-metadata && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "elements-and-metadata" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/unstructured/sub-skills/elements-and-metadata into .gemini/skills/elements-and-metadata/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "elements-and-metadata", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install VectorSpaceLab/AREX-Skill elements-and-metadataInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add VectorSpaceLab/AREX-Skill --skill elements-and-metadata -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/repositories/repo-skills/unstructured/sub-skills/elements-and-metadata .github/skills/elements-and-metadata && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "elements-and-metadata" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/unstructured/sub-skills/elements-and-metadata into .github/skills/elements-and-metadata/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "elements-and-metadata", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add VectorSpaceLab/AREX-Skill --skill elements-and-metadata -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill elements-and-metadata --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/repositories/repo-skills/unstructured/sub-skills/elements-and-metadata .opencode/skills/elements-and-metadata && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "elements-and-metadata" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/unstructured/sub-skills/elements-and-metadata into .opencode/skills/elements-and-metadata/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "elements-and-metadata", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
elements-and-metadata- GitHub stars
- 331
- Token cost
- ~1.3k tokens
- SKILL.md length
- 450 words
- Files
- 6 (incl. scripts, references)
- Skills in repo
- 157
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Understand and manipulate Unstructured Element classes, metadata, coordinates, data-source metadata, staging conversions, and bundled inspection helpers.
- Works in 6 steps: Load JSON with elements_from_json() or… → Confirm each element has a supported… → Inspect metadata sparsely: missing keys… → …
- Inspecting partition output JSON
- SKILL.md covers Core Model, Staging and Conversion, Table Fidelity and Coordinates, plus 2 more sections
- Runs Python scripts from its folder; calls python
What it does
Elements And Metadata is an agent skill from VectorSpaceLab/AREX-Skill. Understand and manipulate Unstructured Element classes, metadata, coordinates, data-source metadata, staging conversions, and bundled inspection helpers. Use when inspecting partition output JSON, preserving table metadata or coordinates, or converting element JSON to JSON, NDJSON, Markdown, text, or HTML; route raw document partitioning to partitioning and chunk composition to chunking.
Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files, including scripts and reference files (for example `references/element-schema.md`, `references/staging-formats.md` and `references/troubleshooting.md`).
The repository describes itself as: A Skill Library for Automated Machine Learning. The licence is Apache-2.0.
When your agent uses it
- Inspecting partition output JSON
- Preserving table metadata
- Converting element JSON to JSON
- Route raw document partitioning to partitioning and chunk composition to chunking
Example prompts
- “/elements-and-metadata”
Requirements
- Python 3
Workflow steps
6 steps, taken from the first numbered list in SKILL.md.
- Load JSON with elements_from_json() or scripts/convert_elements_json.py --inspect to catch malformed JSON early.
- Confirm each element has a supported type; unknown text-like types may be dropped by elements_from_dicts() if they are not mapped.
- Inspect metadata sparsely: missing keys often mean unset fields, not failed serialization.
- For coordinates, verify points and system are both present and that layout_width/layout_height match the originating page or image.
- For tables, compare text, metadata.text_as_html, and metadata.table_as_cells before and after conversion.
- For oversized orig_elements, image payloads, or compressed metadata, watch base64/gzip limits and prefer exclude_binary_image_data=True…
What it can do on your machine
Read from SKILL.md and the folder at commit ac3fe1a. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 2 files in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
python
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Elements And Metadata loads about 1.3k tokens when it runs, and up to ~5.3k if it reads all its reference files. Until then it costs about 103 tokens; SKILL.md has 450 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
SKILL.md
The full file from VectorSpaceLab/AREX-Skill at commit ac3fe1a, republished under its Apache-2.0 licence (© VectorSpaceLab). 450 words, ~1,266 tokens.
Download SKILL.mdSave it as
.claude/skills/elements-and-metadata/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.- name
- elements-and-metadata
- description
- Understand and manipulate Unstructured Element classes, metadata, coordinates, data-source metadata, staging conversions, and bundled inspection helpers. Use when inspecting partition output JSON, preserving table metadata or coordinates, or converting element JSON to JSON, NDJSON, Markdown, text, or HTML; route raw document partitioning to partitioning and chunk composition to chunking.
- disable-model-invocation
- true
- metadata.disco-role
- operating
- license
- Apache 2.0
Elements and Metadata
Use this sub-skill when a task starts from already-partitioned Unstructured elements or element JSON and needs schema inspection, metadata debugging, coordinate reasoning, or format conversion. Do not use it to partition source documents or compose chunks.
Core Model
- Elements are instances of
unstructured.documents.elements.Elementsubclasses such asTitle,NarrativeText,ListItem,Table,TableChunk,Image,Formula,CheckBox,CompositeElement,Header,Footer, andText. - Serialized element dictionaries generally use
type,element_id,text, andmetadata;CheckBoxalso useschecked, while text elements may includeembeddings. ElementMetadatais sparse: unset fields are omitted fromto_dict()and JSON output. Unknown ad-hoc metadata can exist, but known fields should be preferred for portable workflows.CoordinatesMetadatarequires bothpointsandsystem; one without the other is invalid. Coordinate dictionaries includepoints,system,layout_width, andlayout_height.DataSourceMetadatalives undermetadata.data_sourceand supports source-level fields such asurl,version,record_locator, dates, and permissions.
See references/element-schema.md for concrete JSON examples and metadata field guidance.
Staging and Conversion
For in-process conversion, prefer unstructured.staging.base:
from unstructured.staging.base import elements_from_json, elements_to_json, elements_to_md
elements = elements_from_json(filename="elements.json")
markdown = elements_to_md(elements, exclude_binary_image_data=True)
json_text = elements_to_json(elements, indent=2)For command-line use, use the bundled helpers:
python sub-skills/elements-and-metadata/scripts/convert_elements_json.py elements.json --format markdown --output out.md
python sub-skills/elements-and-metadata/scripts/convert_elements_json.py elements.json --format ndjson --output out.ndjson
python sub-skills/elements-and-metadata/scripts/render_elements_html.py elements.json --output rendered.htmlSee references/staging-formats.md for JSON, NDJSON, Markdown, text, and HTML behavior.
Table Fidelity
- Preserve
metadata.text_as_htmlwhenever table structure matters; Markdown and HTML conversion can use it for richer table output than plainelement.text. - Preserve
metadata.table_as_cells,table_id,chunk_index, andnum_carried_over_header_rowswhen reconstructing or validating split tables. - Compact table HTML normalizes whitespace and strips cosmetic attributes, while preserving structural
rowspanandcolspan. - When converting or filtering element JSON, check that
TableandTableChunkelements retain both text and structural metadata.
Show full SKILL.md (204 more words)Show less
Coordinates
RelativeCoordinateSystemuses width and height1;PixelSpaceis screen-oriented with origin at the upper-left;PointSpaceis Cartesian with origin at the lower-left.- Conversion between coordinate systems may invert the y-axis depending on orientation. Use
element.convert_coordinates_to_new_system(new_system, in_place=False)to inspect without mutation. - JSON round-trips should preserve all four coordinate fields. Missing
layout_widthorlayout_heightcan prevent rehydrating concrete coordinate systems.
Debugging Flow
- Load JSON with
elements_from_json()orscripts/convert_elements_json.py --inspectto catch malformed JSON early. - Confirm each element has a supported
type; unknown text-like types may be dropped byelements_from_dicts()if they are not mapped. - Inspect
metadatasparsely: missing keys often mean unset fields, not failed serialization. - For coordinates, verify
pointsandsystemare both present and thatlayout_width/layout_heightmatch the originating page or image. - For tables, compare
text,metadata.text_as_html, andmetadata.table_as_cellsbefore and after conversion. - For oversized
orig_elements, image payloads, or compressed metadata, watch base64/gzip limits and preferexclude_binary_image_data=Truewhen rendering.
See references/troubleshooting.md for failure modes and fixes.
Boundaries
- Raw document partitioning belongs to the
partitioningsub-skill. - Chunking,
CompositeElement,TableChunkcomposition, and chunk metadata consolidation belong to thechunkingsub-skill unless the task is only inspecting existing chunk JSON. - Review/test artifacts should not be added to this runtime subtree.
© VectorSpaceLab, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 5 other files (scripts, references) in skills/repositories/repo-skills/unstructured/sub-skills/elements-and-metadata of VectorSpaceLab/AREX-Skill.
- SKILL.md
- references/element-schema.md
- references/staging-formats.md
- references/troubleshooting.md
- scripts/convert_elements_json.py
- scripts/render_elements_html.py
Open the folder on GitHubat commit ac3fe1a
Compare with similar skills
Elements And Metadata next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Elements And Metadata this skillVectorSpaceLab/AREX-Skill | 331 | — | ~1.3k | Automated safety check: Pass | Apache-2.0 | |
| Custom Element Accessibilitythedaviddias/Front-End-Checklist | 74k | — | ~655 | Automated safety check: Pass | MIT | |
| Agent Adaptive Coordinatorruvnet/ruflo | 74k | 2 repos | ~4k | Automated safety check: Pass | MIT | |
| Agent Consensus Coordinatorruvnet/ruflo | 74k | 2 repos | ~3.2k | Automated safety check: Pass | MIT | |
| Agent Hierarchical Coordinatorruvnet/ruflo | 74k | 2 repos | ~2.8k | Automated safety check: Pass | MIT | |
| Agent Memory Coordinatorruvnet/ruflo | 74k | 2 repos | ~1.2k | Automated safety check: Pass | MIT |
Similar skills
Agent Adaptive Coordinator
ruvnet/ruflo
Agent skill for adaptive-coordinator - invoke with $agent-adaptive-coordinator
Agent Consensus Coordinator
ruvnet/ruflo
Agent skill for consensus-coordinator - invoke with $agent-consensus-coordinator
Agent Hierarchical Coordinator
ruvnet/ruflo
Agent skill for hierarchical-coordinator - invoke with $agent-hierarchical-coordinator
Agent Memory Coordinator
ruvnet/ruflo
Agent skill for memory-coordinator - invoke with $agent-memory-coordinator
Agent Mesh Coordinator
ruvnet/ruflo
Agent skill for mesh-coordinator - invoke with $agent-mesh-coordinator
More from VectorSpaceLab/AREX-Skill
All 157 skills in this repoAgent Lightning
VectorSpaceLab/AREX-Skill
Use this repo skill for Agent Lightning package tasks: authoring trainable agents, tracing rewards and spans, running LightningStore/Trainer loops, using agl CLI services, choosing examples, and…
Agent Tools
VectorSpaceLab/AREX-Skill
A skill your agent uses when configuring LiteLLM for MCP tools, A2A agents, Claude Code/Cursor agent gateway traffic, MCP auth/OAuth, tool permissions, semantic filtering, or agent-specific proxy…
Agents And Awel
VectorSpaceLab/AREX-Skill
Build and debug DB-GPT agents, tools, skills, teams, and AWEL workflows, including deterministic local DAG runs and HTTP-trigger topology without assuming an LLM, credential, or external service.
Agents And Middleware
VectorSpaceLab/AREX-Skill
Work on the actively maintained LangChain v1 agent package: initchatmodel, createagent, structured output, tools, middleware, embeddings initialization, provider routing, and agent runtime…
Agents Workflows
VectorSpaceLab/AREX-Skill
A skill your agent uses for giskard.agents async chat workflows, tools, prompt templates, structured outputs, retries, rate limiting, embeddings, and optional LiteLLM backend.
Alphafold3
VectorSpaceLab/AREX-Skill
A skill your agent uses for AlphaFold 3 input preparation, prediction command planning, output interpretation, and Python API inspection.
Questions about Elements And Metadata
What does Elements And Metadata do?
Understand and manipulate Unstructured Element classes, metadata, coordinates, data-source metadata, staging conversions, and bundled inspection helpers. Elements And Metadata is an agent skill from VectorSpaceLab/AREX-Skill. Understand and manipulate Unstructured Element classes, metadata, coordinates, data-source metadata, staging conversions, and bundled inspection helpers.
When should I use Elements And Metadata?
Elements And Metadata fits situations like: inspecting partition output JSON; preserving table metadata; converting element JSON to JSON; route raw document partitioning to partitioning and chunk composition to chunking.
How do I install Elements And Metadata in Claude Code?
Run `npx skills add VectorSpaceLab/AREX-Skill --skill elements-and-metadata -a claude-code`. Or copy the skill folder (skills/repositories/repo-skills/unstructured/sub-skills/elements-and-metadata in VectorSpaceLab/AREX-Skill) into .claude/skills/elements-and-metadata in your project. Claude Code loads it when a task matches its description.
How do I install Elements And Metadata in Codex?
Run `npx skills add VectorSpaceLab/AREX-Skill --skill elements-and-metadata -a codex`. Or copy the skill folder (skills/repositories/repo-skills/unstructured/sub-skills/elements-and-metadata in VectorSpaceLab/AREX-Skill) into .agents/skills/elements-and-metadata in your project. Codex loads it when a task matches its description.
Can I use Elements And Metadata in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add VectorSpaceLab/AREX-Skill --skill elements-and-metadata -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/elements-and-metadata, .gemini/skills/elements-and-metadata, .github/skills/elements-and-metadata and .opencode/skills/elements-and-metadata in your project.
What does Elements And Metadata need to run?
Going by SKILL.md and its folder, Elements And Metadata needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python 3.
Does Elements And Metadata access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Elements And Metadata safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Elements And Metadata use?
Elements And Metadata is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Elements And Metadata use?
About 1.3k tokens (SKILL.md is roughly 5.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 4k tokens, read only when the agent opens those files.
What are the alternatives to Elements And Metadata?
Skills that share tags, products or a category with Elements And Metadata: Custom Element Accessibility (thedaviddias/Front-End-Checklist, 74k stars), Agent Adaptive Coordinator (ruvnet/ruflo, 74k stars), Agent Consensus Coordinator (ruvnet/ruflo, 74k stars) and Agent Hierarchical Coordinator (ruvnet/ruflo, 74k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Elements And Metadata?
VectorSpaceLab (a GitHub organization) maintains it in VectorSpaceLab/AREX-Skill, which has 331 GitHub stars. The repository holds 157 skills in this directory. The repository was last updated on September 3, 2026.
Source: VectorSpaceLab/AREX-Skill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.