Claude Code Skills Marketplace is a collection and marketplace of skills, plugins, agents, and instructions that extend Claude Code with specialized development workflows. It is for developers who want to install existing workflows or create, validate, and package their own Claude Code skills.
Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add daymade/claude-code-skills/plugin install daymade-docsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/daymade/claude-code-skills/docs-router)<a href="https://agentmods.dev/skills/daymade/claude-code-skills/docs-router"><img src="https://agentmods.dev/badge/skills/daymade/claude-code-skills/docs-router/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/daymade/claude-code-skills/docs-router"><img src="https://agentmods.dev/badge/skills/daymade/claude-code-skills/docs-router.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00091 | $0.01157 |
| Opus 5.5 | $0.00036 | $0.00463 |
| Sonnet 5.5 | $0.00018 | $0.00231 |
| Haiku 4.5 | $0.00009 | $0.00116 |
Grade A, and why
docs-router scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Daymade document router
Choose the one specialist that owns the requested result. First find the path
of this loaded docs-router/SKILL.md in the active skill catalog or the
invocation that opened it. Resolve that path to its canonical location (follow
symlinks), verify that it exists under a docs-router directory, and take that
directory's parent as the suite root. The paths in the table are relative to
this router's directory; resolve the selected path and verify that it points
to a direct sibling SKILL.md inside that suite root. Never anchor resolution
to the task's working directory or an old installed copy. Claude Code may
expand ${CLAUDE_PLUGIN_ROOT} as a shortcut, but the router must work when
that variable is absent, as in Codex. If this router's own active path cannot
be identified unambiguously, stop instead of guessing a copy.
Read the selected child SKILL.md in full before acting; if a read is
truncated, continue from the omitted part. Then load every reference that the
child requires for this branch of work. The leaf skills are intentionally
absent from automatic discovery, so open their files directly rather than
invoking them through the Skill tool. A user can still invoke any leaf's
original /daymade-docs:<leaf> command manually.
| Requested result | Read this exact file |
|---|---|
| Convert a DOCX, PDF, PPTX, or saved HTML/HTM to Markdown; parse Word or extract document text and images into Markdown | ../doc-to-markdown/SKILL.md |
| Turn Markdown into a printable PDF; adapt a manufacturer PDF manual into a concise Chinese illustrated recipient guide | ../pdf-creator/SKILL.md |
Create or format a Word .docx; export or repair an existing Word/WPS manuscript as PDF |
../docx-creator/SKILL.md |
| Turn a PDF into a self-contained, image-faithful HTML reading page, optionally translating it while keeping figures and charts | ../pdf-to-html/SKILL.md |
| Extract Mermaid diagrams from Markdown or render Mermaid as PNG | ../mermaid-tools/SKILL.md |
Create a professionally formatted Excel workbook, parse a complex investment-bank .xlsm model, or control Excel on macOS |
../excel-automation/SKILL.md |
| Turn photos of paper pages into a scanned PDF, replace pages in a scan, or make an unsigned digital document look hand-signed and scanned | ../photo-to-scanned-pdf/SKILL.md |
| Extract Word/WPS DOCX comments or tracked changes into a review ledger | ../read-docx-review/SKILL.md |
| Check documentation impact after an authorized code, script, config, environment, path, deployment, auth, test, or procedure change; or consolidate redundant docs | ../docs-cleaner/SKILL.md |
Decide by the input and requested output, not a shared word such as “PDF”
or “document.” For example, Markdown → PDF selects pdf-creator; an existing
Word manuscript → PDF selects docx-creator; PDF → Markdown selects
doc-to-markdown; PDF → HTML selects pdf-to-html. If the request spans two
results, read each relevant child before its stage.
For a manufacturer manual → Chinese illustrated guide (图文操作指南), select
pdf-creator and load its conditional illustrated-manual reference before
drafting. Use the sibling resolution above for any source-text or image
extraction stage; keep ordinary PDF reading/editing with its existing owner.
For website → Markdown, acquire the authorized pages through the owning web
workflow first, then select doc-to-markdown for the saved HTML. That conversion
branch does not crawl a site or certify presentation in a recipient's reader.
Do not select a Daymade child for a new slide deck or generic PPT work. Use
deck-creator for new presentation creation only when it is installed. If it
is unavailable, this suite has no automatic current PPT builder; external
users may explicitly invoke the retired /daymade-docs:ppt-creator for
its compatibility notice only, not PPT generation. General PDF reading/editing,
ordinary spreadsheet analysis, and other tasks without a matching row remain
with their owning skills or normal workflow. If the result is unclear, inspect
the actual file/task or ask for the missing input or output; do not guess a
Daymade child from an extension alone.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- today Changed · +5 lines 562b1e3950d6
- 2d ago Changed · -1 lines · -3 tokens per session 31321093128d
- 16d ago Changed · +4 lines · +3 tokens per session 9438da0f3cfc
- 28d ago First seen · 67 lines · 91 tokens per session scan A 49901af09d25
docs-router is a skill published in the GitHub repository daymade/claude-code-skills (1,483 stars, last pushed today), licensed MIT. It adds 91 tokens to every session and 1,157 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-24.
Other skills, from other repositories
doc-reader
Read any common document/data file — PDF, Word (.docx), Excel (.xlsx/.xls), PowerPoint (.pptx), images (OCR), CSV/TSV, plain text, JSON/YAML/TOML, HTML/XML, and most source-code files. Use the readdocument tool.
surfsense-documents
Make or change a Word document (.docx), a PDF, a PowerPoint deck (.pptx) or an Excel workbook (.xlsx) by writing a Python script that surfsenserenderdocument runs, optionally starting from a source's own Word or PowerPoint file. Load it whenever the user asks for one of these, or for a change to one you made.
xberg-extracting-tables
Use when extracting tabular data from PDFs, spreadsheets, or images. Covers layout-aware table detection, table model selection, output formats (markdown / JSON cells), and known limits.
skill-doc-delivery
Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables.
report-generator
A report-generation tool for producing SEO and GEO analysis reports in formats such as Markdown, HTML, PDF, JSON, and Excel. It also supports charts, templates, data processing, and interactive report elements.
kordoc
A command-line and server tool for reading and creating Korean official documents, including HWP, HWPX, PDF, DOCX, and spreadsheet files. It can convert documents to Markdown and create or update HWPX files.