New: 97,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Docs Writer

by FoundationDB in FoundationDB/fdb-record-layer

Write or update documentation in docs/sphinx/source/. An agent skill from FoundationDB/fdb-record-layer.

Apache-2.0Auto-check passedDatabases

Install Docs Writer

skills CLI
$ npx skills add FoundationDB/fdb-record-layer --skill docs-writer -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install FoundationDB/fdb-record-layer docs-writer --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/FoundationDB/fdb-record-layer.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/docs-writer .claude/skills/docs-writer && rm -rf skills-src

Use ~/.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/

Facts

Skill name
docs-writer
GitHub stars
675
Token cost
~925 tokens
SKILL.md length
430 words
Files
1
Skills in repo
10
Repo updated
First seen
Licence
Apache-2.0

At a glance

Write or update documentation in docs/sphinx/source/. An agent skill from FoundationDB/fdb-record-layer.

  • Works in 4 steps: Read the code first. Grep/Glob to find… → Identify the non-obvious. Surprises,… → Draft the doc in the appropriate style… → …
  • Tasks that involve SQL
  • SKILL.md covers Two doc types, two styles, Process, Formatting and Source References…, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Docs Writer is an agent skill from FoundationDB/fdb-record-layer. Write or update documentation in docs/sphinx/source/. Applies the appropriate style for user-facing vs. architecture docs. Some example usages: "Document how schema templates work" "Write an architecture doc for the Cascades planner" "Update the SQL reference for the new GROUP BY syntax"

Its SKILL.md is about 930 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Databases, covering SQL. It works with SQL and Java. The repository describes itself as: A relational database with SQL support built on FoundationDB. The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve SQL

Example prompts

  • “Document how schema templates work”
  • “Write an architecture doc for the Cascades planner”
  • “Update the SQL reference for the new GROUP BY syntax”
  • “/docs-writer”

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Read the code first. Grep/Glob to find relevant classes, then read them.
  2. Identify the non-obvious. Surprises, trade-offs, cross-module dependencies, gotchas.
  3. Draft the doc in the appropriate style for the doc type.
  4. Add a Source References section (architecture docs only — see below).

What it can do on your machine

Read from SKILL.md and the folder at commit 20a2376. 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

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

    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

Docs Writer loads about 925 tokens when it runs. Until then it costs about 75 tokens; SKILL.md has 430 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~75
When it runs · the whole SKILL.md, loaded when a task matches
~925

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from FoundationDB/fdb-record-layer at commit 20a2376, republished under its Apache-2.0 licence (© FoundationDB). 430 words, ~925 tokens.

Download SKILL.mdSave it as .claude/skills/docs-writer/SKILL.md (or your agent's skills folder).
name
docs-writer
description
Write or update documentation in docs/sphinx/source/. Applies the appropriate style for user-facing vs. architecture docs. Some example usages: "Document how schema templates work" "Write an architecture doc for the Cascades planner" "Update the SQL reference for the new GROUP BY syntax"

You write and update documentation in docs/sphinx/source/. Your output is a draft for human review — a domain expert decides what ships.

Two doc types, two styles

User-facing docs (docs/sphinx/source/*.md)

Audience: developers building applications with the Record Layer or Relational Layer.

  • Code blocks are welcome — working examples help users get started.
  • Include concrete SQL, Java, or Gradle snippets.
  • Focus on practical usage: how to do X, what happens when Y.
  • Tone: clear and direct. Not a tutorial blog post, not a reference dump — somewhere between.
  • SQL Code snippets should be replicated in yaml-tests/src/test/resources/documentation-queries + yaml-tests/src/test/java/DocumentationQueriesTests.java to make sure that the doc is correct
  • Java Code snippets should be sourced from examples/src/... See direct_access.rst for a direct example
Architecture docs (docs/sphinx/source/architecture/)

Audience: contributors and maintainers understanding the internals.

  • Minimize code blocks. The code is in the source — don't duplicate it here.
  • Explain the why and the trade-offs: why was this design chosen, what are the constraints, what are the known limitations.
  • Prose over snippets. ASCII diagrams (in plain code blocks) are fine for structure.
  • Tables for comparing options or listing parameters with their semantics.
  • Tone: precise and technical. Formal is fine; wordy is not.

Process

  1. Read the code first. Grep/Glob to find relevant classes, then read them.
  2. Identify the non-obvious. Surprises, trade-offs, cross-module dependencies, gotchas.
  3. Draft the doc in the appropriate style for the doc type.
  4. Add a Source References section (architecture docs only — see below).
Show full SKILL.md (193 more words)Show less

Formatting

  • One topic per file.
  • Start with a 2-3 sentence overview paragraph.
  • Use ## for top-level sections, ### for subsections.
  • Write headings in sentence case, not Title Case, and in gerund form for action-oriented headings (e.g., "Renaming a record type" rather than "Rename a Record Type").
  • Wrap SQL keywords, type names, and class/identifier names in code spans (`SELECT`, `RecordType`) rather than plain text.
  • Bold (**term**) for key terms on first use.
  • GitHub link base: https://github.com/FoundationDB/fdb-record-layer/blob/main/ Append path from repo root. Use #L51 suffix for line links. Link the class name on first mention in each section. Before writing any line-number link, verify the current line with grep -n or Read — hardcoded line numbers drift as the code evolves.

Source References (architecture docs only)

Every architecture doc must end with a ## Source References section listing Java files consulted when writing but not already linked inline in the doc body. This enables freshness checking when the code evolves.

markdown
## Source References

- [EmbeddedRelationalStatement.java](https://github.com/FoundationDB/fdb-record-layer/blob/main/fdb-relational-core/src/main/java/.../EmbeddedRelationalStatement.java) — SQL execution entry point

If all source files are already linked inline, write: "All source files are linked inline above."

Input

Arguments: $ARGUMENTS

  • File path → update that doc.
  • Topic → create a new doc in the appropriate directory.
  • No argument → ask what to document.

© FoundationDB, 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

Just SKILL.md in .claude/skills/docs-writer of FoundationDB/fdb-record-layer.

Open the folder on GitHubat commit 20a2376

Compare with similar skills

Docs Writer 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.

Docs Writer compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Docs Writer this skillFoundationDB/fdb-record-layer675—~925Automated safety check: PassApache-2.0
Crudwujun728/jun_java_plugin240—~2.8kAutomated safety check: PassNone
DBoracle/skills872—~1.4kAutomated safety check: PassUPL-1.0
Sankhya Dashboard HTML Jsp Custom Best Praticessickn33/agentic-awesome-skills47k2 repos~4.3kAutomated safety check: PassMIT
Bigtable Basicsgoogle/skills21k—~1.3kAutomated safety check: PassApache-2.0
Jeecg Onlformjeecgboot/skills237—~7.7kAutomated safety check: PassApache-2.0

Similar skills

  • Crud

    wujun728/jun_java_plugin

    一键生成完整业务模块代码（SQL/Entity/DAO/XML/Repository/Service/Controller/Mapper/POJO），用于创建新的业务功能

    240 GitHub stars~2.8k tokensUpdated 4 mo ago
    DatabasesAuto-check passed

  • DB

    oracle/skills

    Official

    Oracle Database guidance for SQL, PL/SQL, SQLcl, ORDS, Oracle Vector SDK, administration, app development, performance, security, migrations, and agent-safe database workflows.

    872 GitHub stars~1.4k tokensUpdated yesterday
    DatabasesAuto-check passed

  • Sankhya Dashboard HTML Jsp Custom Best Pratices

    sickn33/agentic-awesome-skills

    This skill should be used when the user asks for patterns, best practices, creation, or fixing of Sankhya dashboards using HTML, JSP, Java, and SQL.

    47k GitHub starsUsed in 2 repos~4.3k tokens
    DatabasesAuto-check passed

  • Bigtable Basics

    google/skills

    Official

    Assists in provisioning instances/tables, designing performant schemas, and querying data in Bigtable.

    21k GitHub stars~1.3k tokensUpdated today
    DatabasesAuto-check passed

  • Jeecg Onlform

    jeecgboot/skills

    JeecgBoot Online表单（cgform）全生命周期管理——通过API自动创建/编辑数据库表和表单配置， 支持单表、主子表、树表，26种控件类型，以及JS/Java/SQL增强、权限配置、数据CRUD、积木报表集成。

    237 GitHub stars~7.7k tokensUpdated 20 days ago
    DatabasesAuto-check passed

  • 704 Technologies SQL

    jabrena/plinth

    A skill your agent uses when you need framework-agnostic SQL guidance — schema naming, relational table design, query readability, indexes, transactions, database security, migrations, testing, and…

    445 GitHub stars~1k tokensUpdated today
    DatabasesAuto-check passed

More from FoundationDB/fdb-record-layer

All 10 skills in this repo

  • Relational Query Processor

    FoundationDB/fdb-record-layer

    Specialized skill for working in the fdb-relational-core SQL processing layer — parser, plan generator, and Cascades planner.

    675 GitHub stars~1k tokensUpdated today
    Auto-check passed

  • Using Gradle

    FoundationDB/fdb-record-layer

    A skill your agent uses when you need to build the project, compile code, or run tests.

    675 GitHub stars~705 tokensUpdated today
    Auto-check passed

  • Context Resumption

    FoundationDB/fdb-record-layer

    Rebuild working context after a session restart. An agent skill from FoundationDB/fdb-record-layer.

    675 GitHub stars~467 tokensUpdated today
    Auto-check passed

  • Frl Coding Standard

    FoundationDB/fdb-record-layer

    Coding standards for all Java code in fdb-record-layer. An agent skill from FoundationDB/fdb-record-layer.

    675 GitHub stars~1.2k tokensUpdated today
    Auto-check passed

  • Frl Test Coding Standard

    FoundationDB/fdb-record-layer

    Standards for writing tests in fdb-record-layer. An agent skill from FoundationDB/fdb-record-layer.

    675 GitHub stars~792 tokensUpdated today
    Auto-check passed

  • Stacked PRs

    FoundationDB/fdb-record-layer

    Create and manage stacked pull requests on FoundationDB/fdb-record-layer using the gh stack CLI extension.

    675 GitHub stars~1.9k tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Docs Writer

What does Docs Writer do?

Write or update documentation in docs/sphinx/source/. An agent skill from FoundationDB/fdb-record-layer. Docs Writer is an agent skill from FoundationDB/fdb-record-layer. Write or update documentation in docs/sphinx/source/.

When should I use Docs Writer?

Docs Writer fits situations like: tasks that involve SQL.

How do I install Docs Writer in Claude Code?

Run `npx skills add FoundationDB/fdb-record-layer --skill docs-writer -a claude-code`. Or copy the skill folder (.claude/skills/docs-writer in FoundationDB/fdb-record-layer) into .claude/skills/docs-writer in your project. Claude Code loads it when a task matches its description.

How do I install Docs Writer in Codex?

Run `npx skills add FoundationDB/fdb-record-layer --skill docs-writer -a codex`. Or copy the skill folder (.claude/skills/docs-writer in FoundationDB/fdb-record-layer) into .agents/skills/docs-writer in your project. Codex loads it when a task matches its description.

Can I use Docs Writer 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 FoundationDB/fdb-record-layer --skill docs-writer -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/docs-writer, .gemini/skills/docs-writer, .github/skills/docs-writer and .opencode/skills/docs-writer in your project.

What does Docs Writer need to run?

SKILL.md names no scripts, command-line tools or credentials: Docs Writer is instructions for the agent only.

Does Docs Writer 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 Docs Writer 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. Review the folder before installing.

What licence does Docs Writer use?

Docs Writer is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Docs Writer use?

About 925 tokens (SKILL.md is roughly 3.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Docs Writer?

Skills that share tags, products or a category with Docs Writer: Crud (wujun728/jun_java_plugin, 240 stars), DB (oracle/skills, 872 stars), Sankhya Dashboard HTML Jsp Custom Best Pratices (sickn33/agentic-awesome-skills, 47k stars) and Bigtable Basics (google/skills, 21k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Docs Writer?

FoundationDB (a GitHub organization) maintains it in FoundationDB/fdb-record-layer, which has 675 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on October 6, 2026.

Source: FoundationDB/fdb-record-layer on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.