LLM Eval Pipeline Audit
ai-evals-course/evals-skills
Inspects an LLM evaluation setup for missing error analysis, unvalidated judges and vanity metrics, and ranks the problems by impact with fixes.
Write or revise documentation prose so it reads like the rest of this site, in the docs team's shared voice.
$ npx skills add langchain-ai/docs --skill docs-team-voice -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install langchain-ai/docs docs-team-voice --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/langchain-ai/docs.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/docs-team-voice .claude/skills/docs-team-voice && 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 "docs-team-voice" agent skill from https://github.com/langchain-ai/docs/tree/main/.agents/skills/docs-team-voice into .claude/skills/docs-team-voice/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "docs-team-voice", 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/langchain-ai/docs/tree/main/.agents/skills/docs-team-voiceType 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 langchain-ai/docs --skill docs-team-voice -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install langchain-ai/docs docs-team-voice --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/langchain-ai/docs.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/docs-team-voice .agents/skills/docs-team-voice && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "docs-team-voice" agent skill from https://github.com/langchain-ai/docs/tree/main/.agents/skills/docs-team-voice into .agents/skills/docs-team-voice/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "docs-team-voice", 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 langchain-ai/docs --skill docs-team-voice -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install langchain-ai/docs docs-team-voice --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/langchain-ai/docs.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/docs-team-voice .cursor/skills/docs-team-voice && 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 "docs-team-voice" agent skill from https://github.com/langchain-ai/docs/tree/main/.agents/skills/docs-team-voice into .cursor/skills/docs-team-voice/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "docs-team-voice", 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/langchain-ai/docs.git --path .agents/skills/docs-team-voice--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 langchain-ai/docs --skill docs-team-voice -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install langchain-ai/docs docs-team-voice --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/langchain-ai/docs.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/docs-team-voice .gemini/skills/docs-team-voice && 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 "docs-team-voice" agent skill from https://github.com/langchain-ai/docs/tree/main/.agents/skills/docs-team-voice into .gemini/skills/docs-team-voice/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "docs-team-voice", 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 langchain-ai/docs docs-team-voiceInstalls 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 langchain-ai/docs --skill docs-team-voice -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/langchain-ai/docs.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/docs-team-voice .github/skills/docs-team-voice && 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 "docs-team-voice" agent skill from https://github.com/langchain-ai/docs/tree/main/.agents/skills/docs-team-voice into .github/skills/docs-team-voice/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "docs-team-voice", 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 langchain-ai/docs --skill docs-team-voice -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install langchain-ai/docs docs-team-voice --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/langchain-ai/docs.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/docs-team-voice .opencode/skills/docs-team-voice && 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 "docs-team-voice" agent skill from https://github.com/langchain-ai/docs/tree/main/.agents/skills/docs-team-voice into .opencode/skills/docs-team-voice/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "docs-team-voice", 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.
docs-team-voiceWrite or revise documentation prose so it reads like the rest of this site, in the docs team's shared voice.
Docs Team Voice is an agent skill from langchain-ai/docs, published by the product's own GitHub organization. Write or revise documentation prose so it reads like the rest of this site, in the docs team's shared voice. Covers sentence length, cross-link density, how to state defaults and conditions, naming exact identifiers, and what to cut in a revision pass. Use when drafting or rewriting a page, a section, a concept overview, a how-to, a callout, or landing copy.
Its SKILL.md is about 1.5k 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 AI & LLM Engineering. It works with LangSmith. The repository describes itself as: Unified LangChain documentation. The licence is MIT.
Read from SKILL.md and the folder at commit cd302e5. It shows what the files ask for, not the result of running them.
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.
Shell commands in SKILL.md call:
makeFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Docs Team Voice loads about 1.5k tokens when it runs. Until then it costs about 94 tokens; SKILL.md has 881 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.
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.
The full file from langchain-ai/docs at commit cd302e5, republished under its MIT licence (© langchain-ai). 881 words, ~1,480 tokens.
.claude/skills/docs-team-voice/SKILL.md (or your agent's skills folder).AGENTS.md holds the rules a linter can check: no contractions, no first
person, no future tense, sentence-case headings, Oxford commas, spacing around
dashes. Vale enforces most of them and make lint_prose is the gate, though
Vale does not scan inside JSX components such as <Note> and <Tip>, so a
clean run there proves nothing. This skill covers what a linter cannot check:
rhythm, density, and the shape of a sentence that carries information.
The targets below are measured from this repository's own pages, not invented.
Median sentence length on this site is 13 to 15 words. Roughly one sentence in twelve runs past 25 words, one in forty past 30. Treat 25 as the point where you look for a split and 35 as a defect.
One idea per sentence. When a sentence carries two, split it and let the second stand alone.
The agent definition selects the model and core capabilities of a managed deep agent.
Set the
compressionfield to control how exported Parquet files are compressed. When omitted, LangSmith useszstandard.
The second example is two sentences where one long one would have hidden the default inside a subordinate clause.
The target is a floor as well as a ceiling. Keep the condition, the actor, and the exact value even when they push a sentence long, and split it rather than dropping one of them to get under 15 words.
Close to half of all prose sentences here carry a link. Cross-linking is not decoration: it is how a reader escapes a page that does not answer the question they arrived with.
Link a term on first mention only. Pointing forward at the end of a section is standard, and two pointer forms are both established:
Refer to Spend policies.
For the full project layout, see Project structure.
Neither is canonical. Different authors favor different ones, so match the form the page already uses and do not mass-convert one into the other.
Put the trigger first, then the behavior. No hedging, no "please note".
When omitted, LangSmith uses
zstandard.
Defaults to the last 7 days, newest first.
Task planning is opt-in.
Non-zero exits and timeouts from
--startup-cmdwarn but do not abort the session.
Constraints read the same way, as plain statements of fact rather than warnings about them.
Backtick every field, flag, value, environment variable, and status. Between a
quarter and a half of prose sentences on this site contain one. Name the actual
value rather than gesturing at it: zstandard, not "the appropriate
compression"; CREATED, RUNNING, COMPLETED, not "the various statuses".
If your API key is linked to multiple workspaces, specify the workspace in the header with
"x-tenant-id".
"For example" appears in roughly one sentence in thirty, almost always followed by a real value rather than a shape.
For example, in SCIM, the resolved
subclaim and SCIMexternalIdmust match in order for login to succeed.
If you cannot supply a real example, say less rather than inventing one. Never fabricate a field name, a response body, or a policy detail to fill a slot.
Second person carries a quarter to a half of sentences, most heavily in procedures and UI steps. Passive voice appears in only about one sentence in eight, and usually where the actor genuinely does not matter.
When viewing a trace that was generated by a run in LangSmith, you can access the associated server logs directly from the Details view.
Use the product name as the subject when the reader is not the actor: "LangSmith
uses zstandard", not "we use zstandard".
Read the draft once looking only for these:
word — word fails LangChain.DashesSpaces and blocks
CI. Prefer a comma, a colon, or two sentences, and reach for word—word only
when nothing else reads. A bold label opening a paragraph takes a colon:
**Tier assignment**:, measured at 177 uses in src/ against 1 for the dash.src/ for the feature and
read the pages that cover it from another angle, such as a CLI reference or a
permissions table. The docs-edit skill covers what to look for.Then run the gate:
make lint_prose FILES="<changed files>"For a full review against the style guide, with the rule each finding breaks,
use the docs-review skill.
© langchain-ai, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in .agents/skills/docs-team-voice of langchain-ai/docs.
Open the folder on GitHubat commit cd302e5
Docs Team Voice 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 |
|---|---|---|---|---|---|---|
| Docs Team Voice this skilllangchain-ai/docs | 426 | — | ~1.5k | Automated safety check: Pass | MIT | |
| LLM Eval Pipeline Auditai-evals-course/evals-skills | 1.5k | — | ~2.5k | Automated safety check: Pass | Apache-2.0 | |
| Langsmith Online Eval Engineeringlangchain-ai/langsmith-skills | 160 | — | ~1.4k | Automated safety check: Pass | MIT | |
| Langsmith ObservabilityOrchestra-Research/AI-Research-SKILLs | 13k | 2 repos | ~2.4k | Automated safety check: Pass | MIT | |
| Langsmith Trace Analyzersoba-labs/langchain-agent-skills | 107 | — | ~1.4k | Automated safety check: Pass | MIT | |
| LangSmith Trace DebuggingComposioHQ/awesome-claude-skills | 77k | 8 repos | ~2.7k | Automated safety check: Pass | None |
ai-evals-course/evals-skills
Inspects an LLM evaluation setup for missing error analysis, unvalidated judges and vanity metrics, and ranks the problems by impact with fixes.
langchain-ai/langsmith-skills
Design, test, create, and attach LangSmith online evaluators for production traces or conversation threads.
Orchestra-Research/AI-Research-SKILLs
LLM observability platform for tracing, evaluation, and monitoring.
soba-labs/langchain-agent-skills
Fetch, organize, and analyze LangSmith traces for debugging and evaluation.
ComposioHQ/awesome-claude-skills
Debugs LangChain and LangGraph agents by pulling recent execution traces with the langsmith-fetch CLI and reporting errors, tool calls, timings and token use.
langchain-ai/langchain-skills
Routes LangGraph agents with typed decision models that return probabilities, and finds LLM calls that only exist to produce a routing decision.
langchain-ai/docs
Add, move, rename, or delete a page on the LangChain docs site.
langchain-ai/docs
Build batteries-included agents with planning, context management, subagent delegation, and sandboxed execution.
langchain-ai/docs
A skill your agent uses when migrating inline code samples from LangChain docs (MDX files) into external, testable code files that are extracted by this repo’s snippet scripts and used as Mintlify…
langchain-ai/docs
Edit a docs page that already has an open pull request, or revise a page in place.
langchain-ai/docs
Restructure documentation that spans several pages. An agent skill from langchain-ai/docs.
langchain-ai/docs
Build agents with a prebuilt architecture and integrations for any model or tool.
Works with
Categories
Write or revise documentation prose so it reads like the rest of this site, in the docs team's shared voice. Docs Team Voice is an agent skill from langchain-ai/docs, published by the product's own GitHub organization. Write or revise documentation prose so it reads like the rest of this site, in the docs team's shared voice.
Docs Team Voice fits situations like: rewriting a page; A concept overview.
Run `npx skills add langchain-ai/docs --skill docs-team-voice -a claude-code`. Or copy the skill folder (.agents/skills/docs-team-voice in langchain-ai/docs) into .claude/skills/docs-team-voice in your project. Claude Code loads it when a task matches its description.
Run `npx skills add langchain-ai/docs --skill docs-team-voice -a codex`. Or copy the skill folder (.agents/skills/docs-team-voice in langchain-ai/docs) into .agents/skills/docs-team-voice in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add langchain-ai/docs --skill docs-team-voice -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-team-voice, .gemini/skills/docs-team-voice, .github/skills/docs-team-voice and .opencode/skills/docs-team-voice in your project.
Going by SKILL.md and its folder, Docs Team Voice needs the command-line tools its instructions call (make).
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.
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.
Docs Team Voice is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 1.5k tokens (SKILL.md is roughly 5.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Docs Team Voice: LLM Eval Pipeline Audit (ai-evals-course/evals-skills, 1.5k stars), Langsmith Online Eval Engineering (langchain-ai/langsmith-skills, 160 stars), Langsmith Observability (Orchestra-Research/AI-Research-SKILLs, 13k stars) and Langsmith Trace Analyzer (soba-labs/langchain-agent-skills, 107 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
langchain-ai (a GitHub organization, an official publisher) maintains it in langchain-ai/docs, which has 426 GitHub stars. The repository holds 17 skills in this directory. The repository was last updated on October 10, 2026.
Source: langchain-ai/docs on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.