Agent skill

Documentation

by hardisgroupcom in hardisgroupcom/sfdx-hardis

Documentation standards for sfdx-hardis commands (description format with Command Behavior and Technical explanations sections, MkDocs site, build:doc).

AGPL-3.0Auto-check passedSales & Support

Install Documentation

skills CLI

$ npx skills add hardisgroupcom/sfdx-hardis --skill documentation -a claude-code

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

GitHub CLI

$ gh skill install hardisgroupcom/sfdx-hardis documentation --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/hardisgroupcom/sfdx-hardis.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/documentation .claude/skills/documentation && 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/

Paste into Claude Code

Install the "documentation" agent skill from https://github.com/hardisgroupcom/sfdx-hardis/tree/main/.claude/skills/documentation into .claude/skills/documentation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "documentation", 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

$skill-installer install https://github.com/hardisgroupcom/sfdx-hardis/tree/main/.claude/skills/documentation

Type 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.

skills CLI

$ npx skills add hardisgroupcom/sfdx-hardis --skill documentation -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install hardisgroupcom/sfdx-hardis documentation --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/hardisgroupcom/sfdx-hardis.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/documentation .agents/skills/documentation && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "documentation" agent skill from https://github.com/hardisgroupcom/sfdx-hardis/tree/main/.claude/skills/documentation into .agents/skills/documentation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "documentation", 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.

skills CLI

$ npx skills add hardisgroupcom/sfdx-hardis --skill documentation -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install hardisgroupcom/sfdx-hardis documentation --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/hardisgroupcom/sfdx-hardis.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/documentation .cursor/skills/documentation && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "documentation" agent skill from https://github.com/hardisgroupcom/sfdx-hardis/tree/main/.claude/skills/documentation into .cursor/skills/documentation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "documentation", 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

$ gemini skills install https://github.com/hardisgroupcom/sfdx-hardis.git --path .claude/skills/documentation

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add hardisgroupcom/sfdx-hardis --skill documentation -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install hardisgroupcom/sfdx-hardis documentation --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/hardisgroupcom/sfdx-hardis.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/documentation .gemini/skills/documentation && rm -rf skills-src

Use ~/.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/

Paste into Gemini CLI

Install the "documentation" agent skill from https://github.com/hardisgroupcom/sfdx-hardis/tree/main/.claude/skills/documentation into .gemini/skills/documentation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "documentation", 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.

GitHub CLI

$ gh skill install hardisgroupcom/sfdx-hardis documentation

Installs 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).

skills CLI

$ npx skills add hardisgroupcom/sfdx-hardis --skill documentation -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/hardisgroupcom/sfdx-hardis.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/documentation .github/skills/documentation && rm -rf skills-src

Use ~/.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/

Paste into GitHub Copilot

Install the "documentation" agent skill from https://github.com/hardisgroupcom/sfdx-hardis/tree/main/.claude/skills/documentation into .github/skills/documentation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "documentation", 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.

skills CLI

$ npx skills add hardisgroupcom/sfdx-hardis --skill documentation -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install hardisgroupcom/sfdx-hardis documentation --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/hardisgroupcom/sfdx-hardis.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/documentation .opencode/skills/documentation && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "documentation" agent skill from https://github.com/hardisgroupcom/sfdx-hardis/tree/main/.claude/skills/documentation into .opencode/skills/documentation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "documentation", 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: documentation
GitHub stars: 400
Token cost: ~1k tokens
SKILL.md length: 335 words
Files: 1
Skills in repo: 21
Repo updated: Oct 7, 2026
First seen: Oct 7, 2026
Licence: AGPL-3.0

At a glance

Documentation standards for sfdx-hardis commands (description format with Command Behavior and Technical explanations sections, MkDocs site, build:doc).

Works in 4 steps: How to invoke it: a concrete shell… → What flags are required in agent mode… → What defaults are applied when optional… → …
Modifying commands
SKILL.md covers Command Descriptions, Agent Mode Documentation…, Project Documentation and Keeping the Agent Commands…
Calls yarn

What it does

Documentation is an agent skill from hardisgroupcom/sfdx-hardis. Documentation standards for sfdx-hardis commands (description format with Command Behavior and Technical explanations sections, MkDocs site, build:doc). Use when creating or modifying commands.

Its SKILL.md is about 1k 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 Sales & Support. It works with Salesforce. The repository describes itself as: French-army-knife Toolbox for Salesforce. Orchestrates base commands and assist users with interactive wizards to make much more than native Salesforce CLI + Allows you to define…. The licence is AGPL-3.0.

When your agent uses it

Modifying commands

Example prompts

“/documentation”

Workflow steps

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

How to invoke it: a concrete shell example using --agent with all required flags.
What flags are required in agent mode (e.g., --task-name, --target-branch) vs. which are optional.
What defaults are applied when optional flags are omitted (e.g., "defaults to daily period", "skips metadata pull").
What is skipped: list interactive prompts or steps that are bypassed.

What it can do on your machine

Read from SKILL.md and the folder at commit 971ac89. 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
Shell commands in SKILL.md call:
- yarn
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
- sfdx-hardis.cloudity.com
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

Documentation loads about 1k tokens when it runs. Until then it costs about 52 tokens; SKILL.md has 335 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~52
When it runs · the whole SKILL.md, loaded when a task matches: ~1k

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 hardisgroupcom/sfdx-hardis at commit 971ac89, republished under its AGPL-3.0 licence (© hardisgroupcom). 335 words, ~1,046 tokens.

Download SKILL.mdSave it as .claude/skills/documentation/SKILL.md (or your agent's skills folder).

name: documentation
description: Documentation standards for sfdx-hardis commands (description format with Command Behavior and Technical explanations sections, MkDocs site, build:doc). Use when creating or modifying commands.
user-invocable: false

Documentation Standards

Command Descriptions

Every command must have a static description with ## Command Behavior and <details> sections:

typescript

public static description = `
## Command Behavior

**Brief description of what this command does.**

Key functionalities:

- **Feature 1:** Description
- **Feature 2:** Description

This command is part of [sfdx-hardis Feature](${CONSTANTS.DOC_URL_ROOT}/path/).

### Agent Mode

Supports non-interactive execution with \`--agent\`:

\`\`\`sh
sf hardis:<topic>:<action> --agent --target-org myorg@example.com
\`\`\`

In agent mode, all interactive prompts are skipped and default values are applied.

<details markdown="1">
<summary>Technical explanations</summary>

Technical implementation details...
</details>
`;

Agent Mode Documentation Requirements

When a command exposes an --agent flag, its description must include a ### Agent Mode section explaining:

How to invoke it: a concrete shell example using --agent with all required flags.
What flags are required in agent mode (e.g., --task-name, --target-branch) vs. which are optional.
What defaults are applied when optional flags are omitted (e.g., "defaults to daily period", "skips metadata pull").
What is skipped: list interactive prompts or steps that are bypassed.

The examples array must also include at least one entry that uses --agent.

Simple command (no required flags beyond `--target-org`)

typescript


### Agent Mode

Supports non-interactive execution with \`--agent\`:

\`\`\`sh
sf hardis:org:diagnose:mycommand --agent --target-org myorg@example.com
\`\`\`

In agent mode, all interactive prompts are skipped and default values are used.

Command with meaningful flag choices

typescript


### Agent Mode

Supports non-interactive execution with \`--agent\`:

\`\`\`sh
sf hardis:org:diagnose:unusedusers --agent --days 180 --licensetypes all-crm --target-org myorg@example.com
\`\`\`

In agent mode:

- \`--days\` defaults to 180 when not provided.
- \`--licensetypes\` defaults to \`all-crm\` when not provided.
- Interactive deletion prompts are skipped.

Do NOT use

The single-line pattern Supports non-interactive execution with \--agent` (uses default values and skips prompts).- replace it with a proper### Agent Mode` section.

Project Documentation

Main docs: https://sfdx-hardis.cloudity.com
Auto-generated command docs: yarn compile then yarn build:doc --commands <command id> for the commands you changed (ids or * patterns, comma-separated). Plain yarn build:doc rewrites every page: keep it for a change that touches many commands.
Site generator: MkDocs
AI-generated documentation features supported

Show full SKILL.md (159 more words)Show less

Keeping the Agent Commands Table Up to Date

The file docs/salesforce-agentic-automation.md contains a reference table of all sfdx-hardis commands that support --agent. This table is the canonical discovery page for AI agents and users who want to know what automation is possible.

When you add --agent support to a command, you must also:

Add the command to the appropriate category table in docs/salesforce-agentic-automation.md.

Use this table row format:

markdown

| [**hardis:topic:action**](hardis/topic/action.md) | One-sentence description of what an agent can do with this command - include key flags if any |

Place the row in the correct category section (Development Workflow, Org Diagnostics, Monitoring, etc.). Add a new category section if none of the existing ones fit.

When you remove --agent support from a command, remove its row from the table.

The page is registered in mkdocs.yml under AI & Agents > AI Agents Overview. No mkdocs.yml change is needed when adding individual command rows - only the markdown table in docs/salesforce-agentic-automation.md needs updating.

Files

Just SKILL.md in .claude/skills/documentation of hardisgroupcom/sfdx-hardis.

Open the folder on GitHubat commit 971ac89

Compare with similar skills

Documentation 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.

Documentation compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Documentation this skillhardisgroupcom/sfdx-hardis	400	—	~1k	Automated safety check: Pass	AGPL-3.0	today
Sf DatacloudJaganpro/sf-skills	424	—	~2.7k	Automated safety check: Pass	MIT	5 mo ago
Sf Datacloud ActJaganpro/sf-skills	424	—	~1.3k	Automated safety check: Pass	MIT	5 mo ago
Sf Datacloud ConnectJaganpro/sf-skills	424	—	~1.9k	Automated safety check: Pass	MIT	5 mo ago
Sf Datacloud HarmonizeJaganpro/sf-skills	424	—	~1.2k	Automated safety check: Pass	MIT	5 mo ago
Consumer Goods Accruals Datakit Deployforcedotcom/sf-skills	1.1k	—	~5.1k	Automated safety check: Pass	Apache-2.0	4 days ago

Similar skills

Sf Datacloud
Jaganpro/sf-skills
Salesforce Data Cloud product orchestrator for connect→prepare→harmonize→segment→act workflows.
424 GitHub stars~2.7k tokensUpdated 5 mo ago
Sales & SupportAuto-check passed
Sf Datacloud Act
Jaganpro/sf-skills
Salesforce Data Cloud Act phase. An agent skill from Jaganpro/sf-skills.
424 GitHub stars~1.3k tokensUpdated 5 mo ago
Sales & SupportAuto-check passed
Sf Datacloud Connect
Jaganpro/sf-skills
Salesforce Data Cloud Connect phase. An agent skill from Jaganpro/sf-skills.
424 GitHub stars~1.9k tokensUpdated 5 mo ago
Sales & SupportAuto-check passed
Sf Datacloud Harmonize
Jaganpro/sf-skills
Salesforce Data Cloud Harmonize phase. An agent skill from Jaganpro/sf-skills.
424 GitHub stars~1.2k tokensUpdated 5 mo ago
Sales & SupportAuto-check passed
Consumer Goods Accruals Datakit Deploy
forcedotcom/sf-skills
A skill your agent uses to deploy the TPM Liability Accruals data kit end to end to a Salesforce org.
1.1k GitHub stars~5.1k tokensUpdated 4 days ago
Sales & SupportAuto-check passed
Platform Trust Archive Manage
forcedotcom/sf-skills
ALWAYS USE THIS SKILL for anything involving Salesforce Archive (also called Trusted Services Archive) — search, view, unarchive, analyze, mask, and erase (RTBF) archived records via the Archive…
1.1k GitHub stars~3k tokensUpdated 4 days ago
Sales & SupportAuto-check passed

Questions about Documentation

What does Documentation do?

Documentation standards for sfdx-hardis commands (description format with Command Behavior and Technical explanations sections, MkDocs site, build:doc). Documentation is an agent skill from hardisgroupcom/sfdx-hardis. Documentation standards for sfdx-hardis commands (description format with Command Behavior and Technical explanations sections, MkDocs site, build:doc).

When should I use Documentation?

Documentation fits situations like: modifying commands.

How do I install Documentation in Claude Code?

Run `npx skills add hardisgroupcom/sfdx-hardis --skill documentation -a claude-code`. Or copy the skill folder (.claude/skills/documentation in hardisgroupcom/sfdx-hardis) into .claude/skills/documentation in your project. Claude Code loads it when a task matches its description.

How do I install Documentation in Codex?

Run `npx skills add hardisgroupcom/sfdx-hardis --skill documentation -a codex`. Or copy the skill folder (.claude/skills/documentation in hardisgroupcom/sfdx-hardis) into .agents/skills/documentation in your project. Codex loads it when a task matches its description.

Can I use Documentation 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 hardisgroupcom/sfdx-hardis --skill documentation -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/documentation, .gemini/skills/documentation, .github/skills/documentation and .opencode/skills/documentation in your project.

What does Documentation need to run?

Going by SKILL.md and its folder, Documentation needs the command-line tools its instructions call (yarn).

Does Documentation access the network?

SKILL.md names 1 domain. As links in the text: sfdx-hardis.cloudity.com. This is read from the text; nothing was executed.

Is Documentation 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 Documentation use?

Documentation is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Documentation use?

About 1k tokens (SKILL.md is roughly 4.2k 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 Documentation?

Skills that share tags, products or a category with Documentation: Sf Datacloud (Jaganpro/sf-skills, 424 stars), Sf Datacloud Act (Jaganpro/sf-skills, 424 stars), Sf Datacloud Connect (Jaganpro/sf-skills, 424 stars) and Sf Datacloud Harmonize (Jaganpro/sf-skills, 424 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Documentation?

hardisgroupcom (a GitHub organization) maintains it in hardisgroupcom/sfdx-hardis, which has 400 GitHub stars. The repository holds 21 skills in this directory. The repository was last updated on October 7, 2026.

Source: hardisgroupcom/sfdx-hardis on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Documentation

Facts

At a glance

What it does

When your agent uses it

Example prompts

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Documentation Standards

Command Descriptions

Agent Mode Documentation Requirements

Simple command (no required flags beyond --target-org)

Command with meaningful flag choices

Do NOT use

Project Documentation

Keeping the Agent Commands Table Up to Date

Files

Compare with similar skills

Similar skills

More from hardisgroupcom/sfdx-hardis

Related

Questions about Documentation

Simple command (no required flags beyond `--target-org`)