New: 98,000+ 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

Add Skill

by coralogix in coralogix/cx-cli

A skill your agent uses when the user asks to "add a skill", "create a skill", "new skill", "write a skill for", "skill for cx <something", "add a user-facing skill", "create a SKILL.md", "teach an…

Apache-2.0Auto-check passedAgent Workflows

Install Add Skill

skills CLI
$ npx skills add coralogix/cx-cli --skill add-skill -a claude-code

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

GitHub CLI
$ gh skill install coralogix/cx-cli add-skill --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/coralogix/cx-cli.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/add-skill .claude/skills/add-skill && 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
add-skill
GitHub stars
121
Token cost
~1.8k tokens
SKILL.md length
851 words
Files
1
Skills in repo
21
Repo updated
First seen
Licence
Apache-2.0

At a glance

A skill your agent uses when the user asks to "add a skill", "create a skill", "new skill", "write a skill for", "skill for cx <something", "add a user-facing skill", "create a SKILL.md", "teach an…

  • Works in 5 steps: Understand the Domain → Read Existing Skills → Create Directory and Write SKILL.md → …
  • The user asks to add a skill
  • SKILL.md covers Step 0: Understand the Domain, Step 1: Read Existing Skills, Step 2: Create Directory and… and Step 3: Add Reference Files…, plus 1 more section
  • Calls bash

What it does

Add Skill is an agent skill from coralogix/cx-cli. Use this skill when the user asks to "add a skill", "create a skill", "new skill", "write a skill for", "skill for cx <something", "add a user-facing skill", "create a SKILL.md", "teach an agent how to use", "agent skill for", "document a command as a skill", "make a skill", "add skill to skills/", "create agent instructions for", "build a skill", or wants to create a new user-facing skill in the skills/ directory that teaches AI agents how to use a cx CLI command. Use this even when the user is following the…

Its SKILL.md is about 1.8k 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 Agent Workflows, covering Skill authoring and Building AI agents. The repository describes itself as: This is the Coralogix CLI. The licence is Apache-2.0.

When your agent uses it

  • The user asks to add a skill
  • Write a skill for
  • Skill for cx <something
  • Add a user-facing skill

Example prompts

  • “add a skill”
  • “create a skill”
  • “new skill”
  • “/add-skill”

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Understand the Domain
  2. Read Existing Skills
  3. Create Directory and Write SKILL.md
  4. Add Reference Files and Update README
  5. Verify

What it can do on your machine

Read from SKILL.md and the folder at commit c071372. 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:

    • bash

    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

Add Skill loads about 1.8k tokens when it runs. Until then it costs about 146 tokens; SKILL.md has 851 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~146
When it runs · the whole SKILL.md, loaded when a task matches
~1.8k

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 coralogix/cx-cli at commit c071372, republished under its Apache-2.0 licence (© coralogix). 851 words, ~1,791 tokens.

Download SKILL.mdSave it as .claude/skills/add-skill/SKILL.md (or your agent's skills folder).
name
add-skill
description
Use this skill when the user asks to "add a skill", "create a skill", "new skill", "write a skill for", "skill for cx <something>", "add a user-facing skill", "create a SKILL.md", "teach an agent how to use", "agent skill for", "document a command as a skill", "make a skill", "add skill to skills/", "create agent instructions for", "build a skill", or wants to create a new user-facing skill in the skills/ directory that teaches AI agents how to use a cx CLI command. Use this even when the user is following the add-command workflow and reaches the skill creation step.
metadata.version
0.1.0
metadata.internal
true

Add a User-Facing Skill

End-to-end workflow for creating a skill in skills/ that teaches AI agents how to use a cx CLI command. This skill is often invoked from add-command Step 6, but can also be used standalone when documenting an existing command.

contributing/adding-a-skill.md has the full reference guide and a copy-pasteable template. Read it alongside this workflow.

Step 0: Understand the Domain

Before writing anything, answer these questions:

  1. What cx command are you documenting? Identify the command and all its subcommands (e.g., cx alerts list, cx alerts get, cx alerts create).
  2. What can the user do with it? List the key operations, flags, and output formats supported.
  3. Who is the audience? Skills are consumed by AI agents, not humans directly. Write instructions an agent can follow step-by-step to accomplish a user's goal.
  4. Is there dense reference material? Schemas, enum catalogs, field references, or language syntax exceeding ~100 lines belong in a separate references/ file.

Step 1: Read Existing Skills

Before writing any skill, read existing ones to internalize the project's patterns. Agents that study existing skills first produce consistent, high-quality results rather than inventing new formats.

Always read:

  • contributing/adding-a-skill.md - full guide with directory structure, frontmatter conventions, reference file rules, and a copy-pasteable template
  • skills/README.md - the public catalog you'll update in Step 4

Study at least two existing skills:

SkillWhy study it
skills/cx-alerts/SKILL.mdREST-based command with rich examples, JSON payloads, investigation workflow; uses both shared and skill-local reference files
skills/cx-telemetry-querying/SKILL.mdGateway skill that loads shared reference files per pillar — good model for cross-pillar routing and reference-loading patterns
skills/cx-dashboards/SKILL.mdComplex multi-step workflow; uses shared references (dataprime, promql, logs, spans) plus skill-local references
skills/cx-cost-optimization/SKILL.mdWorkflow skill covering 5 commands unified by "reduce costs" intent — good model for multi-command skills

Pick the two closest to what you're building and read them completely.

Step 2: Create Directory and Write SKILL.md

Create skills/cx-<domain-name>/SKILL.md. All skill directories use the cx- prefix. Use the directory structure, frontmatter format, and templates from contributing/adding-a-skill.md § "Directory Structure" through "Complete Template" (single-command) or § "Workflow Skills" (multi-command).

Writing effective trigger descriptions

The description frontmatter field is the primary trigger mechanism - agents use it to decide when to activate a skill. This is the single most important line in the file. Write at least 10 trigger phrases covering:

  • Explicit command names ("list alerts", "get alert by ID")
  • User intents ("investigate alert failures", "debug noisy alerts")
  • Synonyms and variations ("check", "find", "search", "analyze")
  • Domain jargon ("SLO breach", "error budget")
Body structure

Follow this order (see contributing/adding-a-skill.md § "Complete Template" for a starting point):

  1. Title and intro - one sentence explaining what the skill covers and which cx commands it uses
  2. CLI Commands table - | Command | Purpose | Key flags | for every subcommand. Include -o json/-o toon and -p <profile> notes.
  3. Workflow / Investigation steps - numbered steps an agent should follow. Start with discovery, end with verification.
  4. Key Principles - 4-6 bullet points: use -o json with jq, multi-profile behavior, always verify, etc.
  5. Additional Resources - links to references/ files and related skills
Show full SKILL.md (350 more words)Show less
Style guidelines
  • Write for an AI agent - be explicit about what to run and in what order
  • Use code blocks for every CLI invocation
  • Include realistic examples with actual flag values, not placeholders
  • Show jq filtering examples when the command supports -o json
  • Keep SKILL.md under ~200 lines; move dense material to references/

Step 3: Add Reference Files and Update README

Follow contributing/adding-a-skill.md § "Reference Files" for when and how to create references/ files, and § "Updating skills/README.md" for adding the skill to the public catalog.

Shared vs. skill-local references

Before creating a new reference file, check whether the content is language-level or telemetry-pillar material:

  • Language guides (DataPrime syntax, PromQL guidelines) → skills/shared/
  • Telemetry-pillar how-tos (logs querying, spans querying, metrics workflow, RUM) → skills/shared/
  • Skill-specific schemas or templates (alert JSON schemas, dashboard widget templates) → skills/cx-your-domain/references/

If your skill needs a file from skills/shared/:

  1. Add your skill and file list to scripts/sync-shared-references.sh
  2. Run bash scripts/sync-shared-references.sh — it copies the file(s) into your references/
  3. Commit the sync script change and the generated references/ copies together

If you're adding a new shared reference:

  1. Create it in skills/shared/
  2. Register it in the sync script for all consuming skills
  3. Run the script to generate copies, then commit everything

Step 4: Verify

  1. Frontmatter - name matches directory, description has 10+ trigger phrases, metadata.version is "0.1.0"
  2. Body completeness - has CLI Commands table, workflow steps, key principles, and additional resources (if references exist)
  3. Reference links - any references/ paths in SKILL.md point to files that actually exist
  4. README updated - skills/README.md has the new row
  5. No bloat - SKILL.md doesn't duplicate >100 lines of material that belongs in references/
  6. Shared references synced - if the skill uses files from skills/shared/, confirm bash scripts/sync-shared-references.sh was run and the generated references/ copies are committed
  7. Agent readability - would an AI agent know exactly what to do after reading this skill? If not, add missing steps or examples

For advanced trigger optimization, use the /skill-creator skill to run eval-driven description testing and iterate on your trigger phrases.

Use the PR checklist from contributing/adding-a-skill.md § "PR Checklist" in your PR description.

© coralogix, 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/add-skill of coralogix/cx-cli.

Open the folder on GitHubat commit c071372

Compare with similar skills

Add Skill 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.

Add Skill compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Add Skill this skillcoralogix/cx-cli121—~1.8kAutomated safety check: PassApache-2.0
Microsoft Skill CreatorMicrosoftDocs/mcp1.9k3 repos~2.1kAutomated safety check: PassCC-BY-4.0
Agent Creatorjdforsythe/forge151—~4.5kAutomated safety check: PassMIT
Guidancetestdouble/han281—~1.8kAutomated safety check: PassMIT
Skill Creatorjdforsythe/forge151—~4.1kAutomated safety check: PassMIT
Agent Buildertestdouble/han281—~3.8kAutomated safety check: PassMIT

Similar skills

  • Microsoft Skill Creator

    MicrosoftDocs/mcp

    Official

    Create agent skills for Microsoft technologies using official documentation.

    1.9k GitHub starsUsed in 3 repos~2.1k tokens
    Agent WorkflowsAuto-check passed

  • Agent Creator

    jdforsythe/forge

    Creates structured agent definitions using the 7-component format grounded in persona science (the alignment-accuracy tradeoff), vocabulary routing, and the MAST failure taxonomy + Forge watchlist.

    151 GitHub stars~4.5k tokensUpdated 3 mo ago
    Agent WorkflowsAuto-check passed

  • Guidance

    testdouble/han

    Authoritative guidance for building Claude Code skills, agents, and plugins, plus init and update steps that install and refresh the plugin-building skills in the current repository.

    281 GitHub stars~1.8k tokensUpdated 9 days ago
    Agent WorkflowsAuto-check passed

  • Skill Creator

    jdforsythe/forge

    Creates high-quality Claude Code and Cowork skills using evidence-based principles: expert vocabulary payloads for knowledge routing, dual-register descriptions for reliable triggering, named…

    151 GitHub stars~4.1k tokensUpdated 3 mo ago
    Agent WorkflowsAuto-check passed

  • Agent Builder

    testdouble/han

    Builds a new Claude Code agent (subagent) from scratch through a relentless, evidence-based interview that walks the agent's design tree decision-by-decision — entity fit, domain focus and…

    281 GitHub stars~3.8k tokensUpdated 9 days ago
    Agent WorkflowsAuto-check passed

  • Skill Builder

    testdouble/han

    Builds a new Claude Code skill from scratch through a relentless, evidence-based interview that walks the skill's design tree decision-by-decision — entity fit, use cases, name, description…

    281 GitHub stars~4.1k tokensUpdated 9 days ago
    Agent WorkflowsAuto-check passed

More from coralogix/cx-cli

All 21 skills in this repo

  • Cx AI Center

    coralogix/cx-cli

    A skill your agent uses for any question or action about the user's AI/GenAI applications or agents — their behavior, prompts/responses, quality, hallucinations, guardrails, security, cost/tokens…

    121 GitHub stars~2.5k tokensUpdated 3 days ago
    Auto-check passed

  • Cx Alerts

    coralogix/cx-cli

    This skill should be used when the user asks to "manage alerts", "create alert", "list alerts", "delete alert", "check alert status", "enable alert", "disable alert", "investigate firing alerts"…

    121 GitHub stars~2.5k tokensUpdated 3 days ago
    Auto-check passed

  • Cx Coding Agents

    coralogix/cx-cli

    A skill your agent uses when the user asks about AI Center Coding Agents data, wants to reproduce or extend the Coding Agents dashboards, or asks questions about usage, cost, tokens, sessions…

    121 GitHub stars~1.8k tokensUpdated 3 days ago
    Auto-check passed

  • Cx Cost Optimization

    coralogix/cx-cli

    A skill your agent uses when the user asks to "check data usage", "list TCO policies", "reduce Coralogix costs", "optimize observability spend", "lower our logging bill", "data budget exceeded"…

    121 GitHub stars~3.4k tokensUpdated 3 days ago
    Auto-check passed

  • Cx Data Pipeline

    coralogix/cx-cli

    A skill your agent uses when the user asks to "set up parsing", "create parsing rule", "extract fields from logs", "regex extraction", "log parsing", "enrich logs", "add context to logs", "custom…

    121 GitHub stars~3k tokensUpdated 3 days ago
    Auto-check passed

  • Cx Telemetry Querying

    coralogix/cx-cli

    A skill your agent uses for any question involving telemetry data: "investigate an issue", "debug a problem", "find out why something is slow", "check error rates", "analyze user behavior"…

    121 GitHub stars~2.6k tokensUpdated 3 days ago
    Auto-check passed

Categories

Questions about Add Skill

What does Add Skill do?

A skill your agent uses when the user asks to "add a skill", "create a skill", "new skill", "write a skill for", "skill for cx <something", "add a user-facing skill", "create a SKILL.md", "teach an…. Add Skill is an agent skill from coralogix/cx-cli.md", "teach an agent how to use", "agent skill for", "document a command as a skill", "make a skill", "add skill to skills/", "create agent instructions for", "build a skill", or wants to create a new user-facing skill in the skills/ directory that teaches AI agents how to use a cx CLI command.

When should I use Add Skill?

Add Skill fits situations like: the user asks to add a skill; write a skill for; skill for cx <something; add a user-facing skill.

How do I install Add Skill in Claude Code?

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

How do I install Add Skill in Codex?

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

Can I use Add Skill 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 coralogix/cx-cli --skill add-skill -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/add-skill, .gemini/skills/add-skill, .github/skills/add-skill and .opencode/skills/add-skill in your project.

What does Add Skill need to run?

Going by SKILL.md and its folder, Add Skill needs the command-line tools its instructions call (bash).

Does Add Skill 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 Add Skill 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 Add Skill use?

Add Skill 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 Add Skill use?

About 1.8k tokens (SKILL.md is roughly 7.2k 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 Add Skill?

Skills that share tags, products or a category with Add Skill: Microsoft Skill Creator (MicrosoftDocs/mcp, 1.9k stars), Agent Creator (jdforsythe/forge, 151 stars), Guidance (testdouble/han, 281 stars) and Skill Creator (jdforsythe/forge, 151 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Add Skill?

coralogix (a GitHub organization) maintains it in coralogix/cx-cli, which has 121 GitHub stars. The repository holds 21 skills in this directory. The repository was last updated on October 7, 2026.

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