Official agent skill

Working With Skills

by PostHog in PostHog/posthog

Best practices for agents managing PostHog skills via the MCP skill- tools — how to discover, read, create, update, and refactor skills efficiently, especially large skills with many bundled files.

OfficialCustom licenceAuto-check passedDevOps & Cloud

Install Working With Skills

skills CLI
$ npx skills add PostHog/posthog --skill working-with-skills -a claude-code

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

GitHub CLI
$ gh skill install PostHog/posthog working-with-skills --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/PostHog/posthog.git skills-src && mkdir -p .claude/skills && cp -r skills-src/products/skills/skills/working-with-skills .claude/skills/working-with-skills && 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
working-with-skills
GitHub stars
40k
Token cost
~4.4k tokens
SKILL.md length
1,987 words
Files
2 (incl. references)
Skills in repo
254
Repo updated
First seen
Licence
Custom licence

At a glance

Best practices for agents managing PostHog skills via the MCP skill- tools — how to discover, read, create, update, and refactor skills efficiently, especially large skills with many bundled files.

  • Works in 4 steps: Progressive disclosure is… → Pick the smallest write primitive that… → Reads are cheap; concurrent overwrites… → …
  • You are about to call any skill- tool
  • SKILL.md covers Operating principles, Decision tree: which tool do I…, Discover before you fetch and Reading a large skill…, plus 9 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Working With Skills is an agent skill from PostHog/posthog, published by the product's own GitHub organization. Best practices for agents managing PostHog skills via the MCP skill- tools — how to discover, read, create, update, and refactor skills efficiently, especially large skills with many bundled files. Use whenever you are about to call any skill- tool, asked to author or edit a shared skill, or troubleshoot why a skill write was rejected. Also use when asked what skills are good for or how to shape one (project hub, runbook, catalog, handover, daily driver). Pairs with skills-store (which covers the raw tool…

Its SKILL.md is about 4.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/skill-patterns.md`).

It sits in DevOps & Cloud, covering Runbooks and postmortems. It works with PostHog and Model Context Protocol. The repository describes itself as: :hedgehog: PostHog is the leading platform for building self-driving products. Our developer tools – AI observability, analytics, session replay, flags, experiments, error…

When your agent uses it

  • You are about to call any skill- tool
  • Asked to author
  • Edit a shared skill
  • Troubleshoot why a skill write was rejected

Example prompts

  • “/working-with-skills”

Requirements

  • Python 3

Workflow steps

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

  1. Progressive disclosure is non-negotiable. Lists return descriptions, get
  2. Pick the smallest write primitive that does the job. A targeted edits
  3. Reads are cheap; concurrent overwrites are not. Always have a recent
  4. Authoring follows the Agent Skills spec.

What it can do on your machine

Read from SKILL.md and the folder at commit c012c8d. 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 json).

    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):

    • agentskills.io

    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

Working With Skills loads about 4.4k tokens when it runs, and up to ~7.8k if it reads all its reference files. Until then it costs about 155 tokens; SKILL.md has 1,987 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~155
When it runs · the whole SKILL.md, loaded when a task matches
~4.4k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~7.8k

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

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 1,987 words (~4,378 tokens).

“This skill teaches agents how to use the skill-* MCP tools well — minimum context, minimum round-trips, minimum mistakes. If you are not yet familiar with the tool surface itself, read the skills-store skill first for the catalog. This document…”

— opening of SKILL.md by PostHog, Custom licence
name
working-with-skills

Read the full SKILL.md on GitHub

Files

SKILL.md and 1 other file (references) in products/skills/skills/working-with-skills of PostHog/posthog.

  • SKILL.md
  • references/skill-patterns.md

Open the folder on GitHubat commit c012c8d

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders. This page covers the copy in PostHog/posthog, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Working With Skills 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.

Working With Skills compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Working With Skills this skillPostHog/posthog40k—~4.4kAutomated safety check: PassCustom licence
Whyfmflurry/settings-opencode171—~2kAutomated safety check: PassMIT
Prepare Cloudflare Production DeploymentLubomirGeorgiev/cloudflare-workers-nextjs-saas-template786—~5.9kAutomated safety check: NotesMIT
UModel Skill Runneralibaba/UnifiedModel415—~1kAutomated safety check: PassCustom licence
Codflow Setupbighadj22/codflow354—~7.8kAutomated safety check: NotesApache-2.0
Codflow Updatebighadj22/codflow354—~6.2kAutomated safety check: NotesApache-2.0

Similar skills

  • Why

    fmflurry/settings-opencode

    A skill your agent uses for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds.

    171 GitHub stars~2k tokensUpdated 3 days ago
    DevOps & CloudAuto-check passed
  • Prepare Cloudflare Production Deployment

    LubomirGeorgiev/cloudflare-workers-nextjs-saas-template

    Source-of-truth runbook for preparing this Vinext Cloudflare Workers SaaS template for production deployment.

    786 GitHub stars~5.9k tokensUpdated today
    DevOps & CloudAuto-check: notes
  • UModel Skill Runner

    alibaba/UnifiedModel

    Loads one entity-linked Skill through UModel, follows its inline SKILL.md and applies attached knowledge items under their apply policies.

    415 GitHub stars~1k tokensUpdated 16 days ago
    Agent WorkflowsAuto-check passed
  • Codflow Setup

    bighadj22/codflow

    Setup runbook for CodFlow — an AI agent following it authenticates with Cloudflare, creates the required resources (D1, R2, KV) in the developer's account, binds their real IDs into both…

    354 GitHub stars~7.8k tokensUpdated 4 days ago
    DevOps & CloudAuto-check: notes
  • Codflow Update

    bighadj22/codflow

    Update runbook for a self-hosted CodFlow install — an AI agent following it fetches the latest code from the CodFlow GitHub repo, merges it into an EXISTING checkout, syncs the gitignored…

    354 GitHub stars~6.2k tokensUpdated 4 days ago
    DevOps & CloudAuto-check: notes
  • Creates or updates project documentation for a feature, system, or component and publishes it to a user-specified Confluence location.

    281 GitHub stars~2.1k tokensUpdated 9 days ago
    DevOps & CloudAuto-check passed

More from PostHog/posthog

All 254 skills in this repo
  • Authoring Log Alerts

    PostHog/posthog

    Official

    Author useful, low-noise log alerts on services in a PostHog project.

    40k GitHub stars~3k tokensUpdated today
    Auto-check passed
  • Official

    Operating procedure for the conflict-autoresolver agent: sweep open PostHog/posthog PRs that conflict with master, resolve the trivial conflicts (generated artifacts deterministically, source…

    40k GitHub stars~4.2k tokensUpdated today
    Auto-check passed
  • Official

    Help users debug PostHog Error Tracking stack-trace symbolication for any supported platform — JavaScript/TypeScript web, React Native (Hermes), Android (Proguard / R8), or iOS / macOS (dSYM).

    40k GitHub stars~2.2k tokensUpdated today
    Auto-check passed
  • Exploring Apm Traces

    PostHog/posthog

    Official

    Investigates distributed application performance using PostHog APM (OpenTelemetry span) data via MCP.

    40k GitHub stars~3.5k tokensUpdated today
    Auto-check passed
  • Exploring LLM Traces

    PostHog/posthog

    Official

    Debug and inspect LLM/AI agent traces using PostHog's MCP tools.

    40k GitHub stars~4.4k tokensUpdated today
    Auto-check passed
  • Investigate Metric

    PostHog/posthog

    Official

    Diagnose why a product metric changed (dropped, spiked, or plateaued) by orchestrating breakdowns, actors, paths, lifecycle, retention, and annotations queries.

    40k GitHub stars~1.9k tokensUpdated today
    Auto-check passed

Questions about Working With Skills

What does Working With Skills do?

Best practices for agents managing PostHog skills via the MCP skill- tools — how to discover, read, create, update, and refactor skills efficiently, especially large skills with many bundled files. Working With Skills is an agent skill from PostHog/posthog, published by the product's own GitHub organization. Best practices for agents managing PostHog skills via the MCP skill- tools — how to discover, read, create, update, and refactor skills efficiently, especially large skills with many bundled files.

When should I use Working With Skills?

Working With Skills fits situations like: you are about to call any skill- tool; asked to author; edit a shared skill; troubleshoot why a skill write was rejected.

How do I install Working With Skills in Claude Code?

Run `npx skills add PostHog/posthog --skill working-with-skills -a claude-code`. Or copy the skill folder (products/skills/skills/working-with-skills in PostHog/posthog) into .claude/skills/working-with-skills in your project. Claude Code loads it when a task matches its description.

How do I install Working With Skills in Codex?

Run `npx skills add PostHog/posthog --skill working-with-skills -a codex`. Or copy the skill folder (products/skills/skills/working-with-skills in PostHog/posthog) into .agents/skills/working-with-skills in your project. Codex loads it when a task matches its description.

Can I use Working With Skills 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 PostHog/posthog --skill working-with-skills -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/working-with-skills, .gemini/skills/working-with-skills, .github/skills/working-with-skills and .opencode/skills/working-with-skills in your project.

What does Working With Skills need to run?

SKILL.md names no scripts, command-line tools or credentials: Working With Skills is instructions for the agent only. Our summary lists: Python 3.

Does Working With Skills access the network?

SKILL.md names 1 domain. As links in the text: agentskills.io. This is read from the text; nothing was executed.

Is Working With Skills 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 Working With Skills use?

Working With Skills has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Working With Skills use?

About 4.4k tokens (SKILL.md is roughly 18k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 3.4k tokens, read only when the agent opens those files.

What are the alternatives to Working With Skills?

Skills that share tags, products or a category with Working With Skills: Why (fmflurry/settings-opencode, 171 stars), Prepare Cloudflare Production Deployment (LubomirGeorgiev/cloudflare-workers-nextjs-saas-template, 786 stars), UModel Skill Runner (alibaba/UnifiedModel, 415 stars) and Codflow Setup (bighadj22/codflow, 354 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Working With Skills?

PostHog (a GitHub organization, an official publisher) maintains it in PostHog/posthog, which has 40,209 GitHub stars. The repository holds 254 skills in this directory. The repository was last updated on October 10, 2026.

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