Skip to content

Tools

Tools164 free tools that run in your browser.PDF toolsMerge, split, compress and convert PDFs.Image toolsCompress, convert, resize and make ID photos.Audio & videoTrim, convert and record audio and video.Text toolsCount, clean, compare and convert text.Developer toolsJSON, encoding, network and security utilities.CSS & designGradients, shadows, colours and layout CSS.CalculatorsEveryday numbers, dates and conversions.AddressForgeGenerate, copy and export sample addresses in 18 countries and regions.

Games

GamesBoard and card games, ready in one click.Board gamesChess, Go, Xiangqi and 14 more. Play a friend online.Card gamesSolitaire, Hearts, Spades and 40+ classics.MahjongSichuan Blood Battle mahjong for four: swap three, void suit, room codes and a leaderboard.Dou DizhuThree-player Dou Dizhu online: call and rob the landlord, room codes and a leaderboard.GuandanFour-player Guandan in two teams: levels, wild cards, tribute, room codes and a leaderboard.Flying ChessFour-player Flying Chess online: random tables, room codes and a leaderboard.Animal ChessAnimal Chess (Jungle) online against a person or the computer.One More CastAn ink-painting fishing game made for a grandfather: read the float, play the fish, fill the fishbook.

Create & choose

CreatorsRead public TikTok data and download TikTok or Instagram videos.VPS pickerDescribe your project. Get a VPS shortlist.

More

TarotA card reading as a prompt for reflection.Skill RankDiscover and compare AI agent skills.CiteProofCheck a bibliography against real records.SaySee how Korean, Japanese, Chinese, French and English are really pronounced.HACKERSWord clouds, competition guides and Kaggle mind maps for beginners.Pelosi IndexA live graph of politicians, insiders and funds and what they disclose, plus research Skills.

Read & talk

BlogPractical guides with sources.CommunityReviews, recommendations and red flags.
Account

When not to auto-invoke a skill: disable-model-invocation and paths

Skill Rank2026-10-02PocketPlay Editorial4 min readUpdated 2026-10-09

A practical guide to Cursor's disable-model-invocation and paths frontmatter — when a skill should stay slash-only, when to scope it to files, and which Skill Rank entries help you write safer triggers.

Most Agent Skills are meant to wake up when the task matches their description. That is useful until a skill that deploys, commits, or spends money also wakes up because a sentence looked similar. On 2 October 2026, Cursor's Agent Skills docs make the escape hatch explicit: set disable-model-invocation: true so the skill only loads when you type /skill-name, and use paths when guidance should only appear for matching files.

Demand for this corner of the skill ecosystem is real but focused. In the past week, X recent-post counts for agent/cursor/claude skills language totalled about 3.7k posts (non-retweet query checked 2026-10-02). A narrower query tying skills to Cursor/Claude and invoke/auto language was about 770. That is enough signal for a control guide, not a hype roundup.

What auto-invocation actually does

Cursor discovers skills from project and user skill directories (.cursor/skills/, .agents/skills/, and the Claude/Codex compatibility paths). The agent sees available skills and decides relevance from context — mainly the skill description. Manual /skill-name still works for any skill. Auto-invocation is the default.

That default is right for research, drafting, and checklists. It is wrong for side-effect workflows where a false positive is expensive.

Use disable-model-invocation: true for side effects

Cursor documents the field in SKILL.md frontmatter:

---
name: deploy-staging
description: Deploy the app to staging. Invoke only when the user explicitly asks to deploy.
disable-model-invocation: true
---

When true, the agent will not auto-apply the skill from context. You must invoke it with /deploy-staging (or attach it as a Custom Mode for a whole session). Cursor's own /migrate-to-skills converts slash commands into skills with this flag set, so migrated commands keep their explicit-only behaviour.

Good candidates for slash-only:

  1. Deploy, publish, or ship — anything that changes a live environment.
  2. Commit, open a PR, or merge — git and review side effects.
  3. Send a message or charge money — external actions you want to approve every time.
  4. Destructive cleanups — delete, reset, force-push helpers.

Keep auto-on for skills that only advise, draft, or inspect without writing irreversible state.

Use paths when the skill is file-shaped

paths (glob list or comma-separated string) limits when the skill is surfaced. Cursor only offers it while the agent works with matching files. Nested project skills under e.g. apps/web/.cursor/skills/ are automatically scoped to that directory — similar to setting paths by hand.

Example:

---
name: react-component-patterns
description: Conventions for React components in this codebase.
paths:
  - "**/*.tsx"
  - "packages/ui/**/*.ts"
---

Use paths when the skill is true only for certain languages or packages. Do not use it as a substitute for disable-model-invocation on deploy skills: file scope still allows auto-invocation inside that scope.

A short decision tree

SituationPrefer
Repeatable advice, no side effectsAuto-on (default)
Side effects / money / publishdisable-model-invocation: true
Conventions for one language or apppaths (or nested skill folder)
Need the skill for the whole chatCustom Mode (Option/Alt+Enter) after explicit pick

Write the trigger into description either way. Auto-on skills need a sharp description so they do not steal unrelated turns; slash-only skills still need a clear description so humans can find them in /.

Skills already on Skill Rank that help

These are already listed on Skill Rank — no catalog add required for today's post:

  • using-agent-skills (addyosmani/agent-skills) — how to live with the skill model day to day.
  • write-a-skill (mattpocock/skills) — authoring habits that keep triggers honest.
  • skill-creator (anthropics/skills) — Anthropic's SKILL.md authoring workflow.
  • writing-skills (obra/superpowers) — another pass on scope and clarity.

If you are tightening an existing skill, start by editing frontmatter before rewriting the whole body: one boolean and a few globs often fix noisy auto-invocation.

Limits of this note

  • Field names and behaviour follow Cursor docs checked 2026-10-02; other agents may use different activation rules (the Agent Skills spec discussion around standardising disable-model-invocation is still open).
  • X counts are recent-search volume, not Google search demand or Skill Rank rankings.
  • Stars on a catalog row do not prove a skill is safe to auto-invoke — read the skill, then decide the frontmatter.

Sources & checks

How we write and check articles: Editorial method

More from Skill Rank

All articles

From rules to skills: create, migrate, and find Agent Skills that stick

Turn ad-hoc agent rules into portable SKILL.md packages: write them well, migrate with Cursor's /migrate-to-skills, find installs via skills.sh, and read before you trust.

Pick a code-review skill without installing five of them

Agent skills chatter stays busy; code-review skills top many install lists. A 3 October 2026 guide to matching one Skill Rank entry to your review habit — not stacking every reviewer you find.

Where should an Agent Skill live: project vs user scope?

Cursor loads skills from project folders and user-global folders differently. A 4 October 2026 guide to picking .cursor/skills vs ~/.cursor/skills — and what actually syncs to Cloud Agents.

Graphify, Ponytail, Playwright CLI: what the rising agent skills actually install

Google Trends on 5 Oct 2026 shows Graphify, Ponytail and Playwright CLI rising with 'agent skills'. Here is what each installs (hooks, always-on rules, global files), the official sources, and how to remove them.

Taste Skill, Emil Kowalski's skills, awesome-design-md: which design add-on does what

Google Trends on 6 Oct 2026 shows 'taste skill', 'emil kowalski design skill' and 'awesome design md' rising with Claude skills. What each one is, how big it is, how to install it, and which problem it fits.

What is pstack? Lauren Tan's /poteto-mode for Cursor, explained

pstack was a rising 'agent skills' search on 7 Oct 2026. What Lauren Tan's Cursor plugin installs, what /setup-pstack writes, how to keep /poteto-mode on, and how to cut its token cost.

Have a follow-up question?

Reviews, recommendations and red flags from people who tried it.

Open the community