skill-creator
Guides authoring, reviewing, and validating agent skills (SKILL.md + metadata.json + references/ + scripts/) in this Capgo skills repository and similar ones. Covers trigger and negative-trigger design, lean SKILL.md with a when-to-load reference index, traps over basics, verification and error-handling sections, version tagging of facts, subagent-oriented skills (main-agent vs subagent split), optional whentouse frontmatter, inline snapshots with allowed-tools, skillgrade evals, and this repo's canonical skills/ to plugins/ mirroring and registration. Use when creating a new skill, tightening a skill's description or triggers, splitting a long skill into references, or fixing bun run lint-skills failures. Do not use for app documentation, README or marketing copy, or library code that is not a skill.
- Installs
- 684
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/cap-go/capgo-skills --skill skill-creator- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads skill-creator automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Skill Authoring
Write skills that load at the right moment, teach what the model does not already know, and prove their own results.
When to Use
TRIGGER when:
- The user creates a skill directory, or asks to improve, review, or split an existing skill.
- A skill triggers too often, too rarely, or collides with a sibling skill.
bun run lint-skillsfails, or a skill must be registered in a plugin or the marketplace.- The user wants a skillgrade eval for a skill.
Do not use when:
- The user is writing app docs, a README, a changelog, or marketing copy.
- The user is editing library or plugin source that is not a skill.
Reference Index
Only load a reference when its topic is in play.
| File | Load when |
|---|---|
references/repo-layout.md | Adding, renaming, or registering a skill in this repository, mirroring into plugins/, or reading lint errors |
references/authoring-patterns.md | Writing the body: trigger design, reference index, traps, verification, version tags, subagent skills, inline snapshots |
Procedure
1. Scope the skill
- Write one sentence: "Load this when <concrete situation>, so the agent can <outcome>."
- List the sibling skills that could also match. Each one becomes a negative trigger.
- Split the skill if it covers two unrelated workflows. Merge it if it would be a one-paragraph stub.
- Ask the user at real judgement calls (scope, audience, which product to prefer). Do not ask about things you can read from the repo.
2. Write the frontmatter
---
name: my-skill # lowercase, hyphenated, equals the folder name
description: <what it does>. Use when <symptoms, APIs, file names, error strings>. Do not use for <case> (sibling-skill).
---
- The description is the only text the router sees. Put concrete triggers in it: command names, config keys, file names, exact error strings. Name the sibling skills in the negative clause.
- Keep it to one line and at most 1024 characters (lint enforces both).
- Optional
when_to_use:is appended todescriptionin Claude Code's skill listing. The combined text is truncated at 1,536 characters, so put the key use case first. Other agents ignore it, so never move the core trigger out ofdescription. allowed-tools:only when the skill runs inline commands. Keep it minimal and read-only.
3. Write a lean body
Target fewer than about 250 lines. Use this order:
- One-line purpose, plus a version line ("Checked against X 8.77, October 2026").
## When to Use: TRIGGER bullets and aDo not use whenlist that points to sibling skills by name. Lint requires the## When to Useheading.## Reference Index: a table of each file and when to load it, with "Only load a reference when its topic is in play."## Procedure: numbered steps. Inspect before you edit, and report findings before invasive changes.## Traps: the non-obvious failures. Skip basics the model already knows.## Verification: exact commands or checks that prove success.## Error Handling: exact error strings mapped to fixes.
Move dense tables, long code, and per-topic depth into references/<topic>.md, one level deep. Put fragile or repetitive logic in scripts/.
4. Fact-check everything
- Verify every command, flag, config key, and API against source or official docs. Prefer the package's
--help, its type definitions, or its repo over memory. - Tag time-sensitive facts with versions ("Capacitor 8.5+", "Xcode 27", "CLI 8.77"). Gate optional behavior on feature detection when the targets can be older.
- If you cannot verify a fact, write "check current docs" and do not guess. List any commands that do not exist but are commonly hallucinated.
5. Match command context
- Skill prose uses standard
npm/npxexamples. Capacitor and Capgo CLI examples usenpx ...@latest. - Use
bun/bunxonly for this repository's own development and CI commands, or in Bun-specific skills. - When a skill edits another repository, tell the agent to read that repository's instructions and follow its package-manager policy.
6. Preserve secrets
When a skill edits user files, tell the agent never to replace user-provided tokens, keys, certificates, or passwords with placeholders unless asked. Placeholders are for new generic examples only. Do not suggest rotating secrets unless the user asks.
7. Register and validate (this repo)
Follow references/repo-layout.md: canonical folder in skills/, metadata.json, an entry in package.json skills, exposure through a plugin folder plus .claude-plugin/marketplace.json, then bun run sync-skills and bun run lint-skills.
8. Add an eval when behavior must not regress
Use skillgrade (eval.yaml + graders/). Prefer deterministic graders for structure. Use an LLM rubric only for qualitative judgement. Run it with bun run lint-skills-skillgrade, or ENABLE_SKILLGRADE=1 with an API key during lint.
Traps
- A vague description ("Helps with X") never triggers. A greedy one ("Use for anything about mobile") steals sibling requests.
- An index entry like "see references/" with no load condition makes the agent read everything or nothing. Always say when.
- Stale facts age faster than structure. Put the version line at the top so reviewers know what to re-check.
- Editing a mirrored copy under
plugins/<plugin>/skills/is wrong. Edit the canonicalskills/<name>/, then sync. - Inline
!command`` snapshots run on every load. Keep them guarded (fs.existsSync), fast, short in output, and read-only.
Verification
bun run lint-skillspasses. It checks the name against the folder, the description length, the## When to Useheading, validmetadata.json, marketplace exposure, and byte-identical mirrors.wc -l skills/<name>/SKILL.mdis about 250 or less, and every file inreferences/is named in the Reference Index.- A grep for each command in the skill matches the tool's
--helpor source. - Mental routing test: three prompts that should trigger the skill do, and one prompt for each sibling skill does not.
Error Handling
| Lint message | Fix |
|---|---|
<skill>: name "<x>" does not match folder name | Make the frontmatter name equal the directory |
<skill>: description exceeds 1024 characters | Cut filler, keep concrete triggers and the negative clause |
<skill>: missing usage guidance | Add a ## When to Use heading |
<skill>: missing metadata.json / invalid metadata.json | Create or fix the JSON (see references/repo-layout.md) |
claude marketplace: skill "<x>" is not exposed by any plugin | Create plugins/<plugin>/skills/<x>/, then bun run sync-skills |
mirrored skills: ... (run bun run sync-skills) | Run bun run sync-skills. Never hand-edit the mirror |
<plugin>: unknown skill "<x>" | The plugin folder has no matching skills/<x>. Create the canonical skill or remove the folder |
FAQ
What does the skill-creator skill do?
Guides authoring, reviewing, and validating agent skills (SKILL.md + metadata.json + references/ + scripts/) in this Capgo skills repository and similar ones. Covers trigger and negative-trigger design, lean SKILL.md with a when-to-load reference index, traps over basics, verification and error-handling sections, version tagging of facts, subagent-oriented skills (main-agent vs subagent split), optional whentouse frontmatter, inline snapshots with allowed-tools, skillgrade evals, and this repo's canonical skills/ to plugins/ mirroring and registration. Use when creating a new skill, tightening a skill's description or triggers, splitting a long skill into references, or fixing bun run lint-skills failures. Do not use for app documentation, README or marketing copy, or library code that is not a skill.
How do I install skill-creator?
Run npx skills add https://github.com/cap-go/capgo-skills --skill skill-creator in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/skill-creator/ (personal) or .claude/skills/skill-creator/ (project).
Which AI agents can use skill-creator?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is skill-creator safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains skill-creator?
It is published by cap-go in cap-go/capgo-skills. It has 684 recorded installs.
More from cap-go/capgo-skills
capacitor-best-practices
cap-go/capgo-skills
Review and set up Capacitor apps against current best practices (Capacitor 8.5 stable, 9 alpha via @next). Use for a Capacitor codebase review, capacitor.config.ts audit, new project setup, aligning @capacitor/core/cli/ios/android and plugin majors, plugin patterns (availability checks, checkPermissions/requestPermissions, error code handling, web fallbacks), or release prep; or on " " plugin is not implemented on ios, Could not find the web assets directory, platform has not been added yet, a dev server.url shipped to production, lost edits in android/app/src/main/assets/public, SPM vs CocoaPods, or AppDelegate/UIScene drift. Do not use for security audits (capacitor-security), performance (capacitor-performance), tests (capacitor-testing), crashes (debugging-capacitor), major upgrades (capacitor-app-upgrades), SPM migration (cocoapods-to-spm), UIScene adoption (capacitor-uiscene-migration), or live updates (capgo-live-updates).
ionic-design
cap-go/capgo-skills
Builds and reviews Ionic Framework UI in Capacitor apps (Ionic 9 current, Ionic 8 still common) - page structure (ion-header/ion-content/ion-footer), lists, modern form syntax (label/labelPlacement on ion-input/ion-select), sheet modals, tabs + ion-router-outlet, CSS variable theming, dark palettes (palettes/dark.system.css, .ion-palette-dark), iOS vs MD mode, and Ionic 8 - 9 breaking changes (React Router 6, Vue Router 5, Angular 18-22 zoneless, removed ion-picker-legacy, boolean autocorrect, npx @ionic/migrate). Use when writing Ionic components, theming an Ionic app, fixing platform-mode styling, or upgrading @ionic/react, @ionic/vue, @ionic/angular. Do not use for Konsta UI (konsta-ui), Tailwind setup (tailwind-capacitor), raw safe-area CSS (safe-area-handling), keyboard resize (capacitor-keyboard), or Ionic Appflow/Enterprise migrations (ionic-appflow-migration, ionic-enterprise-sdk-migration).
capacitor-plugins
cap-go/capgo-skills
Pick, install, and wire up Capacitor plugins for native features (camera, filesystem, geolocation, biometrics, in-app purchases, social login, SQLite, calendar, contacts, health, BLE, NFC, etc.). Covers official @capacitor/ packages (Capacitor 8.5 stable, 9 alpha on next) plus the 145-package @capgo/ index, native permission keys (Info.plist, AndroidManifest, variables.gradle minSdk), npx cap sync / cap ls verification, and errors like '"Camera" plugin is not implemented on ios', 'unable to find plugin', UNIMPLEMENTED, and OS-PLUG- codes. Use for "which plugin should I use for X", adding a plugin, or a plugin call failing after install. Do not use for push setup (capacitor-push-notifications), splash assets (capacitor-splash-screen), keyboard layout (capacitor-keyboard), deep links (capacitor-deep-linking), OTA updates (capgo-live-updates), upgrading plugin source code (capacitor-plugin-upgrades), or adding SPM to a plugin (capacitor-plugin-spm-support).
debugging-capacitor
cap-go/capgo-skills
Diagnoses and fixes runtime bugs in Capacitor iOS/Android apps - white/blank screen on launch, startup crashes, "X" plugin is not implemented on ios/android, net::ERRCLEARTEXTNOTPERMITTED, App Transport Security blocks, CORS on capacitor://localhost, permission denials, live reload not connecting, and Capacitor 8.5+ UIScene regressions (appUrlOpen, universal links, pause/resume silent because AppDelegate callbacks stopped). Covers Safari Web Inspector, chrome://inspect, Xcode/LLDB, Android Studio, npx cap run --url (Capacitor 9) vs -l --host (8), xcrun simctl openurlprivacypush, xcrun devicectl device process launchopenURL, xctrace. Do not use for only reading device logs (ios-android-logs), the UIScene migration itself (capacitor-uiscene-migration), deep-link setup (capacitor-deep-linking), speed (capacitor-performance), crash SDKs (capacitor-native-observability), tests (capacitor-testing), or upgrades/build errors (capacitor-app-upgrades, cocoapods-to-spm).
capacitor-testing
cap-go/capgo-skills
Testing guide for Capacitor apps and plugins. Covers web-layer unit and component tests with Vitest and mocked Capacitor plugins (vi.mock('@capacitor/core'), registerPlugin), Playwright for the web build, Appium E2E with NATIVEAPP / WEBVIEW context switching, native plugin unit tests with Swift Testing vs XCTest (what can migrate, CAPPluginCall patterns, xcodebuild test on a simulator) and Android JUnit, plus an agent-driven verification loop on simulators and devices (build, install, launch, screenshot, UI hierarchy, tap, logs) with xcrun simctl, xcrun devicectl, adb, Xcode MCP device tools, and live reload via npx cap run --url (Capacitor 9) or -l --host --port (Capacitor 8). Use when adding tests, mocking plugins, "does it work on device", verifying a UI change on a simulator, migrating XCTest to Swift Testing, or setting up test CI. Do not use for crash log capture (ios-android-logs), WebView debugging sessions (debugging-capacitor), or build pipelines (capacitor
safe-area-handling
cap-go/capgo-skills
Fixes notch, Dynamic Island, home indicator, display cutout, and system bar overlap in Capacitor apps. Covers viewport-fit=cover + env(safe-area-inset-), the Capacitor 8 SystemBars core plugin (insetsHandling, injected --safe-area-inset- CSS variables for Android WebView < 140, removal of android.adjustMarginsForEdgeToEdge), Android 15/16 enforced edge-to-edge (overlaysWebView and backgroundColor of @capacitor/status-bar no longer work at targetSdk 36), iOS contentInset, and insets that change at runtime on rotation, iPad/foldable resizable windows. Use when headers sit under the status bar, tab bars hide behind the gesture bar, env() returns 0 on Android, or layout broke after upgrading to Capacitor 8 / targetSdk 35+. Do not use for keyboard overlap (capacitor-keyboard), Ionic/Konsta component theming (ionic-design, konsta-ui), Tailwind utility setup (tailwind-capacitor), or iOS multi-window/resizability adoption (capacitor-ios-resizability).
Popular ai & agents skills
google-agents-cli-publish
google/agents-cli
This skill should be used when the user wants to "publish an agent", "publish my ADK agent", "register an agent with Gemini", "publish to Gemini" (formerly Gemini Enterprise), or needs guidance on the agents-cli publish gemini command. Also use when the user wants to "manage agents in Agent Registry", "list/update/delete registered agents", or "register an MCP server". Covers ADK vs A2A registration modes, programmatic and interactive usage, flag reference, auto-detection from deployment metadata, Agent Registry fleet management, and troubleshooting. Part of the agents-cli skills suite. Do NOT use for deployment (use google-agents-cli-deploy).
google-agents-cli-eval
google/agents-cli
This skill should be used when the user wants to "run an evaluation", "evaluate my agent", "evaluate my ADK agent", "write an eval dataset", "analyze eval failures", "compare eval results", "optimize agent", or needs guidance on the Gemini platform eval methodology and the Quality Flywheel. Covers eval metrics, dataset schema, LLM-as-judge scoring, and common failure causes. Applies to any agents-cli project, whatever framework the agent is written in. Do NOT use for agent API code patterns (ADK: use google-agents-cli-adk-code), deployment (use google-agents-cli-deploy), or project scaffolding (use google-agents-cli-scaffold).
skill-creator
anthropics/skills
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
codex-pet
prime-skills/runcomfy-agent-skills
Codex Pet generator on RunComfy. Build a Codex-compatible Codex Pet spritesheet.webp + pet.json from a single reference image, drop it into ${CODEXHOME:-$HOME/.codex}/pets/ / and Codex picks it up as a custom Codex Pet next to the 8 built-ins. This skill produces the exact Codex Pet atlas Codex expects (1536x1872 PNG/WebP, 8 cols x 9 rows, 192x208 cells, 9 animation states — idle, running-right, running-left, waving, jumping, failed, waiting, running, review). Calls OpenAI GPT Image 2 edit ONCE via the local RunComfy CLI as runcomfy run openai/gpt-image-2/edit to produce a canonical Codex Pet pose, then assembles all 9 animation rows programmatically with ImageMagick micro-transforms — no Codex Pro, no $imagegen, no OPENAIAPIKEY required, only RUNCOMFYTOKEN. Triggers on "codex pet", "create codex pet", "make codex pet", "hatch codex pet", "/hatch image", "desktop pet codex", "codex pets", "spritesheet.webp", or any explicit ask to build a custom pet for OpenAI Codex.
full-output-enforcement
leonxlnx/taste-skill
Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.
executing-plans
obra/superpowers
Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available