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

Dogfood

by exceptionless in exceptionless/Exceptionless

Systematically dogfood Exceptionless locally. An agent skill from exceptionless/Exceptionless.

Apache-2.0Auto-check passedFrontend & Design

Install Dogfood

skills CLI
$ npx skills add exceptionless/Exceptionless --skill dogfood -a claude-code

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

GitHub CLI
$ gh skill install exceptionless/Exceptionless dogfood --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/exceptionless/Exceptionless.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/dogfood .claude/skills/dogfood && 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
dogfood
GitHub stars
2.5k
Token cost
~759 tokens
SKILL.md length
305 words
Files
1
Skills in repo
11
Repo updated
First seen
Licence
Apache-2.0

At a glance

Systematically dogfood Exceptionless locally. An agent skill from exceptionless/Exceptionless.

  • Asked to dogfood
  • SKILL.md covers Setup, Workflow, Evidence Rules and Report Format, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Exploratory test

What it does

Dogfood is an agent skill from exceptionless/Exceptionless. Systematically dogfood Exceptionless locally. Use when asked to dogfood, QA, exploratory test, bug hunt, browser-test, or validate frontend/full-stack behavior in this repo. Start from the AppHost/Aspire local URLs and use the Svelte application. External Exceptionless URLs require an explicit user-provided URL and confirmation.

Its SKILL.md is about 760 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 Frontend & Design. It works with Svelte. The repository describes itself as: Exceptionless application. The licence is Apache-2.0.

When your agent uses it

  • Asked to dogfood
  • Exploratory test
  • Validate frontend/full-stack behavior in this repo

Example prompts

  • “/dogfood”

What it can do on your machine

Read from SKILL.md and the folder at commit 300e8ca. 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.

    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

Dogfood loads about 759 tokens when it runs. Until then it costs about 85 tokens; SKILL.md has 305 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~85
When it runs · the whole SKILL.md, loaded when a task matches
~759

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 exceptionless/Exceptionless at commit 300e8ca, republished under its Apache-2.0 licence (© exceptionless). 305 words, ~759 tokens.

Download SKILL.mdSave it as .claude/skills/dogfood/SKILL.md (or your agent's skills folder).
name
dogfood
description
Systematically dogfood Exceptionless locally. Use when asked to dogfood, QA, exploratory test, bug hunt, browser-test, or validate frontend/full-stack behavior in this repo. Start from the AppHost/Aspire local URLs and use the Svelte application. External Exceptionless URLs require an explicit user-provided URL and confirmation.

Dogfood

Systematically explore Exceptionless as a local user, find issues, and produce a concise report with reproducible evidence.

Setup

Local targets:

The Svelte app at / is the only application UI. Exercise primary hash URLs when testing incoming-link compatibility, then verify they resolve to the root routes without losing the session.

  • Aspire dashboard: https://ex.dev.localhost:7101

  • Svelte app: https://web-ex.dev.localhost:7131/

  • API health check: https://api-ex.dev.localhost:7111/api/v2/about

  • API health fallback for command-line tools with local TLS issues: http://api-ex.dev.localhost:7110/api/v2/about

  • Start the app with aspire run or the AppHost before testing.

  • Probe the API health check before browser work.

  • Store evidence under ./dogfood-output/ unless the user provides another workspace-local path.

  • Use the available browser automation tool for local browser interaction when one is exposed in the session.

  • Test localhost by default. Use an external Exceptionless URL only when the user explicitly provides that URL and confirms external testing for the current task.

If the app is not running, start it or report the infrastructure blocker. Do not skip QA just because infrastructure is initially down.

Workflow

1. Health check   Confirm local API responds
2. Initialize     Create output dirs/report
3. Authenticate   Sign in if the tested flow requires it
4. Orient         Capture the starting page and navigation
5. Explore        Walk realistic workflows
6. Document       Save evidence as each issue is found
7. Wrap up        Summarize severity, repro steps, and residual risk

Evidence Rules

  • Interactive or stateful bugs need step-by-step repro notes and screenshots; video is useful when timing or multi-step interaction matters.
  • Static visible issues, such as clipped text or layout breakage on load, only need a screenshot and the viewport details.
  • Capture console/network errors when they explain the user-visible issue.
  • Write findings as you discover them so interruptions do not lose context.
  • Keep evidence files; do not delete or rewrite history mid-session.

Report Format

For each finding include:

  • Severity: P0, P1, P2, or P3
  • Area / URL
  • Environment: local URL, browser, viewport
  • Repro steps
  • Expected result
  • Actual result
  • Evidence file paths
  • Notes on console/network errors, if relevant

Prefer 5-10 well-documented issues over a long vague list.

Scope

Test the changed surface first, then adjacent critical workflows. Never use production data. Production URLs require an explicit user-provided URL and confirmation.

© exceptionless, 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 .agents/skills/dogfood of exceptionless/Exceptionless.

Open the folder on GitHubat commit 300e8ca

Compare with similar skills

Dogfood 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.

Dogfood compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Dogfood this skillexceptionless/Exceptionless2.5k—~759Automated safety check: PassApache-2.0
GSAP Core Animationgreensock/gsap-skills16k4 repos~3.7kAutomated safety check: PassMIT
GSAP in Vue, Nuxt and Sveltegreensock/gsap-skills16k4 repos~2.6kAutomated safety check: PassMIT
Svelte Core Best Practicesrilldata/rill2.9k4 repos~1.8kAutomated safety check: PassApache-2.0
Boneyard0xGF/boneyard7.5k—~2.2kAutomated safety check: NotesMIT
Kill AI Slopyetone/kill-ai-slop1.3k—~1.4kAutomated safety check: PassApache-2.0

Similar skills

  • GSAP Core Animation

    greensock/gsap-skills

    Covers the GSAP core API for tweens, easing, staggers, defaults and matchMedia, and when to choose GSAP over CSS animations or other JavaScript animation libraries.

    16k GitHub starsUsed in 4 repos~3.7k tokens
    Frontend & DesignAuto-check passed

  • GSAP in Vue, Nuxt and Svelte

    greensock/gsap-skills

    Shows how to use GSAP in Vue, Nuxt, Svelte and other lifecycle-based frameworks: create after mount, scope selectors to the component, and revert on unmount.

    16k GitHub starsUsed in 4 repos~2.6k tokens
    Frontend & DesignAuto-check passed

  • Svelte Core Best Practices

    rilldata/rill

    Rules for writing idiomatic Svelte 5 code: when to reach for runes like state, derived and effect, and how to handle props, attachments and bindings.

    2.9k GitHub starsUsed in 4 repos~1.8k tokens
    Frontend & DesignAuto-check passed

  • Boneyard

    0xGF/boneyard

    Use boneyard-js to add, configure, debug, or rebuild skeleton screens.

    7.5k GitHub stars~2.2k tokensUpdated 1 mo ago
    Frontend & DesignAuto-check: notes

  • Kill AI Slop

    yetone/kill-ai-slop

    Find and remove AI slop — the generic, machine-default visual and copy tics of vibe-coded products — from a web project.

    1.3k GitHub stars~1.4k tokensUpdated 23 days ago
    Frontend & DesignAuto-check passed

  • Uncodixfy

    pdsuwwz/chatgpt-vue3-light-mvp

    Prevents generic AI/Codex UI patterns when generating frontend code.

    578 GitHub starsUsed in 2 repos~3k tokens
    Frontend & DesignAuto-check passed

More from exceptionless/Exceptionless

All 11 skills in this repo

  • Emil Design Eng

    exceptionless/Exceptionless

    This skill encodes Emil Kowalski's philosophy on UI polish, component design, animation decisions, and the invisible details that make software feel great.

    2.5k GitHub starsUsed in 28 repos~6.8k tokens
    Auto-check passed

  • Shadcn Svelte

    exceptionless/Exceptionless

    Manages shadcn-svelte components and projects — adding, updating, fixing, debugging, styling, and composing UI.

    2.5k GitHub stars~3.6k tokensUpdated today
    Auto-check passed

  • Aspire Diagnostics

    exceptionless/Exceptionless

    Inspect local Aspire resource health, logs, traces, and browser telemetry.

    2.5k GitHub stars~769 tokensUpdated today
    Auto-check passed

  • Foundatio Repositories

    exceptionless/Exceptionless

    Query, aggregate, patch, or paginate Exceptionless data through its Elasticsearch repository abstractions.

    2.5k GitHub stars~1.9k tokensUpdated today
    Auto-check passed

  • Releasenotes

    exceptionless/Exceptionless

    Evaluate semantic-version impact and generate formatted changelogs from git history since the last release tag.

    2.5k GitHub stars~1.2k tokensUpdated today
    Auto-check passed

  • Tanstack Form

    exceptionless/Exceptionless

    Build Svelte forms with TanStack Form, Zod validation, and API error mapping.

    2.5k GitHub stars~544 tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Dogfood

What does Dogfood do?

Systematically dogfood Exceptionless locally. An agent skill from exceptionless/Exceptionless. Dogfood is an agent skill from exceptionless/Exceptionless. Systematically dogfood Exceptionless locally.

When should I use Dogfood?

Dogfood fits situations like: asked to dogfood; exploratory test; validate frontend/full-stack behavior in this repo.

How do I install Dogfood in Claude Code?

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

How do I install Dogfood in Codex?

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

Can I use Dogfood 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 exceptionless/Exceptionless --skill dogfood -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/dogfood, .gemini/skills/dogfood, .github/skills/dogfood and .opencode/skills/dogfood in your project.

What does Dogfood need to run?

SKILL.md names no scripts, command-line tools or credentials: Dogfood is instructions for the agent only.

Does Dogfood 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 Dogfood 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 Dogfood use?

Dogfood 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 Dogfood use?

About 759 tokens (SKILL.md is roughly 3k 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 Dogfood?

Skills that share tags, products or a category with Dogfood: GSAP Core Animation (greensock/gsap-skills, 16k stars), GSAP in Vue, Nuxt and Svelte (greensock/gsap-skills, 16k stars), Svelte Core Best Practices (rilldata/rill, 2.9k stars) and Boneyard (0xGF/boneyard, 7.5k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Dogfood?

exceptionless (a GitHub organization) maintains it in exceptionless/Exceptionless, which has 2,457 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on October 8, 2026.

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