agentleFS
Sign inStart free
malinskibeniaminmalinskibeniamin/skills/dogfood/SKILL.md

dogfood

Skill4 starsChanged 13 days agoMITView on GitHub

Use after each material behavior slice and before handoff or shipping to exercise runnable work at its real entrypoint.

78 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use dep-refs, feature-boundary-planner and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • betacatslingSkill

    dep-refs

    Use when needs to inspect TypeScript export references in the z-code workspace, list exports from a file, verify whether an export is unused before deletion, investigate who imports a symbol during refactors, or combine pnpm knip unused-export results with pnpm dep:refs symbol-level reference tracing.

    Also in 5 projects that use this

  • betacatslingSkill

    feature-boundary-planner

    Map a ZCode behavior change to current UI surfaces, state owners, protocol commands, persistence, and validation. Use for impact analysis, product-boundary planning, or an implementation handoff grounded in the checked-out source.

    Also in 5 projects that use this

  • lir-navcooSkill

    yuanbao

    Yuanbao (元宝) groups: @mention users, query info/members.

    Also in 18 projects that use this

  • Cartograf666Skill

    architecture-governance

    Bootstrap, document, enforce, and review a project's architecture through layer responsibilities, dependency direction, architecture manifests, legacy baselines, Change Envelopes, cross-layer approval policy, and deterministic architecture checks. Use when starting a project, auditing an existing codebase, planning cross-layer work, preventing architecture erosion, reviewing structural changes, or deciding whether implementation may expand into another layer.

    Also in 5 projects that use this

  • john-data-chenSkill

    touchdesigner-mcp

    Control a running TouchDesigner instance via twozero MCP — create operators, set parameters, wire connections, execute Python, build real-time visuals. 36 native tools.

    Also in 7 projects that use this

  • math-incSkill

    minecraft-modpack-server

    Set up a modded Minecraft server from a CurseForge/Modrinth server pack zip. Covers NeoForge/Forge install, Java version, JVM tuning, firewall, LAN config, backups, and launch scripts.

    Also in 5 projects that use this

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 78 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Run use -> abuse -> repair -> replay.

    line 20
  2. Distinctive:

    Use representative live-scale data (production-like shape/cardinality).

    line 26
  3. Very specific:

    If a project-local verify-* skill exists, use its doctor, drive, evidence, and cleanup.

    line 73

“Common” is measured: kept by at least 6 in 10 of the 78 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

For behavior/verifier checks, read Poteto.

Dogfood each material runnable slice and final PR at public seams. Tests are not dogfood.

Inventory

  1. Resolve the comparison base with BASE=$(PR_BASE_REF="${DOGFOOD_BASE_REF:-}" "${CLAUDE_PLUGIN_ROOT:-.}/scripts/resolve-pr-base.sh").
  2. Inspect the full PR: merge-base through committed, staged, unstaged, and untracked work.
  3. Cover changed runnable branches at real entrypoints, including skill resources/scripts and hook events. Standalone docs, tests and evals need no experiential coverage.

Loop

Run use -> abuse -> repair -> replay.

Use

Exercise intended paths; inspect output, transitions, effects, console, network and logs.

Use representative live-scale data (production-like shape/cardinality); compare expected/observed counts, ordering, timing, state and effects; expose accumulation.

For bugs, replay the reporter's exact steps unfixed. If you cannot reproduce it, request missing environment or evidence before diagnosis.

Abuse

Try one credible break:

  • Careless: empty, invalid, oversized, duplicate, or reordered input.
  • Impatient: repeat, double-submit, reload, navigate away, cancel, or interrupt.
  • Unlucky: stale or missing data, slow or failed dependency, partial completion.
  • Live data: sparse fields, duplicate IDs, mixed versions or tenants, long text, Unicode, timezone boundaries, realistic cardinality.
  • Performance: measure response time, network, render, CPU, and memory against a baseline or budget.

Observe failure and recovery.

UI content/layout risks: Call the Skill tool with "break-ui". Reuse schema-valid fixtures and evidence in replay/receipt; test only uncovered cases. Keep invalid-input validation separate.

Repair

Defects fail. When automatable, add a RED public-contract test, fix via /tdd, and rerun focused checks. Edits invalidate evidence.

Replay

At the real entrypoint, repeat intended use and every break attempt. For bugs, replay identical steps and adjacent behavior. Use replay packets for stateful bugs or recurring repro gaps. PASS binds to the current runnable state.

Entrypoints

ChangeExercise
Web/UIRun, navigate, act, reload, inspect console/network
CLI/TUIInvoke realistic, invalid, and interrupted flows
API/workerSend real requests/events; inspect response and side effects
LibraryCall the public API from a minimal consumer
Hook/automationTrigger the actual event with representative fixtures
Skill/agentUse on a fresh realistic task and inspect behavior
Demo/prototypeOperate until the question has observed evidence

Fresh agents require explicit delegation.

If a project-local verify-* skill exists, use its doctor, drive, evidence, and cleanup. T3 Code checkout UI only: resolve native context, then load web/desktop or native mobile. Missing Browser/Device tools mean BLOCKED, not installing or switching harnesses. Verifier drift routes to /maintain-verification-skill; a recurring missing path routes to /create-verification-skill after proof.

React: runtime probes.

Receipt

Verdict: PASS | FAIL | BLOCKED; entrypoint/actions/observations:

  • Entrypoint: exact command/URL/event/consumer.
  • Actions: journey and break attempts.
  • Observations: data, outputs, state, effects, console/network/logs, timing.
  • Repairs: defects, RED tests, fixes, replay result.
  • Limits: untried behavior and reason.

PASS: direct evidence per behavior; FAIL: observed defect; BLOCKED: missing access, environment, hardware or safety condition.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free