agentleFS
jammyfujammyfu/open-game-skills/skills/disciplines/debug-slate/SKILL.md

debug-slate

Skill12 starsChanged 22 days agoMITView on GitHub

Use when QA, capture, training, development, or automation modifies game state and the resulting evidence must record exactly which non-natural tools or overrides were active.

The file

Files
SKILL.md

Debug slate

Debug provenance is structured evidence, not merely an on-screen label.

Modes

ModeAvailability policy
offno QA/debug override is active for this session
labeled-devQA/debug tools may be active and every state change is recorded in structured provenance
shipping-hiddentools are removed, disabled, authenticated, or otherwise unavailable to normal play according to the shipping policy

These names are compatibility modes, not a requirement that every development build expose every debug verb.

Session record

Assign a stable session ID and record structured fields such as:

session ID
build ID + commit/version
save/profile provenance
active QA/debug tools or state overrides
activation/deactivation timestamps or logical ticks when relevant
linked capture/case IDs

save-integrity owns which profile/slot may persist synthetic state. gameplay-capture consumes this provenance when labeling evidence.

Rules

  1. Any state-changing QA/debug action appends structured provenance rather than relying on the reviewer noticing a visual overlay.
  2. Runtime debug UI availability is a project/build policy. Production may remove, disable, authenticate or hide tools; do not require every development build to expose every verb.
  3. Debug/training tools reuse live gameplay owners and clocks unless explicitly testing an alternate implementation.
  4. Modified-state evidence may prove a focused feature but cannot silently become proof of a natural progression/challenge path.
  5. Restart/load behavior must make clear whether the override persisted, was reapplied, or was cleared.

Accept

From the session ID a reviewer can recover the exact build, save provenance, active overrides and linked evidence, and distinguish natural state from QA-created state without inspecting implementation code.

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.