dearlordylord/5e-quint/dnd-srd-oracle
Claude Code and agent skill by dearlordylord/5e-quint
- community
Checking that the SKILL.md file is still in the repository.
Explore and use this project's redistributable 5.5e SRD catalog through character creation, character sessions, and battles. Use for requests to inspect available SRD options, make or continue a character, start or continue a battle, ask what can happen next in an existing 5.5e SRD Oracle journey, or determine whether this engine can execute user-authored content; do not use for general D&D rules, history, lore, or other unrelated discussion.
Install
npx vskill@latest install dearlordylord/5e-quint/dnd-srd-oracleSKILL.md
Consult 5.5e SRD Oracle
Establish the user's immediate goal. Use the relevant discovery or read operation before making a stateful choice unless the current MCP result already supplies the required facts.
Read describe_mcp_workflow for this connection's tool names and argument patterns; reuse a guide already returned by the same connection. Select operations from that guide and the current response's routing information.
Distinguish browsing installed catalog presence from asking which choices are currently legal for a character. Use catalog tools for browsing; create or resume a Play Session and use returned character-creation holes for legal draft choices.
Create a Play Session for a new journey. Retain its application-provided playSessionId and pass it in every stateful call without asking the user to manage it during ordinary use. Resume an existing journey with read_play_session when its handle is available in context.
Public Play Sessions require standard MCP OAuth and are saved from creation. Let the tool's OAuth challenge start account linking; never request a password, API key, token, or unrelated permission in conversation. Local stdio Play Sessions need no sign-in and last only for that server process. Use list_saved_play_sessions for explicit public recovery and never silently select a saved session. Treat delete_saved_play_session as immediate and permanent.
For a character-creation continuation, use read_play_session first. If its summary does not contain the detailed remaining choices, call get_character_creation_choices with the retained draft identity before asking the user to choose.
Treat returned catalog records, character-creation holes and options, battle acts, runtime holes, projections, and operation results as authoritative. Copy their identifiers and typed inputs exactly. Never invent an executable choice, fill, rule result, supported capability, or authored record.
For Battle setup, follow the returned battleState variant. If the result is initialInitiativeSetup, use the exposed Initiative-swap and setup-finalization operations before asking for or presenting active Battle Acts. For an active Battle, use the exposed add/remove-combatant operations for supported roster changes and keep the returned occupancy and settlement projections authoritative.
For Battle Acts, use chatGptBattleOperations when the response supplies it to select the current Act or Reaction. For an Act marked ready, choose its labeled readyCalls entry, copy its arguments unchanged, and add the selected playSessionId to open its pending inputs. Copy the opaque actKey exactly; the server resolves the current selection. For tableFactsRequired, copy its arguments and supply its requiredArguments from the table. When presentation.kind is attack, show presentation.name and distinguish the returned damage selections; the ready call already retains the complete selection. Answer ordinary holes through provide_battle_input with a fill and no subject. Select a Reaction through its named operation with an interruptDecision fill and no subject. For a reactionRollOrDamageReduction choice, include the rolledDice fill requested by that choice's initialHoles in choice.fills; use [] when it requests no roll. Other Reaction choices use choice.fills: [] and request any later ordinary inputs through provide_battle_input. The pending transaction owns the parent.
Use the current hole's fact request and its matching chatGptBattleOperations.inputs[].fillSchema to construct the complete fill. Copy its pinned kind and holeId, and supply only fields admitted by that request. For a point-origin Sphere, originAnchor: { kind: "tableSelectedPoint" } represents the point chosen by the table's geometry; use a combatant anchor only when the table chose that combatant's position. A rolled Saving Throw includes its actual d20TestRoll; withoutRoll applies only when no roll was required. Supply an explicit empty collection only when the table confirms there are no requested facts to report. After a rejected fill, correct the input and retry the returned hole. If the response lacks an actionable request, read the Battle state again. Use cancel_battle_action only when the returned availability permits it, copying its arguments with expectedSelectionId. Cancellation is limited to an unanswered player Act before accepted input or committed effects. Respect a cancellation refusal and continue from the returned request. If recovery remains blocked, explain the missing input and preserve the saved checkpoint.
roll_dice is an optional independent raw-face request. It has no Battle Hole or modifier context and never updates Battle state by itself. Copy its ordered faces into an ordinary typed fill only when the current Runtime Hole requests that shape; otherwise ask for the missing user/table fact.
Use the returned Battle checkpoint for HP, resources, and applied effects. A needsHoles result leaves a procedure unfinished. Report changes already in its checkpoint, including committed Reactions, and describe the requested outcome as pending until the engine applies it. Keep any external simulation separate from saved Battle progress. A narrated victory is not a stored result.
Build map HP and event displays from returned checkpoints and applied outcomes. Label table-supplied positions as table facts, and distinguish proposed movement or spell areas from engine-confirmed changes. Preserve that distinction when the engine does not store coordinates.
Present relevant returned rules facts faithfully. Ask only for unresolved user decisions or requested rolls. When the current result contains multiple independent meaningful choices, present them together and let the user answer them in one reply; do not serialize independent current holes into one question per turn. Keep dependent choices for a later batch when their options have actually been returned. Apply forced single-option choices automatically and report them. Synthetic names, situations, and narration may frame play, but must not create mechanics or reproduce non-SRD official content.
After every operation, report the returned result and relevant state. For Play Session operations, also report the projection, unresolved inputs, next operations, and restoration status from the envelope. Continue automatically only when doing so does not take a meaningful choice away from the user. A pause should collect the largest currently valid batch of independent user decisions, not merely the first unresolved hole.
When a Play Session is unavailable, explain that the service cannot access the handle, follow the returned new-session restoration guidance, and never claim why it is absent or silently replace it.
If asked to import or execute user-authored records, state that this MCP uses only its installed redistributable SRD catalogs. Do not invent an admission path or pass invented record data to a stateful tool.
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingplugins/dnd-srd-oracle/skills/dnd-srd-oracle/SKILL.md
Popularity
- 7-day trend score
- 0
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/dearlordylord/5e-quint/dnd-srd-oracle)