MantaDigital/stingray-agent-skills / skills/stingray
stingray
VerifiedTrading strategy builder for coding agents. Use when Codex, Claude, Cursor, or a SKILL.md host needs to turn a trading idea into market Evidence, an inspectable Signal, a private Replay, Replay status, or an opt-in Studio Publication. Stingray does not place trades.
| File | Kind | Size |
|---|---|---|
| LICENSE.txt | markdown | 11.1 KB |
| README.md | markdown | 4.3 KB |
| SKILL.md | skill md | 10.8 KB |
| prompts.md | markdown | 3.6 KB |
| references/access-policy.md | markdown | 2.3 KB |
| references/agent-positioning.md | markdown | 2.5 KB |
| references/business-capabilities.md | markdown | 2.8 KB |
| references/capabilities.json | config | 5.8 KB |
| references/co-development.md | markdown | 1.8 KB |
| references/data-coverage.md | markdown | 1.3 KB |
| references/examples.md | markdown | 3.2 KB |
| references/intent-rubrics.md | markdown | 1.9 KB |
| references/north-star-scenarios.md | markdown | 2.4 KB |
| references/replays-and-publications.md | markdown | 3.3 KB |
| references/signal-definitions.md | markdown | 1.8 KB |
| references/token-lifecycle.md | markdown | 1.5 KB |
| references/troubleshooting.md | markdown | 1.6 KB |
| references/workflows.md | markdown | 2.3 KB |
references/workflows.md
View on GitHub# Workflows
Task-oriented Studio Skills API sequences.
## Load Credentials
1. Read `STINGRAY_PAT` from the environment or `~/.stingray/credentials`.
2. Set `STINGRAY_API=https://stingray.fi/api/studio/v1`.
3. Use `Authorization: Bearer $STINGRAY_PAT`.
## Raw Thesis To Private Replay
1. `idea.intake`
2. `evidence.ground` when coverage or market context is unclear
3. `signal.design`
4. answer `needs_input` questions if returned
5. `artifact.accept` for a staged `signal_candidate`
6. `signal.replay`
7. `signal.status` or lookup routes if the Replay is long-running
8. summarize and stop private
## Raw Thesis To Public Demo
1. `idea.intake`
2. `signal.design`
3. `artifact.accept`
4. `signal.replay`
5. `signal.status` or lookup routes
6. `idea.publish`
Use this only when the user explicitly asked for a public demo or share link.
## Continue Existing Idea
1. Reuse the stored `idea_id`.
2. Choose the next action based on user intent.
3. If the previous response returned `questions`, retry the same action with
`answers`.
4. If the previous response returned `staged_artifact_ids`, use
`artifact.accept` only when acceptance is intended.
## Recover Long-Running Work
1. Use `GET /skills/runs/{run_id}` when available.
2. Use `GET /skills/requests/{client_request_id}` when only the caller recovery
key is available.
3. Use `signal.status` when the selected Signal is known.
4. Retry the action only after recovery confirms there is no useful active or
completed run.
## Hyperliquid Funding Replay
1. `idea.intake` with the funding thesis.
2. `evidence.ground` to confirm funding data coverage.
3. `signal.design`.
4. `artifact.accept`.
5. `signal.replay`.
6. Keep private unless the user explicitly asks for publication.
## Unsupported Hyperliquid Primitive
1. Identify whether the request depends on OI, whale, liquidation, or
mark-to-liquidation data.
2. Tell the user those primitives are not supported in the public skill today.
3. Offer the nearest supported funding-rate example.
4. Optionally produce a privacy-safe product feedback note.
5. Do not call `signal.design` for the unsupported primitive.
## Privacy-Safe Debug Report
1. Complete or stop the user task.
2. Summarize the mismatch in one short `Debug report:` line.
3. Exclude tokens, private account data, and full private prompts.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse 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 | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |