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/access-policy.md
View on GitHub# Access Policy
Read this file when deciding whether the public API-token skill can perform a
task.
## Authentication
- Use `Authorization: Bearer sa_pat_...`.
- The local token is loaded from `STINGRAY_PAT` or `~/.stingray/credentials`.
- The token must include `skills:full`.
- The public skill base URL is `https://stingray.fi/api/studio/v1`.
## Allowed Public Skill Surface
The current public skill is limited to the Studio Skills API route family:
- `POST /skills/actions`
- `GET /skills/runs/{run_id}`
- `GET /skills/requests/{client_request_id}`
Allowed actions:
- `idea.intake`
- `evidence.ground`
- `signal.design`
- `artifact.accept`
- `signal.replay`
- `signal.status`
- `idea.publish`
The token authenticates as one Studio user. The API still checks ownership for
Ideas, staged artifacts, Signals, Replays, and Publications.
## Explicitly Blocked
Do not attempt these through the public skill:
- API token creation
- trading, order placement, order cancellation, signing, transfer, or delegated wallet work
- Hyperliquid account authorization or account-risk operations
- monitor enablement, pause, resume, retirement, or lifecycle mutation
- billing, admin, guest lifecycle, internal routes, webhooks, tool-host routes, Slack install, or social posting
- X link-claiming or public posting
- browser Studio access outside the Skills API family
## Publication Boundary
`idea.publish` creates a public Studio Publication. Use it only when the user
explicitly asks for a public demo, share link, browser link, publish action, or
public artifact. If the user asks only for analysis, stop at the private Replay.
## Artifact Acceptance Boundary
`artifact.accept` is explicit confirmation, not an automatic side effect. In the
first slice it accepts only staged `signal_candidate` artifacts and creates a new
committed Signal. It does not update existing Signals, accept arbitrary artifact
kinds, or enable Monitors.
## Error Handling
- Missing, malformed, unknown, or revoked tokens are auth failures.
- Tokens without `skills:full` are insufficient-scope failures.
- Idea, artifact, Signal, Replay, or Publication resources outside the token
owner's boundary should be treated as unavailable.
- Do not echo token identifiers, raw tokens, token last-four metadata, or hidden
source metadata to the user.
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 | Unverified | 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 |