epgstation
Skill0 starsChanged 4 days agoMITView on GitHub
EPGStation TV recording service. Use when: user asks about TV programs, schedules, recordings, or reservations. Controls EPGStation via REST API for browsing what's on TV, searching programs, managing recordings and auto-recording rules.
In this repository10 other files it gives its agents.
- AGENTS.mdAGENTS.md
- codex-model-profilesSkill
- cognitive-rhythm-writingSkill
- daikinSkill
- decoSkill
- japanese-tech-writingSkill
- piholeSkill
- popin-aladdinSkill
- stirling-pdfSkill
- switch2-controlSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 20
All timestamps are Unix time in milliseconds, not seconds.
- Very specific: line 21
Always pass isHalfWidth=true for readable Japanese text.
- Very specific: line 22
Default limit is 24; paginate with limit/offset.
- Distinctive: line 26
Search for a program first and show results before reserving it.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
EPGStation
Base URL: https://epgstation.msageha.net/api (EPGStation v2.10.0).
Key facts
- All timestamps are Unix time in milliseconds, not seconds.
- Always pass
isHalfWidth=truefor readable Japanese text. - Default
limitis 24; paginate withlimit/offset. - Genre IDs follow ARIB STD-B10 (see references/api-reference.md for the table).
- Confirm with the user before creating or deleting a reservation or rule, and before deleting a recorded program (irreversible).
- Search for a program first and show results before reserving it.
Core operations
| Task | Endpoint |
| Currently broadcasting | GET /schedules/broadcasting |
| Channel list | GET /channels |
| Channel schedule | GET /schedules/{channelId}?days=N |
| Program detail | GET /schedules/detail/{programId} |
| Search programs | POST /schedules/search |
| Reserve (by program or time range) | POST /reserves |
| List reservations | GET /reserves |
| Reservation detail / delete | GET, DELETE /reserves/{reserveId} |
| Reservation counts (conflicts/skips) | GET /reserves/cnts |
| Currently recording | GET /recording |
| List / search recorded | GET /recorded |
| Protect / delete recorded | PUT /recorded/{recordedId}/protect, DELETE /recorded/{recordedId} |
| Auto-recording rules | POST /rules, GET /rules, PUT /rules/{ruleId}/enable|disable |
Full request/response schemas and ready-to-run curl examples: see references/api-reference.md and references/commands.md.
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
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.