Files
awesome-copilot/skills/signal-write/SKILL.md
T
Jenny Ferries 0673e59169 fix: address second review — agent path, display name, signal subtype
- plugin.json: use ./agents/workshop-ta.md path format (matches all other plugins)
- workshop-ta front matter: name 'Workshop TA' preserves acronym (was 'workshop-ta')
- signal-write: add subtype field (hands-up/blocked/done/checkpoint/partnership)
  so dashboard consumers can distinguish specific signal states
- npm run build: regenerated docs/README.agents.md

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Copilot-Session: 26faf13e-639c-4a21-ac05-c0dc2bff7c62
2026-07-17 11:38:08 -07:00

113 lines
3.4 KiB
Markdown

---
name: signal-write
description: 'Emit structured agent signals — hands-up, blocked, done, checkpoint, partnership. Signals are written as JSON to .signals/ for dashboard consumption and noted in the journal for persistence.'
---
# Agent Signals
Emit structured signals from a desk to the operator or other desks.
## When to use
- A desk needs operator attention (hands-up, blocked)
- Work is complete and ready for review (done)
- Significant progress worth noting (checkpoint)
- Two desks disagree and can't resolve it (hands-up)
- The TA is reporting coordination quality (partnership)
## Signal types
### `hands-up`
Two desks disagree and can't settle it against external facts.
This is the system working — the operator reads where desks
*disagree*, not where they perform confidence.
### `blocked`
A desk can't proceed without input — missing access, ambiguous
scope, need a decision only the operator can make.
### `done`
Work is complete and ready for review. Artifacts are on the bench.
### `checkpoint`
Significant progress worth the operator knowing about, but work
continues. Not blocked, not done — just a marker.
### `partnership`
Used by the TA (room coordinator) to report coordination quality.
Self-assessment scores reflect coordination, not code accuracy:
- **intent** — understood what the operator needed
- **confidence** — right work went to the right desks
- **accuracy** — dispatched work produced the right outcome
- **completeness** — nothing fell through the cracks
## How to emit
### 1. Write a JSON signal file to `.signals/`
This is the primary output — it's what the dashboard reads.
Create `desks/<desk-name>/.signals/<timestamp>.json`:
```json
{
"signal_type": "execution",
"subtype": "checkpoint",
"agent_name": "<desk-name>",
"self_assessment": {
"intent": 4,
"confidence": 5,
"accuracy": 4,
"completeness": 3
},
"patterns": {
"what_worked": "description of what went well",
"what_was_hard": "description of challenges",
"skill_gap": "areas for improvement"
},
"escalation": {
"reason": null,
"blocked_on": null,
"recommendation": null
}
}
```
### Signal type mapping
| Signal | `signal_type` | `subtype` |
|-----------|-----------------|----------------|
| hands-up | `"escalation"` | `"hands-up"` |
| blocked | `"escalation"` | `"blocked"` |
| done | `"execution"` | `"done"` |
| checkpoint| `"execution"` | `"checkpoint"` |
| partnership| `"partnership"` | `"partnership"`|
The `subtype` field preserves the specific signal state for
dashboard consumers. `signal_type` controls sort priority
(escalation → top).
### 2. Note the signal in the journal
Also append a short marker to the desk's journal for persistence:
```markdown
## <date> — [signal:<type>] <summary>
- <key details>
```
The journal note is the trail marker. The JSON file is the
machine-readable signal.
## Principles
- Signals are structured, not chatty. Short, factual, actionable.
- hands-up is not failure — it's the most valuable signal. It
means the system caught something one frame alone would have
missed.
- Don't signal for routine progress. Signals are for state
changes that affect the room, not status updates.
- blocked means truly blocked — not "I'd prefer input." If you
can proceed with a reasonable default, proceed and note it.
- Self-assessment scores should be honest, not optimistic. A 3/5
is fine. A 5/5 on everything is suspicious.