dongshuyan/compass-skills / skills/session-handoff-prompt
session-handoff-prompt
VerifiedCreate a concise continuation prompt that a fresh agent session can paste in to resume a long or degraded session. Use when the user asks for a handoff prompt, restart prompt, continuation prompt, context transfer, fresh-session resume, or a compact summary for opening a new session. Do not use for ordinary summaries, task-forest maintenance, durable user-profile updates, automatic session creation, code execution, or external publishing.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 6.8 KB |
| agents/openai.yaml | config | 246 B |
| evals/trigger-and-quality-cases.json | config | 1.2 KB |
| references/compression-modes.md | markdown | 1.3 KB |
| references/examples.md | markdown | 3.3 KB |
| references/output-contract.md | markdown | 2.5 KB |
| references/source-selection.md | markdown | 2.2 KB |
| references/task-forest-integration.md | markdown | 1.4 KB |
| scripts/local_paths.py | script | 976 B |
| scripts/project_session_events.py | script | 8.0 KB |
| scripts/read_task_forest_exports.py | script | 3.9 KB |
| scripts/redact_handoff.py | script | 2.1 KB |
| scripts/smoke_test_handoff.py | script | 9.3 KB |
| scripts/validate_handoff_prompt.py | script | 6.7 KB |
references/output-contract.md
View on GitHub# Output Contract
Default output has two parts:
1. The paste-ready continuation prompt.
2. A short note to the current user about mode, privacy, sources, and limitations.
## Paste-Ready Prompt
Use the user's language. Default to Chinese when unknown. The section labels may be translated, but the structure must remain stable:
```text
You are taking over an ongoing agent session. Resume from the context below. Do not re-open settled decisions unless current files or verified evidence contradict them. If this prompt conflicts with current workspace evidence, prefer current evidence and explain the conflict.
Workspace:
...
User goal:
...
Hard requirements:
...
Confirmed facts and decisions:
- [verified] ...
- [inferred] ...
- [unverified] ...
Task-forest state:
...
Completed:
...
Pending / needs verification:
...
Key files / commands / artifacts:
...
Do not repeat / do not do:
...
Next actions:
1. ...
2. ...
3. ...
```
Omit `Task-forest state` when no exports were read, or state that task-forest exports were not found.
The validator recognizes the English and Chinese headings above. For another language, pass the exact translated headings with `--labels-json <labels.json>`:
```json
{
"workspace": "Espacio de trabajo:",
"goal": "Objetivo del usuario:",
"requirements": "Requisitos obligatorios:",
"completed": "Completado:",
"pending": "Pendiente / por verificar:",
"next": "Próximas acciones:",
"fact_labels": ["[verificado]", "[inferido]", "[no verificado]"],
"task_forest": "Estado de task-forest:"
}
```
The six section keys are required. `fact_labels` and `task_forest` are optional.
## Fact Labels
- `[verified]`: user explicitly stated it, or it came from files, tool output, test output, task-forest exports, or another concrete source.
- `[inferred]`: reasonable inference from multiple sources, but not directly confirmed.
- `[unverified]`: important but currently unchecked, stale, conflicting, or based only on weak evidence.
Never write a model guess as `[verified]`.
## Current-User Note
After the prompt, add a short note outside the paste-ready block:
```text
Mode: balanced. Privacy: local. Sources: current conversation, task-forest exports, workspace files. You can ask for minimal or full.
```
For `shareable` privacy, state that local paths and credential-like strings were redacted.
If source coverage is weak, state the limitation clearly:
```text
Source limitation: no transcript file or task-forest export was available, so this prompt relies on the visible conversation and workspace evidence.
```
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 |