logs

Data Community

Repo stars 330
License MIT
Author repo claude-skill-registry

Interpretation is structured for decision-making; original keeps the upstream SKILL.md unchanged.

Decide Fit First

Core job: View shella daemon and plugin logs. Use when debugging issues, checking what happened, or monitoring plugin output. View daemon…
Best fit: Use it when the task has reusable inputs, steps, and validation criteria rather than a one-off answer.
Avoid forcing it: If the source lacks commands, platform support, or external-service evidence, keep those fields unknown instead of guessing.

Design Intent

Structure: The skill is organized around “Arguments”, “Log File Location”, “Commands”, “Output”, showing how the author expects the agent to judge fit, collect context, and produce verifiable output.
Trigger evidence: Prioritize the author’s wording around when to use it, what context to collect, and what output shape to produce.
Evidence boundary: Author text states facts, repository files prove commands and paths, and Fluxly only adds fit, limits, and usage judgment.

How To Use It

Inputs: Provide target material, scope, expected result, forbidden changes, and validation method.
Invocation: Name logs directly; if the source includes slash commands, start with the command and then add task context.
Validation: Start small and check whether the result follows “Arguments / Log File Location / Commands” before expanding.

Boundaries And Review

Dependencies: It usually needs no extra API key, so start with a small validation task.
Permissions: Declared permissions include read / shell-exec; ask the agent to state file, command, and rollback boundaries before acting.
Quality bar: A useful result names the deliverable, evidence, and next action. Generic prose means the task needs tighter context.

Shella Logs

View daemon and plugin logs from ~/.local/state/shella/dev.log.

Arguments

$ARGUMENTS may contain:
- A plugin name to filter by (e.g., "agent", "terminal")
- A number of lines to show (default: 50)
- "all" to show more lines
- "errors" or "error" to filter to errors/warnings only

Log File Location

~/.local/state/shella/dev.log

Each line is JSON with fields: time, level, prefix, msg, and optional data fields.

Commands

Recent logs (last 50 lines):

tail -50 ~/.local/state/shella/dev.log

Filter by plugin (prefix field contains plugin name):

grep '"prefix":"agent' ~/.local/state/shella/dev.log | tail -50

Errors only:

grep '"level":"error"' ~/.local/state/shella/dev.log | tail -50

Parse and format for readability - extract time, prefix, level, msg:

tail -50 ~/.local/state/shella/dev.log | while read line; do
  echo "$line" | python3 -c "import sys,json; d=json.loads(sys.stdin.read()); print(f'{d.get(\"prefix\",\"daemon\"):20} {d.get(\"level\",\"info\"):5} {d.get(\"msg\",\"\")}')" 2>/dev/null || echo "$line"
done

Output

Present logs in a readable format. For JSON lines, extract the key fields (timestamp, prefix, level, message). Highlight errors in your response.

If the log file doesn't exist, tell the user the daemon hasn't been run yet or logs are empty.

Fluxly profile Author and license come from source; runtime, permissions, and network are Fluxly detections or estimates

Fluxly category: Data
Author-declared agents: No explicit declaration found; this is not inferred or tested compatibility
Static check: 94 / 100 · heuristic scan, not runtime safety proof
Author / version / license: @majiayu000 · MIT
Fluxly token estimate: Lean
Fluxly setup estimate: Guided setup
External API key: No requirement detected
Detected OS requirements: Unspecified
Runtime requirements: Unspecified
Detected file/system behavior: Read-only
Shell exec
Detected network behavior: Local-only
Install commands: None (reference only)

Profile is derived at build time from SKILL.md and install vectors. Subject to drift from author intent.

Heads up: 未限定 allowed-tools，默认拥有全部工具权限。

Output preview logs.preview

The current SKILL.md does not define a fixed output example.

SKILL.md SKILL.md

# Shella Logs

View daemon and plugin logs from `~/.local/state/shella/dev.log`.

## Arguments

- `$ARGUMENTS` may contain:
  - A plugin name to filter by (e.g., "agent", "terminal")
  - A number of lines to show (default: 50)
  - "all" to show more lines
  - "errors" or "error" to filter to errors/warnings only

## Log File Location

```
~/.local/state/shella/dev.log
```

Each line is JSON with fields: `time`, `level`, `prefix`, `msg`, and optional data fields.

## Commands

**Recent logs (last 50 lines)**:
```bash
tail -50 ~/.local/state/shella/dev.log
```

**Filter by plugin** (prefix field contains plugin name):
```bash
grep '"prefix":"agent' ~/.local/state/shella/dev.log | tail -50
```

**Errors only**:
```bash
grep '"level":"error"' ~/.local/state/shella/dev.log | tail -50
```

**Parse and format** for readability - extract time, prefix, level, msg:
```bash
tail -50 ~/.local/state/shella/dev.log | while read line; do
  echo "$line" | python3 -c "import sys,json; d=json.loads(sys.stdin.read()); print(f'{d.get(\"prefix\",\"daemon\"):20} {d.get(\"level\",\"info\"):5} {d.get(\"msg\",\"\")}')" 2>/dev/null || echo "$line"
done
```

## Output

Present logs in a readable format. For JSON lines, extract the key fields (timestamp, prefix, level, message). Highlight errors in your response.

If the log file doesn't exist, tell the user the daemon hasn't been run yet or logs are empty.

Evidence boundary and execution chain

Author text anchors workflow facts; Fluxly only indexes current sections, terms, files, and commands.

sections -> Arguments → Log File Location → Commands → Output
terms    -> Recent logs (last 50 lines) · Filter by plugin · Errors only · Parse and format
files/cmd -> ~/.local/state/shella/dev.log · $ARGUMENTS · time · level · prefix · msg
body sha256 -> bcce1b986a14