skill-trace-debugger

skill-trace-debugger221 wordsMITv1.0.0Repo-owned

skill-trace-debugger

Inspect eval manifests and portable validators for trace-friendly skill signals. Use when debugging skill invocation gaps. NOT for live LLM trace capture.

Quick Start

Install:

npx skills add github:wyattowalsh/agents --skill skill-trace-debugger -y -g --agent antigravity --agent claude-code --agent codex --agent crush --agent cursor --agent gemini-cli --agent github-copilot --agent grok --agent opencode

Use: /skill-trace-debugger <skill-name|repo> [--format json]

Works with Claude Code, Gemini CLI, OpenCode, and other agentskills.io-compatible agents.

Source & provenance

This page is generated from the repository file skills/skill-trace-debugger/SKILL.md by wagents docs generate.

What It Does

Surface trace and eval coverage gaps for repository skills before live behavioral runs.

Modes

$ARGUMENTS	Action
<name>	Trace readiness report for one skill
repo / --all	Fleet trace readiness summary
--format json	Machine-readable report
Empty	Show trace signal checklist

Critical Rules

1. Never claim live trace capture from static reports alone.
2. Treat missing explicit-invocation eval cases as a coverage gap, not a hard failure for internal skills.
3. Do not mutate eval manifests without maintainer approval.
4. Pair trace reports with skill-eval-scaffolder when adding new cases.
5. Keep prompts grounded in each skill’s dispatch table.

Public Metadata

Field	Value
Source Type	repo-owned
Display Source	github:wyattowalsh/agents
Source Kind	repo
Installability	portable command
Review State	reviewed
Target Agents	antigravity, claude-code, codex, crush, cursor, gemini-cli, github-copilot, grok, opencode

General

Field	Value
Name	skill-trace-debugger
License	MIT
Version	1.0.0
Author	wyattowalsh

Claude Code

Field	Value
Argument Hint	`[skill-name

View Full SKILL.md

---
name: skill-trace-debugger
description: >-
  Inspect eval manifests and portable validators for trace-friendly skill signals.
  Use when debugging skill invocation gaps. NOT for live LLM trace capture.
user-invocable: true
argument-hint: "<skill-name|repo> [--format json]"
license: MIT
metadata:
  author: wyattowalsh
  version: "1.0.0"
---

# Skill Trace Debugger

Surface trace and eval coverage gaps for repository skills before live behavioral runs.

**Scope:** Static trace readiness checks only. Does not execute live evals or harvest session logs.

## Dispatch

| $ARGUMENTS | Action |
|------------|--------|
| `<name>` | Trace readiness report for one skill |
| `repo` / `--all` | Fleet trace readiness summary |
| `--format json` | Machine-readable report |
| Empty | Show trace signal checklist |

## Trace Readiness Checklist

| Signal | Meaning |
|--------|---------|
| `evals/evals.json` | Behavioral cases exist for post-hoc grading |
| `scripts/check.py` | Portable validator contract is wired |
| explicit-invocation case | Eval includes a slash-command or named dispatch prompt |
| NOT-for boundary | Description names the correct alternate skill |

## Workflow

```bash
uv run python skills/skill-trace-debugger/scripts/trace_report.py <name>
uv run python skills/skill-trace-debugger/scripts/trace_report.py --all --format json
```

Route live trace grading to agent-eval-runner or maintainer CI workflows.

## Validation Contract

```bash
uv run python skills/skill-trace-debugger/scripts/check.py
```

## Critical Rules

1. Never claim live trace capture from static reports alone.
2. Treat missing explicit-invocation eval cases as a coverage gap, not a hard failure for internal skills.
3. Do not mutate eval manifests without maintainer approval.
4. Pair trace reports with skill-eval-scaffolder when adding new cases.
5. Keep prompts grounded in each skill's dispatch table.

Download from GitHub

Resources

Skill CatalogBrowse custom and external skills.

CLI ReferenceInstall and manage skills.

agentskills.ioThe open ecosystem for cross-agent skills.

---

View source on GitHub