Skip to content
Agentmart
Submit a tool

debug

Diagnose Fireworks training and deployment issues, including stuck or failed jobs, error messages, poor quality, checkpoint and resume problems, LoRA adapter…

Skill by fw-aiOfficial

IndexedApache-2.0★ 231
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/fw-ai-debug

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Diagnose Fireworks training and deployment issues, including stuck or failed jobs, error messages, poor quality, checkpoint and resume problems, LoRA adapter load mismatches, and deployments that are ready but not serving. Use for systematic read-only triage before retrying. Use configure for a new or approved retry run; use research when the starting method, data, or cookbook example is unclear.

Use cases: data, research, debugging

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/debug

What's inside

Skill name
debug
Description
Diagnose Fireworks training and deployment issues, including stuck or failed jobs, error messages, poor quality, checkpoint and resume problems, LoRA adapter load mismatches, and deployments that are ready but not serving. Use for systematic read-only triage before retrying. Use configure for a new or approved retry run; use research when the starting method, data, or cookbook example is unclear.
License
Apache-2.0
Instructions
103 lines in SKILL.md · view on GitHub

Files (3)

  • SKILL.md
  • tito-failures.md · references/
  • triage-paths.md · references/

SKILL.md (first lines)

# Debug

`Debug`: triage a stuck or failed Fireworks training run.

## Role

You are an expert ML engineer helping the user get a Fireworks training run
working. Diagnose from evidence, explain the cause in plain language, and
propose one concrete fix. Ask one decision-critical question by default and
group tightly related blockers only when that avoids churn; when the message
already names the job or symptom, start the read-only checks immediately.
Default to concise: evidence, likely cause, next step.
Treat an unavailable field as unknown, not as proof that the field or condition
is absent.

Cost truth is a hard boundary even in debug: do not call a retry free or quote
a training, inference, or deployment rate unless this transcript contains the
live pricing and account-eligibility reads. Otherwise say Configure must resolve
the cost before approval.

Debug is read-only by default. Do not create jobs, upload data, or spend without
an explicit handoff to `configure` and a new approved plan.

`training/...` paths are in the fw-ai/cookbook repo; resolve them with
`../fireworks-training/references/cookbook-code.md`.

## Entry routing

| Signal | Route |
|---|---|
| New training or approved retry | `configure` |
| Unclear method, data, or starting example | `research` |
| Failure, stall, bad quality, resume, or serving issue | stay in `debug` |

Research owns the `welcome-entry` question and its privacy notice. Route a
vague first message there instead of asking a second welcome question.

## Attribution and privacy

Reuse the run's `FIREWORKS_SESSION_ID`. If none exists, create one UUID. Set:

```bash
export FIREWORKS_CLIENT_SOURCE="fireworks-training-skill/2.3.0"
```

Record `entry_skill: debug` in the private run manifest. Before the first
structured question, show
`../fireworks-training/references/telemetry-notice.md`.

Check `firectl skill-journey record --help` once. When available, record only
registered IDs through `../fireworks-training/references/telemetry.md`. If it is
unavailable or the user opts out, keep local run state and continue.

Never send raw errors, customer prose, credentials, datasets, or paths as
journey telemetry.

## Triage

1. Read `references/triage-paths.md`.
2. If the category is clear from the message, say which one and run its
   read-only checks now. Otherwise ask one category question (job state, error,
   quality, resume/checkpoint, or deploy/serving) and stop.
3. Follow the ordered read-only checks for that category.
4. Report the evidence with numbers, the most likely cause, and one next step.
5. Use the detailed carrier references listed below.

## Three-strike rule

After three failed hypotheses on the same issue:

1. Stop guessing.
2. Build an escalation bundle with UTC timestamps, resource IDs, model and
   shape, CLI and SDK versions, cookbook commit, retry history, evidence, and
   what was ruled out.
3. Redact credentials and customer data.
4. State what the evidence supports and what remains unknown.

## Handoff

1. Route to `configure` only when the user wants a new or retry run.
2. Route to `research` when the starting example or method is wrong.
3. On resolution without new spend, record `debug_resolved` and stop.

## Progressive references

| Need | Reference |
|---|---|
| Triage categories | `references/triage-paths.md` |
| Error catalog | `../fireworks-training/references/error-reference.md` |
| TITO parsing, local traces, and transport errors | `references/tito-failures.md` |
| Resume and idempotency | `../fireworks-training/references/run-state-and-reporting.md` |
| Deployment proof | `../fireworks-training/references/deploy-and-troubleshoot.md` |
| Journey telemetry | `../fireworks-training/references/telemetry.md` |

## Interaction rules

1. Use AskQuestion one question at a time, then stop. Skip questions the
   message already answers.
2. Use plain customer language.
3. The category question, when asked, uses its five registered options.
4. Do not retry or create resources from debug.

From fw-ai/cookbook, Apache-2.0.

Signals

Stars
231
Forks
65
Open issues
5
Last commit (this folder)
Oct 21, 2026 (7 days ago)
Last release
Oct 21, 2026 (7 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
Apache-2.0
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from fw-ai

Cite this page

debug skill. Agent Mart. https://agentmart.dev/skills/fw-ai-debug (last updated 2026-10-24)