> ## Documentation Index
> Fetch the complete documentation index at: https://docs.gofastskill.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Inspecting and Exporting Results

> Drill into step artifacts to understand what changed, and export the best skill document.

# Inspecting and Exporting Results

## Inspect a step

After a run completes (or while it's running), use `inspect` to see exactly what happened at any step:

```bash theme={null}
fastskill optimize inspect .skillopt/runs/<timestamp> --step 7
```

This prints all artifacts for step 7 by default (`--show all`):

* **Patch** — the JSON diff the optimizer proposed
* **Skill diff** — a unified diff of the skill document before and after
* **Gate scores** — the before/after scores that drove the accept/reject decision
* **Skips** — any eval cases that were skipped this step (e.g. due to timeout)

### Show only what you need

```bash theme={null}
# Show only the unified diff
fastskill optimize inspect .skillopt/runs/<timestamp> --step 7 --show diffs

# Show only gate scores
fastskill optimize inspect .skillopt/runs/<timestamp> --step 7 --show gate

# Show only the patch JSON
fastskill optimize inspect .skillopt/runs/<timestamp> --step 7 --show patches

# Show skipped cases
fastskill optimize inspect .skillopt/runs/<timestamp> --step 7 --show skips
```

`--show` options:

| Value           | Output                                                            |
| --------------- | ----------------------------------------------------------------- |
| `all` (default) | Everything: patch, diff, gate scores, skips                       |
| `patches`       | The raw JSON patch the optimizer proposed                         |
| `diffs`         | Unified diff of `skill_before.md` vs `skill_after.md`             |
| `gate`          | Gate scores JSON (before/after scores and accept/reject decision) |
| `skips`         | Cases skipped in this step                                        |

### Interpreting gate scores

A typical `gate_scores.json` looks like this:

```json theme={null}
{
  "score_before": 0.67,
  "score_after": 0.74,
  "delta": 0.07,
  "epsilon": 0.02,
  "accepted": true,
  "trials": 3
}
```

If `delta < epsilon`, the patch is rejected. If the step was rejected, the skill document is rolled back to the `skill_before.md` state.

### Finding a step to inspect

Use `status` to read the history table first, then pick the step with the largest positive delta or the last accepted step before a regression:

```bash theme={null}
fastskill optimize status .skillopt/runs/<timestamp>
```

***

## Export the best skill

When you're happy with the results, export the best skill document to your skills directory:

```bash theme={null}
fastskill optimize export .skillopt/runs/<timestamp> --out skills/my-skill/SKILL.md
```

This copies `best_skill.md` from the run directory to the destination path. Parent directories are created if they don't exist. The output is byte-identical to the run directory copy.

**Note:** `best_skill.md` is the highest-scoring skill document seen across all accepted steps — not necessarily the final step. If the last few steps were rejected, `best_skill.md` reflects the best earlier checkpoint.

***

## Comparing multiple runs

To compare two runs side by side:

```bash theme={null}
# Check final best score for each
fastskill optimize status .skillopt/runs/run-A
fastskill optimize status .skillopt/runs/run-B

# Diff the best skill documents directly
diff \
  .skillopt/runs/run-A/best_skill.md \
  .skillopt/runs/run-B/best_skill.md
```

***

## Artifacts reference

Every step directory contains the same set of files:

| File               | Description                                                     |
| ------------------ | --------------------------------------------------------------- |
| `patch.json`       | Structured patch proposed by the optimizer agent                |
| `gate_scores.json` | Before/after scores, delta, epsilon, accept/reject, trial count |
| `skips.json`       | Array of case IDs skipped this step (timeout, error, etc.)      |
| `skill_before.md`  | Full skill document text before applying the patch              |
| `skill_after.md`   | Full skill document text after applying the patch               |

Top-level run files:

| File                 | Description                                                 |
| -------------------- | ----------------------------------------------------------- |
| `optimize.toml`      | Provenance copy of the config used for this run             |
| `runtime_state.json` | Current best score, epoch, global step (updated live)       |
| `history.json`       | Array of step records: step index, accepted, scores, tokens |
| `best_skill.md`      | The best skill document seen across all accepted steps      |

***

## See also

* [Running and monitoring](/optimize/running)
* [Configuration reference](/optimize/configuration)
* [Skill Optimization overview](/optimize/overview)