@shadowclone/cli 0.0.28 → 0.0.29

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/README.md CHANGED
@@ -53,11 +53,12 @@ To add the plugin, run `/plugin install shadowclone@shadowclone` after `/plugin
53
53
 
54
54
  ## Skills in the box
55
55
 
56
- Shadowclone bundles 14 workflow skills. Pick them in the wizard.
56
+ Shadowclone bundles 15 workflow skills. Pick them in the wizard.
57
57
 
58
58
  | Skill | Loads when |
59
59
  | ----------------------------- | --------------------------------------- |
60
60
  | `choose-by-consequence` | A change adds a skip or fallback |
61
+ | `guided-pr-review` | You want a guided PR walkthrough |
61
62
  | `design-deep-modules` | You design a module |
62
63
  | `diagnose-before-editing` | The cause of a failure is unknown |
63
64
  | `plan-with-review-page` | A change has many steps |
@@ -72,6 +73,15 @@ Shadowclone bundles 14 workflow skills. Pick them in the wizard.
72
73
  | `verify-review-findings` | A pull request has review comments |
73
74
  | `write-plain-english` | You write text for a person (always on) |
74
75
 
76
+ To pick skills without the CLI, run `npx skills add theonly1me/shadowclone`.
77
+ Use `--skill guided-pr-review shadowclone-review` to install guided review and its local reviewer.
78
+ The separate `@shadowclone/skills` npm artifact contains the same portable skills and supporting files.
79
+ See [manual installation](docs/guides/skills.md#install-skills-without-shadowclone).
80
+
81
+ The guided review skill creates an HTML reading route with real diffs, behaviour traces, and inline notes.
82
+ It connects related changes across PRs and identifies each change's PR.
83
+ See [guided reviews](docs/guides/reviews.md#guided-review-with-your-agent).
84
+
75
85
  ## Results
76
86
 
77
87
  Across 24 fixed tasks, Shadowclone learning scored above existing user skills on all four models. Scores measure preference adherence on synthetic tasks. See [setups, methods, and limits](evals.md).