fix(ralph-wiggum): rename dir to pi-ralph-wiggum so SKILL name matches (#12)#29
Merged
Merged
Conversation
#12) Pi expects a skill's frontmatter `name` to match the parent directory. The in-repo directory was `ralph-wiggum/` but the npm-installed directory is `pi-ralph-wiggum/` (matching the package name `@tmustier/pi-ralph-wiggum`). The SKILL.md `name: ralph-wiggum` therefore never matched the installed directory, producing a `[Skill conflicts]` warning on every `pi` startup for anyone who installed from npm — and every `pi update` would overwrite a manual patch. Rename the repo directory to `pi-ralph-wiggum/` and set SKILL.md `name: pi-ralph-wiggum` so both the in-repo and installed layouts pass validation. Also rename the README's 'Install' heading to 'Installation' so the skill validator stops warning. Minor bump (0.1.7 → 0.2.0): breaking only for git-source users who referenced `~/pi-extensions/ralph-wiggum/…` in their pi config; npm users are unaffected. Closes #12. Thanks to @ishanmalik for reporting.
🔍 Tessl Skill Review
|
| Dimension | Score | Detail | Suggestion |
|---|---|---|---|
| conciseness | ██░ 2/3 | Mostly efficient but includes some unnecessary content. The task file format template and best practices section are redundant with the loop behavior section. The user commands list is comprehensive but could be more compact. | Add explicit validation checkpoints and error recovery steps in the Loop Behavior section (e.g., what to do if an iteration fails, how to detect and recover from stuck states). |
| actionability | ███ 3/3 | Provides concrete tool invocations with specific parameters, exact command syntax for user commands, and a clear task file format template. The ralph_start call is copy-paste ready with documented parameters. | Consolidate the 'Best Practices' section into the 'Loop Behavior' section to reduce redundancy—items like 'update checklist' and 'capture verification evidence' are already mentioned in the workflow steps. |
| workflow clarity | ██░ 2/3 | The loop behavior steps are listed but lack explicit validation checkpoints. Step 3 mentions 'record verification evidence' but there's no feedback loop for what to do if verification fails. For an iterative development loop involving many discrete steps, the absence of error recovery guidance is a gap. | |
| progressive disclosure | ██░ 2/3 | Content is structured with clear sections, but everything is inline in a single file. The user commands section and task file format template could potentially be referenced separately. , moderate length so this is a minor issue. |
Optional: add a Tessl API token as TESSL_API_TOKEN in your repo secrets. The action will suggest an optimized version automatically in future PRs.
Owner
Author
Automated review (pr-reviewer subagent)Findings
Verdictneeds attention — the implementation looks sound and no leftover old path references, but the release notes understate a real breaking change introduced by renaming the skill itself. |
Addresses pr-reviewer P2: the skill rename changes the public /skill:<name> identifier for all users (npm and git), not just git-source users with a custom path.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Fixes #12.
Problem
Pi validates that a skill's frontmatter
namematches its parent directory. The in-repo dir isralph-wiggum/but the npm-installed dir ispi-ralph-wiggum/(matches the package name@tmustier/pi-ralph-wiggum). Withname: ralph-wiggum, anyone installing from npm saw this on every startup:And because
pi updatere-downloads the package, manual patching didn't stick.Fix
Rename the in-repo dir
ralph-wiggum/→pi-ralph-wiggum/and set SKILL.mdname: pi-ralph-wiggumso validation passes in both layouts.Validated locally with the freshly-published
[email protected]validator:$ ./extending-pi/skill-creator/scripts/validate_skill.py ./pi-ralph-wiggum Skill is valid!Incidental cleanup
While in the README, renamed the
## Installheading to## Installationso the skill validator stops warning about it (same validator, unrelated pre-existing warning).Impact
pi install npm:@tmustier/pi-ralph-wiggum) — no action needed; package name is unchanged.~/pi-extensions/ralph-wiggum/…in their pi config should update the path to~/pi-extensions/pi-ralph-wiggum/…. Minor bump (0.1.7 → 0.2.0) signals this.Changes
git mv ralph-wiggum/ pi-ralph-wiggum/(history preserved via rename detection)pi-ralph-wiggum/SKILL.md—name: pi-ralph-wiggumpi-ralph-wiggum/README.md—## Install→## Installation, config snippet pathspi-ralph-wiggum/package.json—directory,homepagepackage.json—pi.extensions/pi.skillspathsREADME.md— table + example configpi-ralph-wiggum→ 0.2.0pi-extensions→ 0.1.32Credit: thanks to @ishanmalik for reporting in #12.