ref(skills): Standardize skill paths to Agent Skills spec#66
Open
szokeasaurusrex wants to merge 2 commits intomainfrom
Open
ref(skills): Standardize skill paths to Agent Skills spec#66szokeasaurusrex wants to merge 2 commits intomainfrom
szokeasaurusrex wants to merge 2 commits intomainfrom
Conversation
Removes `${CLAUDE_SKILL_ROOT}` usage and standardizes skill file references to `scripts/...`, `references/...`, and `assets/...` per the [Agent Skills specification](https://agentskills.io/specification).
Why:
- `${CLAUDE_SKILL_ROOT}` was introduced to address path confusion (PR #38 context).
- It was later copied across skills without consistently defining it.
- It is not part of the [Agent Skills specification](https://agentskills.io/specification).
Changes:
- Replace `${CLAUDE_SKILL_ROOT}/...` with skill-root-relative paths across affected skills.
- Keep iterate-pr's execution safety guidance (`run from repo root`; `invoke scripts using absolute paths`) while removing repeated variable usage.
- Update `README.md` and `AGENTS.md` path conventions.
- Update `skill-creator/scripts/quick_validate.py` to error on `${CLAUDE_SKILL_ROOT}`.
Risk: low (docs/guidance/validation only; script behavior unchanged).
szokeasaurusrex
commented
Feb 24, 2026
Warden correctly pointed out the original wording is confusing
lcian
approved these changes
Feb 24, 2026
![cursor[bot]](https://avatars.githubusercontent.com/in/1210556?s=60&v=4){kind=small}
There was a problem hiding this comment.
Cursor Bugbot has reviewed your changes and found 3 potential issues.
Bugbot Autofix is OFF. To automatically fix reported issues with Cloud Agents, enable Autofix in the Cursor dashboard.
|
|
||
| ```bash | ||
| uv run ${CLAUDE_SKILL_ROOT}/scripts/fetch_pr_checks.py [--pr NUMBER] | ||
| uv run scripts/fetch_pr_checks.py [--pr NUMBER] |
This comment was marked as off-topic.
This comment was marked as off-topic.
Sorry, something went wrong.
| ### Phase 4: Prompt Injection Analysis | ||
|
|
||
| Load `${CLAUDE_SKILL_ROOT}/references/prompt-injection-patterns.md` for context. | ||
| Load `references/prompt-injection-patterns.md` for context. |
This comment was marked as off-topic.
This comment was marked as off-topic.
Sorry, something went wrong.
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
2 participants
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.
Removes
${CLAUDE_SKILL_ROOT}usage and standardizes skill file references toscripts/...,references/..., andassets/...per the Agent Skills specification.Why
${CLAUDE_SKILL_ROOT}was introduced in #37 to help with path confusion. In that PR, the skill definition defined what the variable meant. Later, that variable appears to have been copied throughout all skills in this repo, without the proper definition, which is a problem, because the variable is not part of the Agent Skills specification, nor is it recognized by Claude Code per its docs.Changes
${CLAUDE_SKILL_ROOT}/...with skill-root-relative paths across affected skills, in compliance with the Agent Skills specification.iterate-prandskill-scannerskills, so that we still clearly indicate that agents need to run the skills within the Git repo, but without relying on a non-standard variable that might start popping up elsewhere without a proper definition.README.mdandAGENTS.mdpath conventions.skill-creator/scripts/quick_validate.pyto error on${CLAUDE_SKILL_ROOT}.