Repository navigation
Conversation
Remove disable-model-invocation from the unslop frontmatter. The description says the skill must always apply, but the flag limited it to an explicit /unslop call. The agent can now select unslop on its own when it writes prose. Name and description are unchanged. No other skill's flag changes. Co-authored-by: lauren <poteto@users.noreply.github.com>
Patch release for the unslop model-invocation fix. Co-authored-by: lauren <poteto@users.noreply.github.com>
4 of 5 tasks
This treatment is as strange as adding disable-model-invocation to unslop. It was originally expected that this PR would be replaced by #396, but #396 has been closed. So which is the final repair PR? -- Delete only one line of simple switches. Cursor's issue management looks very chaotic🤔. |
fmal
added a commit
to fmal/dotfiles
that referenced
this pull request
Sep 27, 2026
file-pr now writes the title and body with technical-writing, then applies unslop, and runs code-simplifier over the diff before commit. The GOOD examples now pass both skills. Local exception in technical-writing and unslop: drop `disable-model-invocation: true`. The Claude Code Skill tool refuses a skill with that flag unless the user typed its name this turn. A skill body never counts as typed, so file-pr could not reach either skill. Upstream PR cursor/plugins#379 proposes the same change for unslop. Also drop "Must always apply" from the unslop description. With the flag gone, that sentence would load the full skill on nearly every turn.
nexxeln
added a commit
to nexxeln/oc-pstack
that referenced
this pull request
Oct 2, 2026
Adopts cursor/plugins#379 by poteto as a port patch until it merges upstream.
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
3 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.
Why
The
unslopdescription says "Must always apply." The frontmatter said the opposite.disable-model-invocation: truelimited the skill to an explicit/unslopcall, so the agent could not select it on its own when it wrote prose. PR #300 added the flag to five skills at once. This PR removes it fromunsloponly.Scope
pstack/skills/unslop/SKILL.md. Remove thedisable-model-invocation: trueline.nameanddescriptionare unchanged. The body is unchanged.pstack/.cursor-plugin/plugin.json. Version0.15.2to0.15.3.Blast Radius
Two lines. After the plugin updates, the agent can auto-select
unslopfrom its description./unslopstill works as before. Skills that cite unslop by name (poteto-mode,technical-writing,teach,recall,blast-radius,show-me-your-work,automate-me) are not affected.Verification
rg -n 'disable-model-invocation' pstack/skills/unslop/SKILL.mdreturns nothing.plugin.jsonreports0.15.3.node scripts/validate-plugins.mjsprints "All plugins validated successfully." withajvandajv-formatsinstalled as the CI workflow installs them.git diff --stat origin/main...HEADis two files, one insertion, two deletions.