new-shareable-skill: move to standalone skills/operations/#2
Merged
Conversation
new-shareable-skill ships as a standalone catalog skill, not repo-local tooling. Authoring a shareable skill is itself a user-facing capability, so it is compiled + listed in the marketplace like any other skill. Only audit-skills stays in .agents/ (pure verification machinery). Reverses the .agents/ placement from PR #1 on user review. - skills/operations/new-shareable-skill/{SKILL.md,references/} moved - skills/operations/new-shareable-skill/.plugin.json added (marketplace manifest) - SKILL.md / placement.md reframed: standalone, not repo-local - quality-bar.md depersonalized the path example, softened gratuitous leak-pattern tokens - README.md +new-shareable-skill row, counts 14->15 / 9->10 - CONTRIBUTING.md, AGENTS.md point at the new path Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
new-shareable-skill picked up as a standalone skill-plugin; marketplace count 14 -> 15. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
DECISIONS.md: superseding entry -- new-shareable-skill ships standalone, not in .agents/; .agents/ is now specifically for non-user-facing verification / build machinery. Known-consequence note on audit-skills false positives from the skill's pattern documentation. KNOWLEDGE.md / STATE.md / M001-*: reflect the standalone placement, catalog count 15, and the reversal of the earlier .agents/ decision. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Slug = folder name = .plugin.json name (parity rule). An action-verb
slug ("create a shareable skill") reads better than the state-style
"new-shareable-skill" and matches the catalog's other capability skills.
Renamed: folder, SKILL.md name + title + digraph, .plugin.json name +
homepage, README/CONTRIBUTING/AGENTS references, .ytstack/ memory.
DECISIONS.md gets an append-only rename entry; earlier entries keep the
old name verbatim as historical record.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Marketplace entry + skill-plugin symlink dir follow the rename new-shareable-skill -> create-shareable-skill. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
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
1 participant
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.
What
Moves
new-shareable-skillfrom.agents/skills/(where PR #1 placed it) to a standalone catalog skill atskills/operations/new-shareable-skill/. It is now discovered, compiled, and listed in the marketplace like any other skill -- count 14 → 15.Why
User decision on review of PR #1: authoring a shareable skill is itself a user-facing capability, so the skill belongs in the catalog, not in repo-local tooling. Only
audit-skillsstays in.agents/-- it is pure verification machinery.Changes
skills/operations/new-shareable-skill/{SKILL.md,references/placement.md,references/quality-bar.md}-- movedskills/operations/new-shareable-skill/.plugin.json-- added (marketplace manifest: author, homepage, repository, license, keywords)SKILL.md/placement.md-- reframed from "repo-local tooling" to standalone skillquality-bar.md-- depersonalized the path example (/Users/alex/→/Users/<username>/), softened gratuitous leak-pattern tokensREADME.md-- new catalog row + counts14→15/9→10standaloneCONTRIBUTING.md,AGENTS.md-- updated path references.compiled/-- regenerated (compile: regenerate artifacts).ytstack/--DECISIONS.mdsuperseding entry + memory updatesKnown consequence
references/quality-bar.mddocuments leak patterns (grep commands,-internal, migration-framing examples). Now that the skill lives underskills/it is inaudit-skills' scan scope, so axis-1 will surface known false positives from this skill's own pattern documentation -- the same reasonaudit-skillsitself sits in.agents/. The clean structural fix, if the noise is unwanted, is to addskills/operations/new-shareable-skill/references/toaudit-skills'-not -pathexclusions. Not done here (modifies a second skill, out of scope) -- recorded inDECISIONS.md.Verification
node compile.mjsclean; marketplace count 15;.plugin.jsonsymlinked into.compiled/skill-plugins/new-shareable-skill/🤖 Generated with Claude Code