Fixture skill for the package-closure check. Use when exercising validate_harness.py against a plugin-packaged skill.
Scanned 9/3/2026
Install to Claude Code
npx -y skills add tjdwls101010/Harness-Creator --skill packaged --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Packaged?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/tjdwls101010-packaged)More formats (shields.io, HTML) on the badges page.
---
name: packaged
description: >
Fixture skill for the package-closure check. Use when exercising
validate_harness.py against a plugin-packaged skill.
---
# Packaged
Target-project paths — these name files in the repo this skill is *run against*,
which is what it exists to build, so none of them are pointers into its own
package: `.claude/settings.json`, `.claude/rules/*.md`, `CLAUDE.md`, a monorepo's
`packages/api/CLAUDE.md`, another tool's `.github/copilot-instructions.md`, a
vendored `node_modules/some-pkg/README.md`, generated output in `dist/index.md`,
and wherever the reader keeps `docs/notes.md`. None of those resolve here, which
is exactly why they are talking about somewhere else.
Real pointers, which resolve inside the package: references/real.md and
scripts/tool.py.
Leaks — both resolve in this repo and travel nowhere: the rationale is in
docs/design/notes.md and the decision log is in notes/internal-decisions.md.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...