From open-source-hardening-skills
Converts open-source hardening audits into executable GitHub-ready checklists with staged execution order, acceptance criteria, commands, and impact estimates.
How this skill is triggered — by the user, by Claude, or both
Slash command
/open-source-hardening-skills:oss-planThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Turn audit findings into a staged implementation plan that is ready to paste into a GitHub issue or PR description.
Turn audit findings into a staged implementation plan that is ready to paste into a GitHub issue or PR description.
OSS_AUDIT.md.OSS_AUDIT.md is missing, derive a minimal audit summary from the repository and clearly label it as reconstructed.Create or update OSS_PLAN.md in the repository root. The file must contain:
Use this item shape exactly:
- [ ] Add CLI regression tests
Purpose: protect the main user flow before refactoring.
Change points: `tests/test_cli.py`, `src/cli.py`.
Acceptance criteria: happy-path and invalid-input flows pass locally and in CI.
Suggested commands: `python -m unittest`, `python src/cli.py --help`.
Estimated impact radius: low; test-only plus light CLI guard changes.
Also include a short "minimum shippable subset" section for contributors who only have one small PR available.
Prefer this dependency order unless the repository clearly needs a different one:
Each item should be independently reviewable. If an item feels too big for one PR, split it.
Good checklist items are:
Add explicit pause points such as:
P0) with aspirational roadmap work in the same checklist tier.Before declaring this stage complete, verify:
OSS_PLAN.md exists in the repo root.OSS_PLAN.md exists and contains a scope summary, staged markdown checklist, execution order, explicit stop points, and a minimum shippable subset section.npx claudepluginhub zeyuzhangzyz/open-source-hardening-skillsDecomposes epics into trackable, right-sized tasks with Size, Urgency, Risk, ROI, Blast Radius, LOE ratings. Audit-aware modes use codebase reports or handoff.yaml; standalone option.
Audits a repository as a senior lead and produces self-contained, agent-executable implementation plans. Use when the goal is a prioritized plan backlog, not a report-only audit.
Audits a codebase as a senior advisor and produces prioritized, self-contained implementation plans for other models/agents to execute. Read-only — never implements or fixes code itself.