shiptoday/forge-plugin-claude-mp (forge-autopilot)

Routes any product, engineering, or software development lifecycle (SDLC/PDLC) activity to Forge. Invoke this skill whenever the user describes work that involves the product development process — across any phase: discovery, definition, planning, execution, review, handoff, release, or reporting. This includes: building or shipping features, fixing bugs, writing PRDs, breaking down stories, estimating, prioritizing, reviewing PRs, security audits, vulnerability assessments, release readiness checks, deployment gates, test planning and strategy, refactoring, mapping or documenting system architecture across the codebase, reconstructing an architecture estate or building an architecture atlas, or any similar SDLC activity. ALSO invoke when the current user request directly targets a tracked work item key matching "PROJ-123" / "BUG-42" / any "<UPPERCASE>-<digits>" id. Do NOT invoke for pure coding requests ("write a function", "refactor this file", "add a test") or continuation of already-scoped execution, even when a tracked key appears only in earlier conversation context. Do NOT invoke for git operations, file editing, applying already-scoped review feedback, resolving merge conflicts, publishing an existing change, or general Q&A unrelated to a project.

Claude Skills are markdown + scripts loaded into Claude Code; scanned with the same pipeline.

Source:

github.com/shiptoday/forge-plugin-claude-mp

Provenance:

Found by crawling (provenance, not a security rating)

We found this by crawling public sources and nobody has attested to it. That is how most of the registry gets here, and it is not a mark against the artifact — it only means no authenticated act of publication is on record. An artifact can be the vendor's own and still appear here.

4 critical findings reported by cisco-skill-scanner, agent-audit-kit. The composite score alone does not reflect this — read the per-scanner reports below.