jeredblu-tools

Plugin jeredblu-tools from marketplace jeredblu-marketplace in JeredBlu/jeredblu-marketplace. Commands read from the repo's manifest — 30 days ago.

Skills (5)

• agent-skill-evaluator

  Statically review agent skills, skill directories, and .skill archives before installation. Use for skill safety or trust assessments, including prompt injection, unwanted output, execution, credential access, and data disclosure. Produce evidence-backed findings, a per-check rubric score, and expli

• frugal-fable

  Use when running on Claude Fable (or any premium model) and the work is token-heavy — building features, multi-file changes, research, testing, debugging, migrations, or anything spanning many files/sources. Keeps Fable on the judgment (decompose, architect, synthesize, review) and delegates bounded

• mcp-evaluator

  Review an MCP server's security, privacy, permissions, and launch risks before use. Use for a supplied MCP repository or hosted MCP endpoint, or an explicit safety comparison. Produces an evidence-based per-check score with coverage and deployment limits; does not install or run the server.

• prd-creator

  Create comprehensive PRDs through conversational discovery. Use when users want to plan software projects, document requirements, or prepare specifications. Supports beginners to experienced PMs. Asks deep clarifying questions to gather requirements, researches technologies, and produces structured

• repo-evaluator

  Evidence-led pre-install review of GitHub software without executing the target. Inspect install paths, code behavior, data flows, dependencies, provenance and agent instructions; produce a versioned per-check risk rubric with explicit coverage and uncertainty. Use when the user asks whether a repo