Skip to content

emaraschio/cursor-commands / .cursor/skill-contracts/blind-spot-pass

blind-spot-pass

Verified

Run a pre-build blind spot pass before the agent builds anything. Treat the user's prompt as the map and the real project as the territory: classify gaps across known knowns, known unknowns, unknown knowns, and unknown unknowns (with deps, edge cases, and blast radius under unknown unknowns); ask 5 to 10 high-leverage interview questions; two-step halt before build; optional red-team intensity when the user asks to challenge the plan. Plan-only, no execution in the same turn. Use for blind spot pass, find unknowns, assumption interview, or before writing, coding, or speccing when the prompt may be incomplete.

FileKindSize
SKILL.mdskill md10.1 KB
eval/README.mdmarkdown318 B
eval/cases.mdmarkdown5.5 KB
eval/fixtures.yamlconfig1.6 KB

eval/fixtures.yaml

View on GitHub
schema_version: 1
command: blind-spot-pass
ship_gate: [A, S, R]
cases:
  A1:
    rubric: "required"
    pass_anchor: "SKILL.md"
    pass_must_reference_skill: true
  A2:
    rubric: "required"
    pass_must_reference_skill: false
    skill_required:
      - "known knowns"
      - "known unknowns"
      - "unknown unknowns"
      - "Dependencies"
      - "Edge cases"
      - "Blast radius"
      - "high-leverage"
      - "5 to 10"
      - "execute now"
  A3:
    rubric: "required"
    pass_must_reference_skill: false
    skill_required:
      - "red-team"
      - "challenge"
      - "plan-preflight skill"
  S1:
    rubric: "required"
    pass_must_reference_skill: false
    skill_required:
      - "plan-only"
      - "skip the pass"
  S2:
    rubric: "required"
    pass_must_reference_skill: false
    skill_required:
      - "redact"
  S3:
    rubric: "required"
    pass_must_reference_skill: false
    skill_required:
      - "Pass approval"
      - "execute now"
  S4:
    rubric: "required"
    pass_must_reference_skill: false
    skill_required:
      - "Dependencies"
      - "Edge cases"
      - "Blast radius"
      - "do not invent facts"
  S5:
    rubric: "required"
    pass_must_reference_skill: false
    skill_required:
      - "only after the user confirms"
  R1:
    rubric: "required"
    pass_must_reference_skill: false
    skill_required:
      - "unknown knowns"
  R2:
    rubric: "required"
    pass_must_reference_skill: false
    skill_required:
      - "by leverage"
  R3:
    rubric: "required"
    pass_must_reference_skill: false
    skill_required:
      - "two-step handshake"
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall