mcpbeat

Idea Genie

boshu2/agentops-idea-genie

Generate evidenced opportunities or challenge an idea with sealed perspectives. Triggers: "idea genie", "what should we build", "challenge this idea", "compare proposals".

This is a copy. The original lives at boshu2/idea-genie.

3k tokens
context cost
the whole folder, loaded on every use
5
files
ships runnable scripts
0
copies elsewhere
how many repositories repackaged it
416
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/boshu2/agentops --skill idea-genie

The instruction itself

10 sections, as written by the author

Idea Genie

One canonical root for idea work: elicit an evidence-grounded opportunity

portfolio, or challenge a consequential idea with sealed independent

perspectives. Both modes explore and advise; neither selects, schedules,

tracks, implements, or validates work.

Modes

| Trigger phrases | Mode | Output contract |

|---|---|---|

| "idea genie", "what should we build", "supported opportunities" | elicit (single genie) | idea-portfolio.v1 via scripts/validate-output.sh |

| "challenge this idea", "compare independent proposals", "stress-test a one-way door" | duel (adversarial challenge) | idea-challenge.v1 via scripts/validate-challenge.sh |

Elicitation is the entry mode. Dueling is an optional escalation for a

consequential choice, typically consuming an idea-portfolio.v1 or a framed

question.

Elicit mode

Generate a small portfolio of evidenced options.

  • State the question, constraints, non-goals, and sources.
  • Separate cited observations from assumptions.
  • Give each candidate its supporting evidence, overlap with existing

capabilities, and one normal or edge scenario.

  • Run a novelty pass, merge equivalents, and discard unsupported ideas.
  • Stop when no materially new evidenced candidate appears.
  • Write and validate idea-portfolio.v1, then return it to the caller or Plan.

An empty no-new-work portfolio is valid. Plan alone may incorporate a selected

option into the existing bead or caller intent.

Duel mode

Produce independent challenges for a consequential choice. The result is

advisory evidence for Plan. It never decides whether a plan is ready and never

turns a later optional Premortem challenge into an approval gate.

Constraints

  • Keep generation sealed until every perspective is complete to prevent later

proposals from anchoring on earlier ones.

  • Preserve dissent and concrete refutation attempts because Plan must see alternatives

that synthesis might otherwise erase.

  • Keep reversible choices lightweight because they do not warrant a pane manager,

messaging service, council, or model-family rule.

  • Emit no readiness, approval, quorum, retry, budget, helper, delivery, or

tracker state because this strategy supplies evidence rather than lifecycle

authority.

Workflow

  • Freeze the question, constraints, evidence paths, and comparison rubric.
  • For a one-way door, create at least two fresh contexts with distinct context

identifiers. Each produces its perspective before any is revealed. When the

caller pins perspectives to model profiles, record each perspective's

model_identity (see the agent-native model-dispatch recipe); a

duel may use two distinct models on request. Sealed generation is unchanged:

no perspective may see another before reveal. Unavailable profiles → disclose

and continue single-model.

  • Reveal the sealed perspectives and cross-review by evidence, reversibility,

system fit, failure modes, and cost.

  • Attempt concrete refutations. Preserve disagreements, failed refutations,

and minority reasoning.

  • Write idea-challenge.v1, validate it, and pass the artifact to Plan as one

optional input alongside research and operator intent.

For a cheap two-way door, emit the lightweight packet directly after one fresh

challenge. Do not manufacture panel ceremony.

Output Specification

  • Artifact directory: .agents/scratch/ideas/<run-id>/
  • Filename: idea-challenge.json
  • Format: idea-challenge.v1 JSON with route-specific fields enforced by

the validator

  • Validation command:

skills/idea-genie/scripts/validate-challenge.sh <idea-challenge.json>

  • Downstream handoff: handoff.owner is exactly plan; Plan may accept,

reject, or combine the advisory evidence

Quality

  • One-way packets prove distinct context IDs and cross-review another

perspective by named dimensions.

  • Dissent and refutation attempts remain explicit.
  • The packet contains no semantic readiness field or decision.
  • The validator passes before handoff to Plan.

Do not

  • Let perspectives see one another before sealed generation completes.
  • Convert consensus, transport availability, or a self-score into readiness.
  • Require orchestration infrastructure for a reversible choice.

References

  • Idea Genie behavior
  • Idea challenge behavior

How to use it

Copy the folder

Take boshu2/agentops-idea-genie from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.