All skills
aktsmm avatar

/opportunity-factory

@e63d714
by yamapanaktsmm/agent-skills26 stars
4

Run a reusable opportunity-to-artifact workflow: discover unmet needs, set up workspace factories, schedule recurring commander/worker/reporter prompts, batch-refine many items, optionally use SQLite state, build small artifacts, review quality, and track outcomes. Use when the user wants to repeatedly create apps, games, products, content, or experiments from market/user needs.

Use this Skill: https://skilld.dev/gh/aktsmm/agent-skills/opportunity-factory

This session only. Nothing lands on disk.

assetstemplatesfactory-plan.md

≈564 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Factory Plan

Frame

  • Domain:
  • Artifact type:
  • Audience:
  • Success metric:
  • Constraints:

Roles

Role Owner Notes
Orchestrator
Scout
Researcher
Critic
Designer
Builder
Reviewer
Tracker
Workflow Reviewer Reviews cadence, queue quality, dashboard freshness, and missing gates

Durable State

  • Dashboard/status state:
  • Factory state:
  • Pending queue:
  • Done history:
  • Outcome log:
  • Pipeline log:
  • Artifact directory:
  • Portfolio/Top-N state:

Queue Slice

Kind Task Artifact
discover
research
evaluate
design/build
review
track/learn

Runtime Preset

  • Environment: hosted agent scheduler / OpenClaw / cron / Windows Task Scheduler / GitHub Actions / manual / other
  • Profile: low-cost / supervised / standard / burst
  • Commander cadence:
  • Worker cadence:
  • Reporter-learner cadence:
  • Workflow-review cadence:

Workspace Setup Matrix

Surface Skill location Prompt runner Schedule mechanism State store Approval mode Verification status

Human Approval Boundaries

  • Approved autonomy envelope:
  • Reviewer PASS may advance:
  • Cost:
  • Login/account:
  • External publish:
  • Personal data:
  • Legal/platform risk:

Operating Limits

  • Max pending tasks:
  • Max daily worker runs:
  • Max active portfolio candidates:
  • Max daily cost estimate:
  • Lock TTL:
  • Stale task TTL:
  • Blocker threshold:
  • Notification policy:

Next Decision

  • Continue if:
  • Stop if:
  • Ask human if:

Portfolio Replacement Gate

  • Top-N capacity:
  • Promote if:
  • Demote incumbent if:
  • Watchlist if:
  • Reject if:
  • Required reviewer evidence:

Source: SKILL.md on GitHub

2 warnings22d3 checks · Risk MEDIUM
  • Gen Agent Trust Hub22d

    This skill is an autonomous agent framework that manages complex workflows. It is rated as medium severity because it is self-modifying (the AI edits its own instructions), establishes persistent automated loops, and automatically accesses local secrets for its operations. While it includes many internal safety rules, the high degree of autonomy requires review before deployment.

  • Socket22d

    No alerts

  • Snyk22d

    Risk: MEDIUM · 1 issue

Signed by skilld at e63d714. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 18 hours ago.

Activeupdated 4 weeks ago
argument-hint
対象ドメイン、成果物タイプ、制約、今回の入力
user-invocable
true
metadata
{
  "author": "yamapan (https://github.com/aktsmm)"
}

README badge

README badge for aktsmm/agent-skills/opportunity-factory