skilld
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.

Ask your Agent

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

This session only. Nothing lands on disk.

assetstemplatessetup-preflight.md

≈494 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Opportunity Factory Setup Preflight

Target

  • Primary surface:
  • Secondary surfaces:
  • Runtime profile:
  • State store:
  • Prompt runner:
  • Schedule mechanism:
  • Verification source:
  • Verification timestamp:
  • Checked by:

Capability Gate

  • Skill or prompt assets are available to the target surface
  • commander, worker, and reporter-learner prompts are callable
  • State, queue, artifact, outcome, and audit-log storage are durable
  • The runtime can prevent duplicate or overlapping runs
  • Lock acquisition is atomic and long runs refresh a heartbeat
  • A stale-lock recovery path reconciles partial target changes against required artifacts and verification
  • Runtime limits are configured
  • Human approval boundaries are configured
  • A test artifact can be created and imported
  • Reporting destination is configured
  • Capability verification source is recorded
  • Runtime dependencies executed on this host (interpreter, libraries, browsers, timezone data)

Approval Boundaries

  • External publishing requires approval
  • Payment or paid API usage requires approval
  • Account creation or login requires approval
  • Secrets require approval and are never written into prompts
  • Personal data processing requires approval
  • Destructive commands require approval or are denied
  • Legal/platform policy risks stop unattended runs

Schedule Gate

  • Commander cadence:
  • Worker cadence:
  • Reporter-learner cadence:
  • Max pending tasks:
  • Max daily worker runs:
  • Max daily cost estimate:
  • Lock TTL:
  • Stale-lock recovery threshold (recommended >= 2x TTL):
  • Stale task TTL:
  • Quiet hours / notification policy:
  • Jobs registered disabled, verified, then enabled:
  • Automation IDs recorded with host and registration time:

Result

  • Preflight: PASS / FAIL / BLOCKED
  • Blocking issue:
  • Safe first run:
  • First three jobs:
  • Evidence:

Source: SKILL.md on GitHub

Third-party checks

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

Provenance

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

Capability

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