AgentStack
SKILL verified Apache-2.0 Self-run

Idea Refinement

skill-mmccalla-coding-agent-skill-library-idea-refinement · by mmccalla

Use when a rough idea needs to be shaped into a concrete, testable proposal before planning or implementation.

No reviews yet
0 installs
12 views
0.0% view→install

Install

$ agentstack add skill-mmccalla-coding-agent-skill-library-idea-refinement

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

Are you the author of Idea Refinement? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Idea Refine

When to use

Use this skill when the user has an early-stage concept, a loose feature idea, or a partial proposal that needs structured clarification before build work begins.

Objective

Turn a vague idea into a focused proposal with a clear problem statement, options, recommended direction and known tradeoffs.

Procedure

  1. Restate the idea in plain language.
  2. Identify the intended user or stakeholder.
  3. Define the problem the idea is meant to solve.
  4. List the simplest viable options.
  5. Compare the options against complexity, risk and fit with the repo.
  6. Recommend the narrowest coherent path.
  7. Capture assumptions and unknowns that still matter.

Rules

  • Do not expand the idea into a large design before the problem is clear.
  • Do not invent features just because they are common elsewhere.
  • Do not collapse distinct options into one vague middle ground.
  • Keep the recommendation aligned with the repository's existing structure and intent.

References

Verification

  • [ ] Refined problem statement and proposed approach stated.
  • [ ] Constraints, assumptions and open questions listed.
  • [ ] Success criteria or falsifiable hypotheses captured.
  • [ ] Recommendation for spec, interview or implementation next step.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet — be the first.

Versions

  • v0.1.0 Imported from the upstream source.