agentsclimarketplace

Feasibility check

Skill NjoyimPeguy/augments/skills/planning/feasibility-check

A collection of rigorous, phase-isolated SDLC skills to tether autonomous agents to real-world engineering standards.

Install
npx -y skills add NjoyimPeguy/augments --skill feasibility-check

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Use before committing to a project or initiative — to decide whether the goal is achievable within the real constraints (time, team, tech, budget), surface the risks that could sink it, and route the riskiest unknowns to prototyping. Skip when the approach is already proven or the commitment is trivially reversible.

SKILL.md

1.8 KB, as published. Nobody here has run it

Feasibility Check

Optimism is not a plan. Before a project is greenlit, find the thing most likely to kill it — and decide honestly whether it's achievable.

When to use

  • Before committing to a project or initiative (the go/no-go moment).
  • When feasibility is genuinely uncertain — new tech, hard constraints, unknown data.
  • Skip when the path is well-trodden and the risk is obviously low.

Procedure

  1. List the hard constraints: time, team, budget, tech, data, external dependencies, compliance.
  2. Find the killer risks: the assumptions that, if false, sink the project. Rank them by likelihood × how fatal.
  3. Reduce the top unknowns cheaply — usually a small spike (see prototyping), not more discussion.
  4. Give a verdict: go / no-go / go-if (with the conditions that must hold). A no-go now is far cheaper than a failure later.
  5. Write the ## Feasibility section of the project brief: constraints, top risks, the verdict and its conditions.

A go hands off to scope-it — draw the boundary before design.

Common mistakes

  • Greenlighting on optimism — no named risks means you didn't look.
  • Treating "we'll figure it out" as feasibility — name what would make it infeasible.
  • Endless analysis instead of a cheap spike to kill the biggest unknown.
  • Skipping Option Zero — the cheapest path is sometimes to not build it: an existing tool, a config change, or a smaller change to the problem. Rule it out before greenlighting a build.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.