Feasibility check

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

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.From its SKILL.md

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.

SKILL.md

1.8 KB, 355 tokens by cl100k_base, 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

List the hard constraints: time, team, budget, tech, data, external dependencies, compliance.
Find the killer risks: the assumptions that, if false, sink the project. Rank them by likelihood × how fatal.
Reduce the top unknowns cheaply — usually a small spike (see prototyping), not more discussion.
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.
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.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most quality gates skills give in 355 tokens

Counted across 1,195 of the 2,094 authors here whose files we hold, read 2026-08-07

Read the output and check the exit codein 54 of 1195, across 14 files
Verify requirements using a line-by-line checklistin 53 of 1195, across 12 files
Identify the verification command proving the claimin 51 of 1195, across 12 files
Run the full verification commandin 50 of 1195, across 11 files
Verify output confirms the claimin 49 of 1195, across 12 files
Check version control diff after agent delegationin 46 of 1195, across 6 files
State claim with evidencein 44 of 1195, across 4 files
Run the test suitein 33 of 1195, across 26 files
Keep state in memory by defaultin 27 of 1195, across 6 files
Make prototype runnable with one commandin 26 of 1195, across 5 files
Produce a verification reportin 25 of 1195, across 14 files
Detect the package manager from lockfilesin 24 of 1195, across 5 files

Said here and by no other author read

list the hard constraints
identify and rank killer risks
reduce unknowns with a small spike
give a go, no-go, or go-if verdict
write the feasibility section
rule out not building before greenlighting

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.