assess
Skill23 starsChanged 2 months agoMITView on GitHub
Use when someone wants to know whether an idea deserves building before anyone builds it: \"is this worth doing?\", \"should we build X?\", \"evaluate this idea\", \"would users actually want this?\", \"help me decide whether to invest in this\", a product or business idea with no code yet, or a feature request nobody has said yes to. Not for scoping something already decided (that's `interview` or `specify`), not for adopt-vs-build on a library (that's `tech-scout`).
13 other projects use a version of this.
Adopted by
Most recently taken up by
- baney75/myelinatetheir own version, first seen Oct 20, 2026
- awslabs/service-onboarding-accelerator-on-awstheir own version, first seen Oct 20, 2026
- rivendale/ai-redteamtheir own version, first seen Oct 17, 2026
- jvalin17/agent-toolkittheir own version, first seen Oct 12, 2026
- bjcoombs/ai-native-toolkittheir own version, first seen Oct 11, 2026
- saleh-alhaddad/itqan-engineeringtheir own version, first seen Sep 29, 2026
Used with
Projects with it also use verify.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
Microsoft AzureSkillverify
End-to-end app testing pipeline for browser-based web apps on cloud browsers via Azure Playwright Workspaces: verify the live app, author tests for working flows, heal failing tests, then re-run with video and produce one consolidated report. Three phases (app verification, test authoring, test healing) plus a scoped final sanity run; each phase emits a sub-report. Use when asked to "verify my app", "make sure my app works and has good test coverage", "do a full QA pass", "add tests where I'm missing coverage", "fix failing tests and add new ones", "smoke test before deploy", "QA my deployment", or any combined verify-and-test ask. Requires Azure CLI (`az login`) and a Playwright Workspace resource ID — bootstraps configs on first invocation. Browser-based web apps with Playwright only — not for unit/API tests, native mobile/desktop, load/perf, or full accessibility audits.
Also in 4 projects that use this
Other versions13 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 13
- bjcoombs/ai-native-toolkit★ 32same name
- saleh-alhaddad/itqan-engineering★ 10same name
- Ic3b3rg/learn-skills★ 9same name
- benyoskovitz/claude-code-workflow★ 8same name
- awslabs/service-onboarding-accelerator-on-aws★ 7same name
- baney75/myelinate★ 6same name
- jhlee0409/omni-harness-kit★ 2same name
- jvalin17/agent-toolkit★ 2same name
- rivendale/ai-redteam★ 2same name
- sequant-io/sequant★ 1same name
3 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository34 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- analyzeSkill
- blueprintSkill
- breakdownSkill
- buildSkill
- checklistSkill
- clarifySkill
- constitutionSkill
- convergeSkill
- debugSkill
- deepenSkill
- deprecateSkill
- double-checkSkill
- explainSkill
- handoffSkill
- helpSkill
- initSkill
- interviewSkill
- learnSkill
- levelupSkill
- lintSkill
- living-docsSkill
- performanceSkill
- personaSkill
- promptSkill
- prototypeSkill
- qaSkill
- quarantineSkill
- reportSkill
- roadmapSkill
- routeSkill
- signatureSkill
- specifySkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 0 are distinctive, and 3 are very specific to this project.
0
Common
Most of the 13 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 13
Write one file, specs/ideas/<slug>.md, from specs/.templates/idea.md if present, else template.md beside this file.
- Very specific: line 39
Do not grade your own research: Before deciding, send the shaped version and its assumptions to a fresh-context reviewer with the brief …
- Very specific: line 41
Stopping is the decision people avoid: If every assumption is untested and the cost is high, the honest verdict is clarify with the …
“Common” is measured: kept by at least 6 in 10 of the 13 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
MasterMind: Assess
A documented "stop" is a good outcome. This decides whether an idea earns a spec, using evidence rather
than enthusiasm (~/.mastermind/engineering/core/product-sense.md). It works in a folder with no code.
Paths follow ~/.mastermind/engineering/core/spec-driven.md.
Idea: $ARGUMENTS.
Write one file, specs/ideas/<slug>.md, from specs/.templates/idea.md if present, else
template.md beside this file. Fill it stage by stage; each stage refines the same
file instead of producing a new one.
The five stages
- Intake. The idea in one sentence, who asked, and who it is for. Then the problem it removes, in
that person's words. An idea with no named person and no named problem stops here as
clarify. - Research. What exists today: the workaround people use, the competitors, the prior attempt in
this codebase. Search the code by the concept, not the request's wording, and read earlier verdicts in
specs/ideas/. An idea already built stops here with its path; one already stopped needs new evidence. Cite every claim with its source. Label each finding observed, reported or assumed. - Define. The outcome that would mean it worked, as one to three measurable signals with a target and a deadline. Then the constraints: budget, legal, technical, the constitution if one exists.
- Shape. The smallest version that would test the outcome. What it leaves out. The two or three assumptions it stands on, each with the cheapest test that could prove it false.
- Decide. One verdict, with its reasons and what would change it:
| Verdict | Means | Next |
| go | the evidence supports it and the smallest version is clear | hand the shaped version to specify |
| clarify | a named unknown decides it and can be resolved | the unknown, who resolves it, by when |
| stop | the evidence is against it, or the cost outweighs the outcome | the reason, and what would reopen it |
Gotchas
- Enthusiasm is not evidence. "Users would love this" with no source is an assumption. Write it as one.
- Do not grade your own research. Before deciding, send the shaped version and its assumptions to a
fresh-context reviewer with the brief from
interview's red-team pass. Fold in what survives. - Stopping is the decision people avoid. If every assumption is untested and the cost is high, the
honest verdict is
clarifywith the cheapest test, nevergoon hope. - The decision is the user's. You recommend with reasons; they own go or stop. Record who decided.
- No market numbers from memory. A figure without a fetched source is labelled
assumed, or omitted.
Report
The verdict, the two strongest reasons, the riskiest assumption and its test, and the file path. On
go, offer to start specify from the shaped version.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.