write-nfr
Skill0 starsChanged 16 days agoMITView on GitHub
Write measurable non-functional requirements or mark them unknown. Use when the user asks for NFRs, SLOs, quality attributes, performance or security targets, or /write-nfr. Do not invent numbers. Do not write product code.
In this repository66 other files it gives its agents.
- AGENTS.mdAGENTS.md
- a11y-passSkill
- assess-changeSkill
- build-regression-packSkill
- charter-exploratorySkill
- classify-dataSkill
- commitSkill
- cut-releaseSkill
- data-changeSkill
- debugSkill
- design-experimentSkill
- diff-environmentsSkill
- draft-steercoSkill
- engineering-barSkill
- explain-codeSkill
- explore-codebaseSkill
- fix-ciSkill
- handoffSkill
- implement-changeSkill
- incident-triageSkill
- lean-reviewSkill
- map-dependenciesSkill
- map-design-handoffSkill
- map-processSkill
- open-prSkill
- performanceSkill
- plan-data-migrationSkill
- plan-incrementSkill
- plan-rollbackSkill
- plan-uatSkill
- prioritize-backlogSkill
- production-passSkill
- ready-to-mergeSkill
- record-decisionSkill
- refactor-safelySkill
- revert-changeSkill
- review-architectureSkill
- review-changeSkill
- review-pipelineSkill
- security-passSkill
- shape-workSkill
- ship-notesSkill
- spec-analyticsSkill
- spec-observabilitySkill
- start-projectSkill
- synthesize-discoverySkill
- triage-blockersSkill
- triage-defectSkill
- update-raidSkill
- verify-uiSkill
- write-api-examplesSkill
- write-architectureSkill
- write-designSkill
- write-dev-tasksSkill
- write-docsSkill
- write-integration-contractSkill
- write-opportunitySkill
- write-prdSkill
- write-requirementsSkill
- write-runbookSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 2 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
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
- Distinctive: line 19
Do not implement. Do not invent SLOs, SLAs, or baselines.
- Very specific: line 36
If the user says “it must be fast/secure/scalable” with no number and no existing baseline, write unknown and stop for a human target.
- Very specific: line 45
Read AGENTS.md if present.
- Distinctive: line 46
Read the named PRD, requirements, and architecture.
- Very specific: line 50
Do not specify implementation (caches, vendors, instance sizes).
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Write NFR
Record quality attributes as numbers or as unknown. This is not a PRD, not architecture, and not a test plan.
Do not implement. Do not invent SLOs, SLAs, or baselines.
Is this the right skill?
| Signal | Do this instead |
| Functional behavior | write-requirements |
| Durable system shape | write-architecture |
| How this initiative is built | write-design |
| What we will and will not automate | write-test-strategy |
| PII classification of a change | classify-data |
Required inputs
- A PRD and/or requirements path, or an architecture doc for an existing system
AGENTS.md;context/environments.mdif it exists
If the user says “it must be fast/secure/scalable” with no number and no existing baseline, write unknown and stop for a human target. Do not pick industry-typical numbers.
Human decisions (do not invent)
- Any numeric target that is not already in the repo, the PRD, or a signed architecture doc
- What happens if a target is missed (error budget / reject traffic / unknown)
Procedure
- Read
AGENTS.mdif present. Readcontext/environments.mdif present. - Read the named PRD, requirements, and architecture. Collect quality attributes they already state.
- Find the home: first existing
docs/nfr/, or offer to create it. Name:docs/nfr/<slug>.md. - Open references/nfr-template.md. Copy every heading. Write
n/awhen unused. - For each category in the template: either a number with its source (path or “user-set”), or
unknown. - Do not specify implementation (caches, vendors, instance sizes). That is
write-design. - Point at environments by the names in
context/environments.md. Do not invent prod URLs.
Output
- Path:
docs/nfr/<slug>.md - Template:
references/nfr-template.md
Quality bar
- Every numeric target names a source or is
unknown - No invented baseline
- No implementation or vendor choice presented as an NFR
- Unused headings are
n/a - At least one row is a real target or an explicit
unknownthe human must set
Done
- Path
- How many targets vs unknowns
- Next skill:
write-design,write-test-strategy, or stop — need user for unknowns that block
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.