Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Quality Attribute Discovery · jabrena | DecimalAI

Registry skillby jabrena

Quality Attribute Discovery

jabrena/025-quality-attribute-discovery

Source jabrena/plinth ↗License Apache-2.0

Use when a problem under exploration needs its quality attributes (non-functional requirements) identified and prioritized before architecture and design begin. This should trigger when an issue's Quality Attribute Discovery point of view needs evaluation, or when a maintainer directly asks to discover and prioritize candidate quality attributes for a problem, before any ADR or design work starts. Part of Plinth Toolkit

SkillScore64Maintained

Automatic

Product Management pack

Last verified 8/20/2026

What it changes

Passed 14 of 22 test cases with the skill, and 9 of 22 without it.

Without skill41%

With skill64%

Checks it passed that the model alone missed

Avoids making architectural decisions.
Refuses to write an ADR for Kong Gateway rate-limiting policy.
Stops output at the prioritized quality attribute discovery list.

and 8 more in the full report

8 fixed6 passed either way5 still failing3 broke

Pass-rate lift: +23 pp
Tokens: -10%
Agent turns: 0%
Response time: -32%

Model gemini-3.6-flashMeasured 8/20/2026v114 of 22 cases passed with skill

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/jabrena-025-quality-attribute-discovery/SKILL.md https://app.decimal.ai/s/jabrena-025-quality-attribute-discovery/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add jabrena-025-quality-attribute-discovery, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/jabrena-025-quality-attribute-discovery/ and pins it in .decimal/skills.lock

decimalai skills add jabrena-025-quality-attribute-discovery

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/jabrena-025-quality-attribute-discovery/SKILL.md https://app.decimal.ai/s/jabrena-025-quality-attribute-discovery/SKILL.md

Raw file: /s/jabrena-025-quality-attribute-discovery/SKILL.md ↗ · machine-readable summary at /s/jabrena-025-quality-attribute-discovery.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 8

Prompt

We are preparing to build an automated patient notification system for urgent lab results. Here is our problem background, context map, and initial assumptions regarding high volume spikes and HIPAA compliance requirements. Before our engineering team meets to make any technology selections or write ADRs, please analyze our context and provide a prioritized list of relevant non-functional requirements/quality attributes ranked by business impact and operational risk. Make sure to call out any areas where information is too vague to determine a priority.

What was checked, without and with the skill
Checked	Without skill	With skill
Asks clarifying questions regarding missing details on volume spikes.	Passed	Passed
Avoids making architectural decisions.	Missed	Passed
Stops output at the prioritized quality attribute discovery list.	Missed	Passed

case-01 · gemini-3.6-flash · 8/20/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md56 lines2 files

Quality Attribute Discovery

Guide identification and prioritization of the quality attributes a future solution must satisfy, before architecture and design decisions begin. This is an interactive SKILL.

What is covered in this Skill?

Identifying candidate quality attributes (for example performance, security, availability, maintainability, scalability, usability, observability) relevant to the problem
Grounding each candidate in evidence from the problem frame, root causes, assumptions, and context map, not a generic checklist
Prioritizing candidate quality attributes by stakeholder impact and risk
Stopping at a prioritized discovery list rather than selecting or recording an architectural decision
Explicitly not producing ADRs or an architecture direction itself

Constraints

Discover and prioritize candidate quality attributes as input to later architecture work; do not make or record the architecture decision here. When this technique is orchestrated by another workflow, the orchestrator owns clarifying-question sequencing; when applied standalone, ask directly.

MUST read references/025-quality-attribute-discovery.md before applying Quality Attribute Discovery guidance
MUST ground each candidate quality attribute in evidence from the problem frame, root causes, assumptions, or context map
MUST prioritize candidate quality attributes by stakeholder impact and risk, not list them unordered
MUST stop at a prioritized discovery list without selecting or recording an architecture decision
MUST NOT record an architectural decision, ADR, or design direction as part of this skill's output
MUST NOT invent a quality attribute or priority when the available content is vague or ambiguous; flag the gap for a clarifying question instead

When to use this skill

Discover the quality attributes for this problem
Identify non-functional requirements before design begins
Prioritize candidate quality attributes for this issue
Apply quality attribute discovery before architecture decisions
Draft the Quality Attribute Discovery section of a Functional Specification

Workflow

Read the Reference

Read references/025-quality-attribute-discovery.md, then review the problem frame, root-cause findings, assumptions, and context map for evidence of quality pressure.

Identify Candidate Quality Attributes

Identify candidate quality attributes grounded in that evidence, avoiding a generic unfiltered checklist.

Track record

Benchmark

14 / 22

test cases passed, vs 9 / 22 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

jabrena / plinth

skills/025-quality-attribute-discovery/SKILL.md

View on GitHub ↗

License Apache-2.0Imported 10/2/2026Version v1Bundled 1 file

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Quality Attribute Discovery

Constraints

When to use this skill

Workflow

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills