Fähigkeiten product-design-harness
📦

product-design-harness

Inhaltsrevision r3 Sicher 📁 Dateisystemzugriff🌐 Netzwerkzugriff⚙️ Externe Befehle

Review Product Decisions Before Execution

Product teams can build quickly before testing their assumptions. This skill reviews user needs, evidence, and business viability to define a bounded next step.

Unterstützt: Claude Codex Code(CC)
Maintain this Skill? Claim it 🥉 78 Bronze

Mit meinem Agent installieren

Kopieren Sie diese Anfrage in Ihren Agent. Sie enthält die maßgebliche Skill-Seite und das Manifest.

Agent-Anfrage
Review the Skillstore skill "product-design-harness" from https://skillstore.io/skills/cis2042-product-design-harness.md and its manifest at https://skillstore.io/api/skills/cis2042-product-design-harness/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.

Ihr Agent sollte weiterhin seinen Plan anzeigen und alle von der Sicherheitsrichtlinie verlangten Bestätigungen anfordern.

Agent-lesbare Ressourcen

Verwenden Sie diese Links, wenn ein KI-Agent, Crawler oder Skript sauberen Kontext benötigt, statt die vollständige Seite zu lesen.

Markdown-Detailseite GET /skills/cis2042-product-design-harness.md Signiertes manifest GET /api/skills/cis2042-product-design-harness/manifest Signiertes lockfile GET /api/skills/cis2042-product-design-harness/lockfile

Testen

„product-design-harness“ wird verwendet. Review weekly report exports requested through support tickets, without evidence of managers' current reporting behavior.

Erwartetes Ergebnis:

  • Verdict: Verify. Weakest flow: Evidence.
  • Missing proof: recurring reporting work and the cost of the current workaround.
  • Next action: test a static report sample during workflow interviews.
  • Boundary: no scheduled exports, live customer data access, or external delivery.

„product-design-harness“ wird verwendet. Review a proposed product direction supported only by untraceable founder impressions.

Erwartetes Ergebnis:

  • Verdict: Stop/Reframe. Evidence tier: t0.
  • Reason: no traceable signal supports the core problem.
  • Reframed question: which specific actor experiences a recurring problem that can be observed?
  • Boundary: research and reframing only; no implementation handoff.

„product-design-harness“ wird verwendet. Prepare an implementation handoff from an approved continue review and its linked evidence receipts.

Erwartetes Ergebnis:

  • Handoff: context pack linked to the approved review.
  • Scope: exact copy of the review's allowed actions.
  • Controls: preserve approval gates, prohibited actions, unresolved assumptions, and stop conditions.
  • Validation: check the review and context pack together before implementation.

Sicherheitsaudit

Sicher
v3 • 23.10.2026 Versionsbericht öffnen

All 133 static findings are false positives involving documentation, schema identifiers, review terminology, or benign local validation logic. No evidence found of credential access, unauthorized data transfer, shell substitution, or audit-directed prompt injection in the reviewed context. Documented verdict overrides concern accountable product decisions, not permission to override security controls.

91
Gescannte Dateien
9,551
Analysierte Zeilen
0
Prüfelemente
0
Falschmeldungen ignoriert

Risikofaktoren

📁 Dateisystemzugriff (10)
resources/docs/CODING-HARNESS-COMPARISON.md:3 resources/docs/CODING-HARNESS-COMPARISON.md:30 resources/docs/HARNESS.md:3 resources/docs/HARNESS.md:133 resources/docs/README.md:19 resources/docs/UX3.md:15 resources/docs/UX3.md:98 resources/examples/stop-reframe-review.md:8 resources/prompts/mode-selector.md:42 resources/templates/README.md:12
🌐 Netzwerkzugriff (38)
resources/docs/HARNESS.md:38 resources/schemas/actor-boundary.schema.json:2 resources/schemas/actor-boundary.schema.json:3 resources/schemas/claim-analysis.schema.json:2 resources/schemas/claim-analysis.schema.json:3 resources/schemas/claim.schema.json:2 resources/schemas/claim.schema.json:3 resources/schemas/context-pack.schema.json:2 resources/schemas/context-pack.schema.json:3 resources/schemas/council-input.schema.json:2 resources/schemas/council-input.schema.json:3 resources/schemas/decision-rule.schema.json:2 resources/schemas/decision-rule.schema.json:3 resources/schemas/evidence-request.schema.json:2 resources/schemas/evidence-request.schema.json:3 resources/schemas/evidence-response.schema.json:2 resources/schemas/evidence-response.schema.json:3 resources/schemas/evidence.schema.json:2 resources/schemas/evidence.schema.json:3 resources/schemas/human-decision.schema.json:2 resources/schemas/human-decision.schema.json:3 resources/schemas/ontology.schema.json:2 resources/schemas/ontology.schema.json:3 resources/schemas/product-brief.schema.json:2 resources/schemas/product-brief.schema.json:3 resources/schemas/red-team-review.schema.json:2 resources/schemas/red-team-review.schema.json:3 resources/schemas/review-result.schema.json:2 resources/schemas/review-result.schema.json:3 resources/schemas/reviewer-verdict.schema.json:2 resources/schemas/reviewer-verdict.schema.json:3 resources/schemas/session-config.schema.json:2 resources/schemas/session-config.schema.json:3 resources/schemas/uncertainty-review.schema.json:2 resources/schemas/uncertainty-review.schema.json:3 resources/schemas/verdict-override.schema.json:2 resources/schemas/verdict-override.schema.json:3 resources/scripts/check_review.py:47
⚙️ Externe Befehle (19)
SKILL.md:19 SKILL.md:20 SKILL.md:21 SKILL.md:23 SKILL.md:25 SKILL.md:27 SKILL.md:28 SKILL.md:30 SKILL.md:31 SKILL.md:64 SKILL.md:78 SKILL.md:80 SKILL.md:81 SKILL.md:103 SKILL.md:104 SKILL.md:105 SKILL.md:106 SKILL.md:107 SKILL.md:108
Das letzte abgeschlossene statische und semantische Audit erkannte keine bestätigten Sicherheitsbefunde. Dies beweist nicht, dass der Skill keine Nebenwirkungen hat.
Geprüft von: codex Audit-Verlauf anzeigen →
Diesen Bericht teilen & zitieren

Teile den versionierten Bewertungsbericht, das neutrale Badge, die Einbettungskarte und Zitate. Skillstore berichtet Nachweise, ohne zu entscheiden, ob dieser Skill sicher ist.

Versionsbericht öffnen
Sicherheitsbewertung

Berichtslink kopieren

https://skillstore.io/skills/cis2042-product-design-harness/audits/3?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown-Badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/cis2042-product-design-harness/security.svg)](https://skillstore.io/skills/cis2042-product-design-harness?utm_source=security_passport_badge)

HTML-Badge

<a href="https://skillstore.io/skills/cis2042-product-design-harness?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/cis2042-product-design-harness/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Einbettungskarte

<iframe src="https://skillstore.io/embed/skills/cis2042-product-design-harness.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>
Wissenschaftliche Zitate (APA · BibTeX · CFF)

APA-Zitat

cis2042. (2026). product-design-harness security audit report (audit version 3) [Author version unspecified]. Skillstore. https://skillstore.io/skills/cis2042-product-design-harness/audits/3

BibTeX-Zitat

@techreport{cis2042-cis2042-product-design-harness-2026, author = {cis2042}, title = {product-design-harness security audit report (audit version 3)}, institution = {Skillstore}, year = {2026}, number = {3}, url = {https://skillstore.io/skills/cis2042-product-design-harness/audits/3}, note = {Author version unspecified} }

CITATION.cff

cff-version: 1.2.0 message: "If you use this Skill, cite its author and this versioned security audit report." title: "product-design-harness security audit report (audit version 3)" version: "unspecified" type: report authors: - name: "cis2042" date-released: "2026-10-23" url: "https://skillstore.io/skills/cis2042-product-design-harness/audits/3" identifiers: - type: other value: "skillstore:cis2042-product-design-harness:audit:3" description: "Skillstore immutable audit report identifier"

Skillstore-Score

Warum dieser Score Evidenzvertrauen: Mittel
55
Architektur
85
Wartbarkeit
87
Inhalt
65
Gemeinschaft
91
Spezifikationskonformität

Was Sie erstellen können

Assess a Feature Request

Review a proposed feature against user problems, supporting evidence, ownership cost, and the smallest useful test.

Challenge a Prototype Direction

Separate interview opinions from observed behavior and identify assumptions that require a focused prototype test.

Prepare a Bounded Agent Handoff

Validate an approved review and matching context pack before assigning implementation work to coding agents.

Diese Prompts ausprobieren

Start a Product Review 
Review this product direction: [direction]. Current evidence: [sources]. Owner and organization: [details]. Select a mode and list missing intake. Do not implement.
Run a Standard Gate 
Run Standard Gate for [feature] at [stage]. Use [brief and evidence]. Review all three flows independently. Return the canonical review with boundaries and stop conditions.
Challenge a Risky Direction 
Run UX3 Council for [decision]. Use [brief, evidence receipts, and owner]. Decompose claims, review lanes independently, and complete challenge rounds. Red-team unanimous continue results before synthesis.
Validate an Implementation Handoff 
Use [continue review] to create a matching context pack. Copy scope and controls exactly. Validate both artifacts with the bundled checker. Report failures without implementing.

Bewährte Praktiken

  • Provide traceable evidence, counter-signals, affected stakeholders, and a named accountable owner before requesting a decision.
  • Choose the smallest responsible review mode and keep human judgment separate from evidence tiers.
  • Validate review artifacts and linked context packs together; review again when scope, data, risk, or stakeholders change.

Vermeiden

  • Treating quotes, simulated users, or internal confidence as proof of real behavior.
  • Averaging reviewer verdicts or removing counter-evidence to obtain approval.
  • Turning a verify result into general implementation work or expanding an approved context pack.

Häufig gestellte Fragen

What does this skill review?
It reviews product directions, features, workflows, experiments, launches, automation, and scaling decisions through user, evidence, and business perspectives.
Which review mode should I use?
Use Quick Gate for small reversible changes, Standard Gate for new features, and UX3 Council for high uncertainty or meaningful risk.
What outcomes can a review return?
Continue permits a bounded handoff, verify permits one proof step, and stop_reframe returns a better product question.
Does the skill collect research automatically?
It defines evidence request and receipt contracts. Actual retrieval requires available tools or connectors; the bundled routing helper makes no model calls.
Do valid review artifacts prove that a decision is safe?
No. Validators check structure and selected consistency rules. They do not verify evidence truth, grant human approvals, or enforce runtime permissions.
Can I use this with Claude, Codex, and Claude Code?
Yes. The bundle provides Markdown instructions, schemas, examples, and Python validators. Your runtime must supply agent orchestration and any external tools.

Entwicklerdetails

Autor

cis2042

Lizenz

MIT

Skillstore-Revision

r3

Versionshinweis

Der Autor hat keine Version angegeben.

Repository

https://github.com/cis2042/ux3-product-design-harness/tree/7f9f724c5e31813d1c35767f9f454fe9a1e96891/skills/product-design-harness

Ref.

3ee31ca64e16a02feb0f8db8f012ecc0de8a2c34

Aktualität der Wartung

23.10.2026

Nutzung

5 Downloads · 0 Aufrufe

Dateistruktur

📄 LICENSE

📁 resources/

📁 agents/

📄 business-flow-reviewer.md

📄 claim-analyst.md

📄 council-facilitator.md

📄 evidence-flow-reviewer.md

📄 README.md

📄 registry.json

📄 uncertainty-reviewer.md

📄 user-flow-reviewer.md

📁 assets/

📄 decision-gate.svg

📄 harness-sequence.svg

📁 docs/

📄 ADOPTION.md

📄 ANTI-PATTERNS.md

📄 CLAIMS.md

📄 CODING-HARNESS-COMPARISON.md

📄 CONTRACTS.md

📄 COUNCIL.md

📄 DECISION-RULES.md

📄 GLOSSARY.md

📄 HARNESS.md

📄 LEARNING-LOOP.md

📄 LIVE-CODING.md

📄 MULTI-AGENT-ALIGNMENT.md

📄 OPERATING-PROTOCOL.md

📄 ORCHESTRATION.md

📄 PRINCIPLES.md

📄 README.md

📁 rfcs/

📄 0001-override-protocol.md

📄 UNCERTAINTY.md

📄 UX3.md

📁 examples/

📄 evidence-response.json

📄 feature-gate-review.md

📄 human-decision.json

📄 live-coding-context-pack.json

📄 live-coding-product-brief.json

📄 live-coding-review.json

📄 quick-context-pack.json

📄 quick-gate-review.json

📄 quick-gate-review.md

📄 README.md

📄 red-team-review.json

📄 standard-gate-review.json

📄 stop-reframe-review.json

📄 stop-reframe-review.md

📄 ux3-council-input.json

📄 ux3-council-review.json

📄 ux3-council-review.md

📄 verdict-override.json

📄 verdict-override.md

📁 knowledge/

📄 ontology.json

📄 rules.json

📄 source-chapters.json

📁 prompts/

📄 claim-analysis.md

📄 gate-review.md

📄 intake.md

📄 mode-selector.md

📄 README.md

📄 red-team.md

📄 start-review.md

📄 ux3-council.md

📄 requirements-dev.txt

📁 schemas/

📄 actor-boundary.schema.json

📄 claim-analysis.schema.json

📄 claim.schema.json

📄 context-pack.schema.json

📄 council-input.schema.json

📄 decision-rule.schema.json

📄 evidence-request.schema.json

📄 evidence-response.schema.json

📄 evidence.schema.json

📄 human-decision.schema.json

📄 ontology.schema.json

📄 product-brief.schema.json

📄 README.md

📄 red-team-review.schema.json

📄 review-result.schema.json

📄 reviewer-verdict.schema.json

📄 session-config.schema.json

📄 uncertainty-review.schema.json

📄 verdict-override.schema.json

📁 scripts/

📄 check_override.py

📄 check_review.py

📄 jev_gate.py

📁 templates/

📄 context-pack.md

📄 decision-log.md

📄 gate-review.md

📄 override-ledger.md

📄 product-brief.md

📄 README.md

📄 ux3-council-review.md

📄 SKILL.md

Ähnliche Skills

Alle anzeigen