Agent skills for Perplexity

Use when the user wants completed Codex or agent work checked before accepting it: project-goal fit, task fit, hallucinated code…

Use when preparing to deploy a service or release, especially when verifying tests, approvals, migrations, feature flags, rollback…

Create or revise evidence-backed engineering diagrams that explain system context, component ownership, data movement, runtime…

Use when writing or updating technical documentation such as READMEs, API docs, runbooks, architecture docs, or onboarding guides.

Apply proportional truth, scope, authority, simplicity, and verification discipline to substantive engineering work.

Define the universal engineering philosophy for all platform skills: discovery, contracts, anti-slop, quality gates.

Use when triaging a production incident, drafting status updates, assessing severity, coordinating mitigation, or writing a blameless…

Index of engineering failure-mode skills — routes to the right one for evidence-driven bug hunting, fuzzing, data correctness, resilience…

This skill should be used when the user asks to "design an onboarding plan", "write a 30/60/90 day plan for a new engineer", "set up…

Apply a compact set of engineering principles to substantial design, migration, operations, concurrency, and maintenance decisions.

Drafts, refines, and structures Chinese engineering project proposals and technical grant applications with professional industry phrasing.

Automatically discover software engineering practice skills when working with code review, documentation, pair programming, production…

Use when designing a system, service, or architecture from requirements and constraints, especially for API design, data modeling, service…

Use when designing a test strategy, choosing test types and coverage priorities, or building a test plan for APIs, data pipelines…

Drafts, extends, and revises English academic papers with automated citation verification, structural integrity checks, and…

Product and business-rule guardrails for Engram.

Commit and branch naming standards for Engram contributors, enforced by GitHub rulesets.

Cultural and collaboration norms for Engram contributors and agents.

HTMX and templ interaction rules for the Engram dashboard.

Persistent memory discipline for Engram contributors.

Repository structure and placement rules for Engram.