Productivity & Workflow Agent Skills for Perplexity

Drive dirtywork — delegate a coding task to a local model that works in an isolated git worktree, then review the result, resume it with…

Browse, search, read, upload, and share the user's Dropbox — including team/shared folders — through per-user OAuth.

Use when a question requires comprehensive evidence gathering from multiple sources, systematic synthesis, and traceable citations…

Use when engineering needs testable, implementable technical requirements — not a PRD but a capability spec with acceptance criteria, task…

Use when a task must stay inside a narrow file or directory boundary, or when risky commands need an explicit stop rule — define the…

Use when implementing framework-specific or library-specific code — verify non-trivial APIs against official documentation before writing…

Use when a plan, spec, or PRD must become an actionable backlog — break it into thin dependency-aware issues that each deliver a…

Use before claiming any task is done — run the exact command that proves the fix works, read the output, and only then report success.

When it comes to DSA: elements of the offense, evidentiary issues and the evidence situation in DSA, DMA and EU digital regulation: the…

Scaffolds, builds, and releases DeepSeek Harness (DSH) Web plugins with full Cordis runtime, RPC channel, and GUI support.

Maintain a persistent `.context/ISSUE/` directory for complex engineering work spanning sessions or coding agents.

Agent-only policy for completing investigations and visual reviews without losing unresolved captain decisions.

Inspect or select subscription accounts for the current Dex routed session.

Design task-local harnesses, eval gates, and reusable skill extraction for Claude dynamic workflow mode and other adaptive agent harnesses.

User researcher — interviews, personas, Jobs-to-Be-Done, and customer feedback synthesis.

Helps users discover and install capabilities from the open agent skills ecosystem.

Audit your entire .claude ecosystem (skills, agents, slash commands, hooks, rules, memory) for duplicates, overlapping capabilities, stale…

Use when produce mechanical interface control documents (MICDs) under ECSS-E-ST-10-24C §5.11: categorize each mechanical interface as…

Use when drafting a The Econometrics Journal response letter and revision plan after a referee report, especially for assumptions, proofs…

Use when running the final The Econometrics Journal pre-submission check for Editorial Express, RES/OUP template compliance, 20-page…

Use when sequencing a The Econometrics Journal manuscript from venue fit through leading-case framing, asymptotic identification, Monte…