Learning & Documentation Agent Skills for Perplexity

Extract reusable patterns from the session, self-evaluate quality before saving, and determine the right save location (Global vs Project).

Analyze local git history to extract coding patterns and generate SKILL.md files.

Design a source evaluation protocol using lateral reading and credibility checks for digital information.

Use when evaluating the trustworthiness of external websites, research data, or cited literature to audit and select Tier 1/Tier 2…

Evaluate source quality, build annotated bibliographies, and maintain curated reference collections.

Synthesize multiple documents into a traceable brief, report, comparison, or decision memo when claims must remain faithful to supplied or…

Ground version-sensitive external claims and implementation choices in authoritative evidence.

The canonical, extensible source-type registry for a research corpus — paper, preprint, blog, repo, book, chapter, standard, doc…

Cross-validates research facts and evaluates source credibility before content creation to ensure factual accuracy.

Use when citing authority in a Harvard Law Review (HLR) piece — pinpoint citations, the authority hierarchy, and The Bluebook (which HLR…

Use when building and formatting the citation apparatus for a The Yale Law Journal (YLJ) piece — pinpoint cites, Bluebook form, and source…

Generate AI-friendly repository documentation with the SourceSage CLI.

Build students' capacity to interrogate a historical source before reading — asking who authored it, when, why, and what this means for…

Documentation templates and structure guidelines.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that…

Manages spaced repetition review sessions and calculates recall intervals to ensure long-term knowledge retention.

Set up Speak language learning API integration and authentication.

Use when creating, reviewing, or updating SPEC.md files, running /specout, or entering the ADF SPEC gate.

Check that a spec has need, scope, impacts, tests, assumptions, open questions and links to relevant corpus files.

How a project's agent-facing documentation is run so it stays true: one job per doc, facts flowing DECISIONS → SPECS → IMPL with the copy…

Turn a raw need into a spec package grounded in corpus facts and explicit assumptions.