AGENTIC MEMORY
Skills
Useful instructions for your AI. Search, read and use them through the same MCP connection.
research
Use for any research request that doesn't clearly match a research specialist ('research X', 'look into Y'). Routes with classifier.py to pulse, grants, litreview, syllabus, patent, dossier or deepread, or runs its own cited search.
research
Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading legwork delegated to a background agent.
research-finance
Use for R&D program money: multi-period budgets with indirect cost split, burn and runway against milestones, or capitalize vs expense routing. Runs program_budget_planner.py, burn_runway_tracker.py and capex_vs_opex_router.py.
research-ops-skills
Use when an enterprise research request needs routing (clinical study design, R&D finance, market sizing, user research): 'what sample size', 'R&D budget'. Lists the research-ops skills and routes to one.
research-summarizer
Use when summarizing a research paper, article or report, comparing several sources or extracting citations into a brief. Formats with format_summary.py and pulls citations with extract_citations.py.
resemble-detect
Deepfake detection and media safety — detect AI-generated audio, images, video, and text, trace synthesis sources, apply watermarks, verify speaker identity, and analyze media intelligence using Resemble AI
resolving-ingestion-warnings
Diagnoses and resolves PostHog ingestion warnings — problems recorded while ingesting events (dropped events, rejected person merges, oversized payloads, invalid data). Use when a user asks why events are missing, dropped, or undercounted, why identify/alias calls don't work or accounts stay duplicated, why person or group properties aren't updating or profiles look inflated, why recordings have gaps, heatmaps are empty, LLM token counts are missing, why cookieless events vanish, or whenever the `ingestion_warning` health check fires. Explains severity triage (error = dropped, warning = modified, info = intentional) and routes all warning types — size limits and enrichment, merges and distinct IDs, high-volume distinct IDs, `$process_person_profile`, timestamps, cookieless, heatmaps, transformations, session replay — to per-issue reference files with code-level causes and per-SDK fixes.
responsive-design
Implement modern responsive layouts using container queries, fluid typography, CSS Grid, and mobile-first breakpoint strategies. Use when building adaptive interfaces, implementing fluid layouts, or creating component-level responsive behavior.
resx-source-generator-migration
Migrates a project that uses checked-in .designer.cs files behind .resx to using a source-generator instead
retro
Analyze sprint retrospectives for patterns and action item tracking. Usage: /retro analyze <retro_data.json>
retro
Conduct a retrospective on a coding session.
revenue-operations
Use for pipeline coverage, forecast accuracy or GTM efficiency (magic number, CAC payback). Runs pipeline_analyzer.py, forecast_accuracy_tracker.py and gtm_efficiency_calculator.py.
reverse-engineer-marketing
When the user wants to reverse engineer how another company grew and copy what worked. Also use when the user mentions 'reverse engineer,' 'how did X grow,' 'how does X get customers,' 'growth teardown,' 'marketing teardown,' 'GTM teardown,' 'growth blueprint,' 'what is X doing for marketing,' 'what made X take off,' 'copy X's playbook,' 'X's distribution strategy,' 'what content works for X,' 'funnel hack,' 'map their funnel,' or 'watch what X is doing.' Builds a dated log of a company's moves against its traffic curve from public data, sign-ups and demos, team interviews, and hidden signals (DNS, certificate logs, archives, sponsorships), compares it with the user's own data, and turns what lined up with growth into plays routed to the skill that runs each one. For a snapshot profile of a competitor's positioning, pricing, and features, see competitor-profiling. For comparison pages, see competitors. For why a single post went viral, see social.
review-agent-setup
Configure human-in-the-loop gating for AI agent review actions in Claude Code. Use when setting up a project where an agent may post PR reviews, comments, merges, or edit CI configuration, and you want a cryptographically auditable approval trail with Cedar-enforced gates.
review-and-refactor
Review and refactor code in your project according to defined instructions
review-hog-authoring
How to author custom PostHog Review skills: the review perspectives, blind-spot checks, validation criteria, and resolution criteria that drive PostHog Review's automated PR reviews. Use when a user wants a new review perspective (a specialist lens on their PRs), a custom blind-spot sweep, their own validation bar for which findings get published, or their own bar for which review comments get implemented. Trigger on "create a PostHog Review perspective", "custom review perspective", "my own blind-spot check", "custom validation criteria", "custom resolution criteria", "tune what PostHog Review publishes", "tune what PostHog Review implements".
review-hog-blind-spots-general
Checks each chunk for issues the other reviewers missed. Uses their findings to avoid repeating them.
review-hog-perspective-contracts-security
Checks security, input validation, and API compatibility. Reports security and contract issues only.
review-hog-perspective-logic-correctness
Checks business logic, edge cases, data transformations, and queries. Reports correctness issues only.
review-hog-perspective-performance-reliability
Checks resource use, error recovery, and scaling. Reports performance and reliability issues only.
review-hog-resolution-criteria
Implements safe, verifiable fixes from review comments. Explains declined requests and asks a human to handle risky changes.
review-hog-resolution-criteria-gaps
Fixes should-fix and must-fix bugs and missing functionality. Leaves wording, documentation, and style suggestions to the author.
review-hog-resolution-criteria-small
Fixes small bugs, typos, wording, and outdated documentation. Leaves changes that need a design decision to the author.
review-hog-validation-criteria
Keeps findings that affect correctness, security, data, API compatibility, or performance. Drops speculative issues and style suggestions before publishing.
Third-party instructions in their original language. Reading does not install files, run code or grant permissions. Snapshots are updated only after review.