poly-gents/syncolab-skills - Page 8

shadow-qa-lead

Test strategy and exploratory charter — risk-based coverage and edge-case hunting.

Langue du texte source : anglais

shadow-qa-reporter

Structured bug reporting and triage — repro, environment, expected vs actual, severity.

Langue du texte source : anglais

shadow-release-lander

Land-and-deploy discipline — merge, deploy sequence, verification, and rollback readiness.

Langue du texte source : anglais

shadow-release-scribe

Release documentation — user-facing notes, internal runbooks, and version narrative.

Langue du texte source : anglais

shadow-retro-lead

Facilitation pattern for sprint or weekly retros — safety, themes, experiments, and follow-through.

Langue du texte source : anglais

shadow-review-board

Orchestrates a staged review — strategy, design intent, engineering, and DX — with merged findings.

Langue du texte source : anglais

shadow-second-opinion

Independent challenge of a plan or review — assumptions, blind spots, and devil’s advocate arguments.

Langue du texte source : anglais

shadow-security-officer

Security and abuse review using STRIDE-style and OWASP-style lenses on the plan and surfaces.

Langue du texte source : anglais

shadow-ship-manager

Shipping checklist — PR quality, CI, risk, and communication for merge and release.

Langue du texte source : anglais

slack

Automates Slack messages, channels, search, reactions, and threads via Rube MCP (Composio). Use after RUBE_SEARCH_TOOLS and an ACTIVE Slack workspace connection.

Langue du texte source : anglais

snyk

Runs Snyk dependency and code security scans, prioritizes findings by severity and exploitability, and proposes minimal-breakage remediations. Use when auditing vulnerabilities or validating fixes.

Langue du texte source : anglais

suggest-knowledge

Recommend knowledge base articles to resolve issues

Langue du texte source : anglais

suggest-refactors

Identify code smells and propose improvements

Langue du texte source : anglais

suggest-updates

Flag stale content and suggest improvements

Langue du texte source : anglais

summarize-client-calls

Capture and summarize key points from client conversations

Langue du texte source : anglais

sync-docs

Keep documentation aligned with code changes

Langue du texte source : anglais

syncolab-cognitive-memory

Guides Syncolab Cognitive Memory Layer (CML)—Qdrant + Mem0 composite, tenant scope, REST memory endpoints, and TS agent recall/persist. Use for long-term memory hydration and external runtime memory_layer contracts.

Langue du texte source : anglais

syncolab-living-docs

Searches and reads Syncolab Living Docs (SKS) and proposes human-reviewed patches via sks_docs_* tools. Use for authoritative platform docs, internal/external facets, and minimal doc drift fixes.

Langue du texte source : anglais

tell-data-stories

Transform data findings into narrative insights

Langue du texte source : anglais

test-driven-development

Use when implementing any feature or bugfix, before writing implementation code

Langue du texte source : anglais

test-fixing

Run tests and systematically fix all failing tests using smart error grouping. Use when user asks to fix failing tests, mentions test failures, runs test suite and failures occur, or requests to make tests pass.

Langue du texte source : anglais

testing-patterns

Jest testing patterns, factory functions, mocking strategies, and TDD workflow. Use when writing unit tests, creating test factories, or following TDD red-green-refactor cycle.

Langue du texte source : anglais

threat-modeling

Performs STRIDE-style threat modeling on features and systems with ranked mitigations and residual risk. Use before shipping new surfaces, auth flows, or third-party integrations.

Langue du texte source : anglais

track-follow-ups

Monitor and coordinate follow-up actions for client accounts

Langue du texte source : anglais

track-impediments

Identify, escalate, and resolve delivery blockers

Langue du texte source : anglais

track-invoices

Monitor outstanding invoices and match to purchase orders

Langue du texte source : anglais

track-pipeline

Monitor opportunity progress and pipeline health

Langue du texte source : anglais

track-risks

Maintain and prioritize the security risk register

Langue du texte source : anglais

transcribe-live

Real-time speech-to-text transcription of calls

Langue du texte source : anglais

triage-inbox

Summarize, prioritize, and route incoming email threads

Langue du texte source : anglais

tune-queries

Optimize slow database queries for performance

Langue du texte source : anglais

tune-seo

Optimize website metadata and structure for search

Langue du texte source : anglais

typescript-expert

TypeScript and JavaScript expert with deep knowledge of type-level programming, performance optimization, monorepo management, migration strategies, and modern tooling. Use PROACTIVELY for any TypeScript/JavaScript issues including complex type gymnastics,…

Langue du texte source : anglais

update-cms

Publish content updates to CMS-powered websites

Langue du texte source : anglais

upstream-patches

Manage upstream Terraform patch stacks in provider repos.

Langue du texte source : anglais

vectorize

Runs semantic RAG and vector search over indexed knowledge via Vectorize MCP tools discovered at runtime. Use for memory retrieval, knowledge-base lookup, and evidence-backed answers from chunks.

Langue du texte source : anglais

workflow-automation

Workflow automation is the infrastructure that makes AI agents reliable. Without durable execution, a network hiccup during a 10-step payment flow means lost money and angry customers. With it, workflows resume exactly where they left off. This skill covers…

Langue du texte source : anglais

write-agent-documentation

Create, maintain, and improve repository documentation that helps coding agents understand the project, follow engineering standards, make safe changes, and work consistently across tools such as Claude Code, Cursor, GitHub Copilot, Codex, and other AI coding…

Langue du texte source : anglais

write-frontend-tests

Create end-to-end and visual regression tests

Langue du texte source : anglais

writing-plans

Use when you have a spec or requirements for a multi-step task, before touching code

Langue du texte source : anglais