CustomerNewsletter

Validates newsletter output against quality standards. Use after Phase 4 assembly to verify the newsletter meets all requirements. Runs automated checks for required sections, link format, forbidden patterns, and structural compliance. Keywords: newsletter validation, quality check, post-pipeline, validation rubric.

Transforms the compiled Phase 3 working set into polished, newsletter-ready content sections, with Phase 1C discoveries used only as a missing-data fallback. Use when running Phase 3 of the newsletter pipeline. Selects and structures high-value items, applies GA/PREVIEW labels, and prepares complete section material for assembly. Keywords: content curation, phase 3, selection, formatting, enterprise relevance.

Fetches and extracts content from Phase 1A URL manifest into 5 interim files by source. Use when running Phase 1B of the newsletter pipeline. Processes URLs sequentially by source, extracts relevant items using universal extraction format, outputs one interim file per source. Keywords: content retrieval, phase 1b, web extraction, interim files.

Processes the human curator's monthly notes file into pipeline-ready content. Reads raw URLs, text hints, and structured sections from the curator's brain dump, classifies each item, filters internal/industry content, visits surviving URLs, and outputs processed items + editorial signals. Use between Phase 1C and Phase 3 when a curator notes file exists. Keywords: curator notes, brain dump, links file, monthly notes, human curation, editorial signals.

Extracts and formats upcoming events and webinars from provided URLs. Use when running Phase 2 of the newsletter pipeline after the Phase 1C discoveries receipt exists. Fetches event pages, classifies into canonical categories, formats virtual and in-person event tables. Keywords: events extraction, phase 2, webinars, conferences, event formatting.

Maintains kb/ knowledge base through automated polling and health checks. Use for monthly kb/ refresh, link health validation, and SOURCES.yaml updates. Polls RSS/Atom feeds for new content, validates canonical URLs, generates delta reports. Keywords: kb maintenance, knowledge base, link health, sources refresh, monthly maintenance.

Applies automated polishing rules to a Phase 4 newsletter before human review. Runs deterministic structural fixes, content-aware normalization, and editorial guidelines mined from 132 actual polishing edits across 14 newsletters. Use as Phase 4.5 between assembly and editorial review. Keywords: polishing, phase 4.5, formatting, normalization, quality, post-assembly.

Fast local code review of staged changes via Copilot CLI. Pipes git diff into copilot -p with full file context and a generic review prompt. Repo-specific rules load automatically from AGENTS.md. Use when you want a quick pre-commit review without the PR overhead. Keywords: code review, local review, make review, pre-commit, staged changes.

Generates a scope manifest at pipeline start and validates against it at pipeline end. The scope contract declares expected versions, sources, date boundaries, and categories -- then post-generation testing verifies all expectations were met. Use at the beginning and end of each newsletter pipeline run. Keywords: scope contract, QA, validation, date range, version scope, pre-generation, post-generation.

Manages AI agent session logs across Copilot CLI and VS Code stores. Health checks, per-repo archival with compression, age-based rotation, and crash forensics. Use when you need to monitor session storage growth, archive sessions per-repo, compress old sessions, investigate crashes/stalls, or detect oversized sessions. Keywords: session log, archive, rotate, compress, health check, forensics, crash RCA, disk usage, session storage.

Generates validated URL manifest from kb/SOURCES.yaml for a given DATE_RANGE. Use when starting Phase 1A of the newsletter pipeline. Reads SOURCES.yaml canonical URLs and feed endpoints, generates candidate URLs per source, validates existence, and outputs a manifest file. Keywords: url manifest, phase 1a, url generation, source discovery.

Matches newsletter entries to official YouTube videos from VS Code and GitHub channels. Fetches RSS feeds, matches by topic, and adds [Video (Xm)](URL) links to relevant newsletter bullets. Use as Phase 4.6 after polishing and before editorial review. Keywords: video matching, youtube, video links, phase 4.6, enrichment.

Assembles all pipeline components into the complete, polished newsletter. Use when running Phase 4 of the newsletter pipeline. Combines Phase 3 curated sections with Phase 2 events, adds introduction and closing, enforces section ordering and quality checks. Keywords: newsletter assembly, phase 4, final assembly, newsletter generation.

Creates complete Agent Skills from user requirements. Use when the user wants to create, build, design, or generate a new skill, or when they describe automation, workflows, or specialized AI capabilities they want to package as reusable skills. Produces SKILL.md files, scripts, references, assets, and examples following the Agent Skills specification (agentskills.io). Keywords: create skill, build skill, new skill, design skill, generate skill.

Merges, deduplicates, and filters 5 interim files for enterprise relevance. Use when running Phase 1C of the newsletter pipeline. Takes 5 source-specific interim files from Phase 1B, consolidates into 30-50 enterprise-relevant discoveries. Keywords: consolidation, phase 1c, deduplication, enterprise filter, discoveries.

Consolidates all deprecation, sunset, revocation, and migration-notice content into a single bundled update under Enterprise and Security Updates, and removes any standalone Migration Notices section. Use when assembling or polishing a newsletter, or when you see duplicated deprecation notes across multiple sections (models, metrics, runner enforcement, token revocations, syntax changes). Keywords: deprecation, deprecated, sunset, migration notice, breaking change, enforcement, revoked, revocation, end-of-life, EOL, retiring.

Applies human editorial corrections to a generated newsletter and produces an updated version. Use as Phase 5 after the human provides corrections. Reads corrections file, applies changes to newsletter, updates intelligence files, captures learnings. Keywords: editorial review, phase 5, corrections, iteration, review loop.

Tests prompt and skill changes using Hypothesis-Implement-Grade-Rework cycles. Use when modifying newsletter prompts, skills, or agent instructions. Compares output against benchmark known-good intermediates. Keywords: test prompt, HIGR testing, prompt validation, benchmark testing.