borghei/Claude-Skills

📦 Highlights

• 43 new skills across 3 tiers, 1 new domain (`research/`), and 5 new C-suite advisors.
• Skill count: 294 → 338 (+44 incl. previous)
• Domain count: 15 → 16
• Python tools: 720+ → 784+ (stdlib only)

📦 Tier 1 — 17 deep skills (engineering, commercial, compliance, marketing)

• Engineering (6):
• `feature-flags-architect` — flag audit, rollout simulator, kill switch runbook
• `chaos-engineering` — experiment designer, blast radius calculator, gameday planner
• `kubernetes-operator` — CRD validator, operator scaffold, reconciliation audit
• `azure-cloud-architect` — architecture validator, cost estimator, WAF scorer
• `gcp-cloud-architect` — architecture validator, cost estimator, CAF scorer
• `data-quality-auditor` — DQ check runner, schema drift detector, freshness monitor
• Business-growth — commercial mechanics (4):
• + 5 more

✨ Tier 2 — 14 deep skills (C-suite, product, new research/ domain)

• C-level advisory (5):
• `chief-ai-officer-advisor` — AI maturity, investment planner, risk register (NIST AI RMF / ISO 42001 / EU AI Act)
• `chief-data-officer-advisor` — data maturity, DAMA-DMBOK governance audit, platform evaluator
• `chief-customer-officer-advisor` — CX maturity, churn intervention, VoC program designer
• `general-counsel-advisor` — legal risk register, contract portfolio analyzer, regulatory calendar
• `vpe-advisor` — engineering org health, DORA/DevEx dashboard, capacity planner
• Product team (5):
• `product-analytics` — metric tree designer, event taxonomy auditor, retention cohort analyzer
• + 9 more

📦 Tier 3 — 12 PM skills (PM 54 → 66)

• Strategy frameworks — new `project-management/strategy-frameworks/` subfolder (5):
• `business-model-canvas` — Osterwalder 9-block + cross-block coherence validator
• `lean-canvas` — Ash Maurya startup canvas + unfair-advantage discipline
• `swot-analysis` — SWOT + TOWS matrix + evidence audit
• `porters-five-forces` — industry analysis + strategy translation
• `ansoff-matrix` — growth quadrants + stage-appropriate investment mix
• Go-to-market — new `project-management/gtm/` subfolder (2):
• `gtm-strategy` — ICP × motion × channels × messaging × T-90 to T+90 sequence
• + 8 more

📝 Documentation

• README: added Claude Cowork plugin install section (3-step flow — Customize → Browse plugins → repo name)
• bundles.json: 15 → 20 bundles. New: `research-stack`, `fractional-c-suite`, `customer-experience-stack`, `strategy-frameworks-kit`, `gtm-launch-kit`
• Per-domain CLAUDE.md refreshed with new skill counts and Tier 2/3 additions
• docs/SKILLS.md updated with Tier 2 and Tier 3 sections

📦 Stats

• 285+ new files
• ~73K lines (markdown + Python)
• 110 stdlib-only Python tools (no external deps)
• All scripts pass `--help` smoke test
• All bundles validate; all skill paths resolve

📦 TL;DR

• ~30,000 lines added since v4.2.0, across 9 atomic commits and 12+ background-agent passes.

📦 Domain expansion (v4.3.0 + v4.4.0)

• PM grew from 25 → 54 skills (+29 new). Added modern AI/growth PM (`ai-feature-prd`, `activation-funnel`, `feature-flag-strategy`), strategy (`product-vision`, `quarterly-planning`), execution gaps (`post-mortem`, `customer-feedback-triage`, `pricing-prd`), career growth (`pm-interview-prep`, `pm-career-ladder`, `pm-onboarding`, `pm-1on1s`), integrations (`linear-expert`, `notion-pm`, `productboard-expert`), and discovery (`customer-interview-script`, `value-proposition-canvas`, `jtbd-workshop`, `interview-synthesis`).
• Library total: 245 → 294 skills across 15 domains.
• 4 new PM-focused bundles in `bundles.json`: `pm-starter-pack`, `pm-scrum-master`, `pm-discovery-coach`, `pm-career-track`.

📦 Tier 1 of the depth investment (v4.5.0)

• 54 worked examples, one per skill (~13k lines). Each has a realistic fictional scenario (Acme Analytics, Wayfinder, Northwind, Helix Platform, Pylon), the workflow applied, and the FULL generated artifact PMs can copy.
• 3 live data adapters at `tools/adapters/` — pull from Jira / Linear / Notion APIs and emit JSON in the shapes PM Python tools expect. Stdlib only, env-var auth.
• 15 MCP tools registered in `scripts/mcp_server.py`. Each PM skill callable from any AI conversation: `pm_create_prd`, `pm_status_update`, `pm_funnel_analyze`, `pm_flow_metrics`, `pm_dependency_map`, `pm_feedback_triage`, `pm_nsm_tree`, `pm_refinement_score`, `pm_interview_synthesize`, `pm_prioritize`, `pm_okr_validate`, `pm_roadmap_transform`, `pm_pre_mortem`, `pm_release_notes`, `pm_stakeholder_map`.

📦 Tier 2 of the depth investment (v4.6.0)

• 54 red-flag libraries, one per skill (~12k lines). Each lists 10-12 concrete anti-patterns with paired bad/good quoted artifact snippets and a "How to catch it" check question. Anchored to canonical authors (Wodtke, Wake, Lawrence, Vacanti, Allspaw, Dekker, Klein, Klement, Ellis, McClure, Karpathy, Anthropic RSP, Ramanujam, Westendorp, etc.).
• 5 runnable pipelines at `pipelines/` — chain 3-7 PM skills end-to-end with one command: `feature-end-to-end`, `weekly-cadence`, `customer-discovery`, `post-mortem-flow`, `launch-coordination`. Each supports `--demo`, `--input`, `--format markdown|json`, `--output <dir>`.

📦 Tier 3 of the depth investment (v4.7.0)

• Output eval harness at `evals/` — deterministic scoring of any markdown artifact, no LLM needed.
• `engine.py` — 13 supported check types (regex, section_present, keyword_none, has_table, etc.)
• `run.py` — runner with `--all`, `--skill`, `--artifact`, `--threshold`, `--format` flags
• 12 rubrics with 190+ criteria total, each anchored to a specific red-flag or success-criterion item
• Smoke-test: 12/12 worked examples pass at threshold 70. Average score 96.4.

🐛 Infrastructure fixes

• `scripts/build_manifest.py` now recurses into container folders (`discovery/`, `execution/`, `career/`). Previously the registry undercounted PM by ~30 nested skills.
• `.claude/settings.json` hooks use `$CLAUDE_PROJECT_DIR` instead of relative paths — works regardless of CWD.
• `.github/workflows/sync-codex-skills.yml` retries push on concurrent-bot race condition (rebase + retry up to 3 times). Fixes a fragile-but-non-blocking workflow failure.

📦 Website (`borghei.github.io/Claude-Skills`)

• New dedicated PM landing page at `/skills/project-management/`.
• Front-page hero refreshed: 266 → 294 skills, 17 → 15 domains, "cs-* Agents" → "Expert Agents". New 18-compliance-frameworks stat.
• PM domain card highlighted with border + new tags (`ai-prd`, `linear`, `notion`, `productboard`).
• Section heading rewrites: "Key Features" → "How it works"; "Cross-Domain Personas" → "Pre-built expert identities"; "Starter Bundles" → "Ready-made kits by role"; "Platform Support" → "Works with your AI assistant".
• Install section now leads with Try it now (chat) + Save to my AI; npx demoted to "For developers".
• All em dashes replaced with context-appropriate punctuation (period / comma / colon / parens) across README and front page.

📦 Repository metadata

• GitHub description updated to highlight PM and regulated industries.
• Topics refreshed: added `project-management`, `product-management`, `linear`, `notion`, `jira`, `agile`; removed lower-value tags.

📦 Branch hygiene

• Two fully-merged stale feature branches removed (`feature/product-pm-skills-upgrade`, `feature/skill-pattern-adoption`).
• Repo is one branch only: `main`.

📦 Final PM domain layout

• | Layer | Count |
• |---|---|
• | Skills | 54 |
• | Worked examples (per-skill) | 54 |
• | Red-flag libraries (per-skill) | 54 |
• | Python tools | 9+ |
• | Live data adapters | 3 (Jira / Linear / Notion) |
• | MCP tools | 15 |
• + 4 more

💥 Breaking changes

• None. Fully additive.

📦 Upgrade path

• ```bash
• npx @borghei/claude-skills add pm-starter-pack
• ```
• Or browse the [PM domain on the live site](https://borghei.github.io/Claude-Skills/skills/project-management/).

📦 Highlights

• 3 new skill domains: `personal-productivity/` (10 skills), `documents/` (4 skills, stdlib OOXML), `vertical-advisors/` (7 strategic founder advisors)
• 41 new `cs-*` agents across engineering (21), c-level (9), marketing (4), business-growth (3), HR (2), product (2), and a new vertical agent tier (7)
• 21+ new Python tools — all stdlib only, all smoke-tested

📦 `personal-productivity/` — 10 skills

• Resume tailor · lead researcher · meeting insights · domain name brainstormer · invoice organizer · email triage · calendar prep · investor update generator · pitch deck reviewer · weekly review.
• Each skill ships SKILL.md, a stdlib-only Python tool with `--json` output, a reference guide, and a user-facing template.

📝 `documents/` — 4 skills (stdlib-only OOXML / PDF parsing)

• `docx-toolkit` — comments, tracked changes, heading gaps, style sprawl
• `pdf-toolkit` — metadata leakage, encryption, JavaScript, embedded files
• `pptx-toolkit` — slide density, hidden slides, speaker notes, animations
• `xlsx-toolkit` — hidden sheets, external links, formula density, named ranges
• No `python-docx` / `python-pptx` / `openpyxl` / `pypdf` required — uses `zipfile` + `xml.etree` for OOXML and regex for PDF.

📦 `vertical-advisors/` — 7 strategic advisors

• Industry-specific strategic advisory complementing the implementation-focused `ra-qm-team/`:
• fintech — US/EU regulatory triggers, license-vs-partner playbook, KYC/AML, embedded finance
• healthtech — HIPAA scope, FDA SaMD classification, payor/provider/employer GTM, value-based care
• edtech — FERPA / COPPA / state laws, K-12 vs higher ed vs corporate L&D dynamics
• ecommerce — unit economics, fulfillment models, channel strategy
• proptech — segments, MLS / brokerage, RESPA / fair housing
• climate-tech — categories, GHG accounting, IRA / DOE / VC funding stack
• marketplace — chicken-and-egg, take-rate design, liquidity / network effects
• + 1 more

✨ 41 New `cs-*` Agents

• | Domain | New agents |
• |---|---|
• | C-Level (9) | coo · chro · cro · cpo · chief-of-staff · ma · board-secretary · fundraising · investor-relations |
• | Marketing (4) | developer-advocate · pr-comms-lead · community-manager · event-marketing-manager |
• | Business Growth (3) | customer-experience-lead · partnership-manager · competitive-intel-analyst |
• | HR (2) | talent-acquisition · people-ops-lead |
• | Product (2) | ux-researcher · learning-designer |
• | Vertical (7) | fintech-advisor · healthtech-advisor · edtech-strategist · ecommerce-strategist · proptech-advisor · climate-tech-advisor · marketplace-advisor |
• + 1 more

📦 Headline Numbers

• | Metric | v4.1.1 | v4.2.0 |
• |---|---|---|
• | Skills | 245 | 266 |
• | Domains | 14 | 17 |
• | `cs-*` agents | 32 | 67 |
• | Total agents (cs-* + personas) | 39 | 74 |
• | Python tools | 653 | 674+ |
• | Compliance frameworks | 18 | 18 |
• + 1 more

📦 Verification

• All 226+ new agent path references verified to resolve to existing files
• All 21+ new Python tools smoke-tested with sample inputs
• All scripts use Python stdlib only (no new pip dependencies)
• All scripts support both human-readable and `--json` output

📦 Compatibility

• Additive release. No breaking changes. No skills removed. No agent removed.

📦 Install

• ```bash
• npx @borghei/claude-skills add fintech-advisor
• npx @borghei/claude-skills add resume-tailor
• npx @borghei/claude-skills add docx-toolkit
• ```
• Or browse the full library: https://borghei.github.io/Claude-Skills
• ---
• Full changelog: https://github.com/borghei/Claude-Skills/blob/main/CHANGELOG.md#420---2026-05-04

📦 One-Click Skill Setup for Beginners

• Every skill page on the [website](https://borghei.github.io/Claude-Skills) now has two copy-paste buttons:
• "Try in Chat" -- Paste a condensed prompt into claude.ai, ChatGPT, or any AI chat for instant expertise. No setup needed.
• "Add to My AI" -- Paste the full skill into any AI chat. The AI walks you through creating a permanent Claude Project or Custom GPT with that skill built in.
• No terminal, no git, no configuration. Just copy, paste, and go.

✨ New Domain: Legal (17 skills, EXPERIMENTAL)

• > All legal skills are experimental and provided for educational/informational purposes only. They do NOT constitute legal advice.
• Contract Analysis: `contract-review`, `nda-triage`, `nda-review`, `tech-contract-negotiation`
• Privacy & Data Protection: `privacy-compliance`, `dpia-assessment`, `data-breach-response`, `privacy-notice-generator`
• Risk & Compliance: `legal-risk-assessment`, `vendor-due-diligence`, `whistleblower-compliance`
• Legal Methodology: `statute-analysis`, `mediation-analysis`, `legal-red-team`
• Legal Operations: `legal-canned-responses`, `legal-meeting-briefing`, `tabular-document-review`

✨ New PM Execution Skills (3)

• `daci-framework` -- DACI decision facilitation and governance (Driver/Approver/Contributor/Informed)
• `eol-communication` -- End-of-life product messaging and sunset communication
• `story-mapping` -- Jeff Patton user story mapping for release planning and MVP scoping

📦 Enhanced Product & PM Skills (6)

• Inspired by [deanpeters/product-manager-prompts](https://github.com/deanpeters/product-manager-prompts):
• job-stories -- Added full JTBD Discovery Canvas (Customer Jobs, Pains, Gains)
• agile-product-owner -- Added 8-rule story splitting decision logic (Humanizing Work methodology)
• ux-researcher-designer -- Added proto-persona canvas + enhanced journey mapping with happy/fail/difficult paths
• create-prd -- Added Problem Framing Canvas and Amazon Working Backwards Press Release as pre-PRD techniques
• product-manager-toolkit -- Added Geoffrey Moore positioning statement and Recommendation Canvas
• product-strategist -- Added PESTEL macro-environment analysis and TAM-SAM-SOM market sizing

✨ New Python Tools (33)

• 33 new CLI tools for legal analysis -- contract review, NDA screening, privacy compliance, breach response, risk scoring, and more.

🐛 CI/CD Fixes

• Fixed security audit false positives (eval/exec in scanner tools, placeholder secrets in scaffolders)
• Added `workflow_dispatch` trigger for manual security audit runs

📦 Stats

• | Metric | v4.0.0 | v4.1.0 |
• |--------|--------|--------|
• | Skills | 225 | 245 |
• | Python Tools | 613 | 653 |
• | Domains | 13 | 14 |
• | Agents | 32 | 32 |
• | Slash Commands | 26 | 26 |

📦 Disclaimer

• ---
• Full Changelog: https://github.com/borghei/Claude-Skills/compare/v4.0.0...v4.1.0

📦 Highlights

• The biggest release yet — 21 new skills, 7 personas, compound sub-skills, Gemini CLI support, full 241-page website, CLI tool, MCP server, and a complete quality audit.

📦 By the Numbers

• | Metric | v3.0.0 | v4.0.0 | Change |
• |--------|--------|--------|--------|
• | Skills | 204 | 225 | +21 |
• | Python Tools | 559 | 613 | +54 |
• | Agents | 17 | 32 | +15 |
• | Slash Commands | 5 | 26 | +21 |
• | Sub-Skills | 0 | 21 | +21 |
• | CI/CD Workflows | 1 | 6 | +5 |
• + 4 more

✨ New: 21 Skills

• Finance (2): saas-metrics-coach, business-investment-advisor
• Marketing (3): video-content-strategist, x-twitter-growth, ab-test-setup

✨ New: Persona System

• 7 cross-domain personas that combine expertise across domains:
• startup-cto — Engineering + Strategy + Product
• growth-marketer — Marketing + Analytics + Product
• solo-founder — All domains, resource-constrained decisions
• content-strategist — Content + SEO + Brand
• devops-engineer — Infrastructure + Security + Dev
• finance-lead — Finance + Strategy + Operations
• product-manager — Product + Engineering + Business

✨ New: Compound Sub-Skills

• 3 skills with nested sub-skill architectures (21 sub-skills total):
• Playwright Pro — 9 sub-skills (init, generate, fix, migrate, review, report, coverage, browserstack, testrail)
• Self-Improving Agent — 5 sub-skills (remember, extract, promote, review, status)
• AgentHub — 7 sub-skills for multi-agent DAG orchestration

✨ New: Infrastructure Tooling

• `cs` CLI — Search, install, list, info, stats, doctor, bundle commands
• MCP Server — 6 tools exposing skills to Claude Code via JSON-RPC
• Quality Scorer — Scores SKILL.md against authoring standard (100-pt scale)
• Integration Test Runner — 5 checks per Python script
• Skill Scaffolder — `create_skill.py` generates complete skill skeleton
• Skill Graph — Relationship analysis with Mermaid output
• Starter Bundles — 8 role kits (SaaS Founder, DevOps, Agency, etc.)
• Sample Data — 18 fixture files across 10 skills

✨ New: Gemini CLI Support

• Full `.gemini/` directory with `skills-index.json`, 20 skill wrappers, `GEMINI.md`, and `gemini-install.sh`.

✨ New: Full Website (241 pages)

• claude.ai-inspired warm minimal design (cream backgrounds, terracotta accent, serif headings)
• Individual pages for all 225 skills with AI platform selector tabs
• 11 domain category pages with searchable skill grids
• Agents catalog, commands catalog
• SEO: JSON-LD structured data, Open Graph, sitemap, llms.txt
• Live at https://borghei.github.io/Claude-Skills/

✨ New: CI/CD Workflows

• 5 new workflows: enforce-pr-target, skill-security-audit, claude-code-review, virustotal-scan, sync-codex-skills

✨ New: Standards

• Orchestration Protocol — 4 multi-agent coordination patterns
• Skill Authoring Standard — 10 formal patterns for skill creation

📦 Quality Audit

• 7 bloated skills cut by 67-78% (massive token savings)
• 15 mid-range skills refined (trigger clauses, agent voice, anti-patterns)
• All 22 skills now have proper "Use when..." triggers and third-person agent voice
• ---
• Full Changelog: https://github.com/borghei/Claude-Skills/blob/main/CHANGELOG.md

📦 Highlights

• The largest update ever — transforms Claude Skills from a skills collection into a production platform.

📦 By the Numbers

• | Metric | Before | After |
• |--------|--------|-------|
• | Python Tools | 230+ | 559 |
• | AI Agents | 6 generic | 25 (6 upgraded + 19 role-based) |
• | README | 1,082 lines | 196 lines |
• | Domains | 13 (split dirs) | 13 (unified) |
• | Website | None | GitHub Pages |

✨ New: Role-Based Agents

• 8 new agents that orchestrate skills for specific executive/lead roles:
• cs-tech-lead — Architecture review, tech debt, code quality gates
• cs-engineering-director — Portfolio health, hiring plans, technology radar
• cs-cfo-advisor — Financial analysis, board prep, revenue forecasting
• cs-ciso-advisor — Security posture, SOC 2/NIST compliance dashboards
• cs-cmo-advisor — Campaign attribution, SEO health, brand dashboard
• cs-privacy-officer — GDPR/CCPA audits, privacy impact assessments
• cs-growth-lead — Growth loops, churn prediction, pricing optimization
• + 1 more

📦 Upgraded: Existing Agents Now Use Skills

• All 6 `.claude/agents/` upgraded with Skill-Powered Analysis — they now run Python tools for quantitative, measurable output instead of LLM-only opinions.

📦 Repository Restructured

• `engineering-team/` + `engineering/` merged into unified `engineering/` (61 skills)
• `marketing-skill/` renamed to `marketing/`
• All 100+ cross-references updated
• `docs/` directory with SKILLS.md, USAGE.md, AGENTS.md, WORKFLOWS.md

📦 README Redesigned

• 1,082 → 196 lines. Concise stats, 2 install methods, domain summary table. Detailed content moved to `docs/`.

📦 GitHub Pages Website

• Minimal dark-theme site at borghei.github.io/Claude-Skills with terminal animations, domain grid, agent showcase.

📦 All Config Files Updated

• CLAUDE.md, AGENTS.md, .cursorrules, .windsurfrules, .clinerules, .goosehints, copilot-instructions.md — all updated from "230+ tools" to accurate "559 tools".
• ---
• Full Changelog: https://github.com/borghei/Claude-Skills/compare/v2.1.0...v3.0.0