Markdown

team-builder is an interactive agent picker for composing and dispatching parallel teams from markdown persona files. The team-builder skill helps you browse available agents, group specialists by domain, and build ad-hoc teams for Workflow Automation. Best for repos with flat or subdirectory agent libraries and clear persona structure.

nanoclaw-repl is a session-aware REPL skill for operating and extending NanoClaw v2. It supports persistent markdown-backed sessions, branching, search, compaction, model switching, and export for Workflow Automation. Use this nanoclaw-repl guide to keep local tasks deterministic and easy to resume.

hookify-rules helps you create Hookify rule files with YAML frontmatter for .claude/hookify.{rule-name}.local.md. Use it to define the right event, pattern, and action for warnings or blocks, and to turn a rough policy into a reliable hookify-rules guide for Skill Authoring.

The article-writing skill helps draft long-form content with strong structure, voice consistency, and evidence. Use it for articles, guides, tutorials, newsletters, and article-writing for Copywriting workflows where polished, publishable prose matters.

architecture-decision-records helps capture architectural decisions during Claude Code sessions as structured ADRs. It detects decision moments, records context, alternatives, and rationale, and keeps an ADR log for future maintainers. Useful for Technical Writing and engineering teams that need durable decision history.

technical-writer is a lightweight documentation skill for creating clearer README files, API docs, setup guides, tutorials, onboarding docs, and release notes. It centers Technical Writing on user goals, quick starts, examples, and troubleshooting. The skill is delivered as a single SKILL.md file with no extra scripts or templates.

meeting-notes is a lightweight skill for turning raw transcripts or notes into structured meeting minutes with agenda, discussion points, decisions, action items, next steps, and a parking lot.

document-release is a post-ship documentation update skill that reads project docs, cross-references the shipped diff, and updates README, ARCHITECTURE, CONTRIBUTING, CLAUDE.md, CHANGELOG, and VERSION so docs match what actually shipped. Use the document-release skill for technical writing when code is already merged and you need a reliable document-release guide.

grill-with-docs is a planning-and-documentation skill that pressure-tests your plan against the repo’s existing domain model, sharpens terminology, and updates CONTEXT.md and ADRs as decisions crystallize. Use it for Technical Writing, product-minded engineering, and any workflow where repo-grounded language matters more than a prompt-only brainstorm.

obsidian-vault helps search, create, and connect Obsidian notes using Title Case filenames, [[wikilinks]], and index notes. It fits obsidian-vault for Knowledge Bases workflows where linking and note structure matter more than folders.

writing-shape is a conversational drafting skill for turning markdown raw material into a publishable article. It helps with opening selection, paragraph-by-paragraph development, and structure choices for Technical Writing, interview notes, transcript cleanup, and rough drafts. Use the writing-shape guide when you need a guided editorial process rather than a one-shot prompt.

writing-beats is a drafting workflow skill for turning raw markdown notes into an article one beat at a time. It helps writers, editors, and agents shape scattered notes into a readable narrative instead of a linear argument. Best for exploratory explainers, founder stories, case studies, and writing-beats for Blog Writing.

ubiquitous-language is a DDD-style skill that extracts a shared glossary from conversations, flags ambiguous terms and synonyms, and writes UBIQUITOUS_LANGUAGE.md. Use it to define domain terms, align teams, and improve ubiquitous-language for Technical Writing.

timeline-report turns claude-mem timeline data into a readable "Journey Into [Project]" report. Use it to analyze development history, major phases, pivots, and project trajectory. Best when claude-mem observations already exist and the worker is running on localhost:37777.

adr-skill helps teams create and maintain Architecture Decision Records that agents can execute. It supports drafting, bootstrapping ADR folders, choosing templates, updating status, and validating decisions with checklists, scripts, and examples.

md-review converts markdown PR writeups with unified diff fences and severity callouts into a single-file, two-column HTML code review. It uses parser, annotation, and renderer scripts, requires a named reviewer, supports BLOCKER/MAJOR/MINOR/NIT conventions, and preserves accessible severity cues.

write-a-skill helps agents author reusable skills with clear triggers, concise SKILL.md files, progressive disclosure, references, and Python validation scripts for review.

runbook-generator creates operational runbook drafts for services using a Python CLI and templates for deployment, health checks, rollback, incident response, maintenance, and validation. Useful for SRE, DevOps, and Technical Writing teams standardizing on-call procedures.

changelog-generator turns Conventional Commit history into auditable Keep a Changelog release notes. Use this changelog-generator skill to lint commits, infer semver bumps, generate CHANGELOG.md entries, and support CI, monorepo, hotfix, and Technical Writing workflows.

collab-proof helps Claude Code users turn AI-assisted coding sessions into collaboration evidence, separating developer decisions, Claude contributions, rejected alternatives, and proof artifacts for retrospectives, portfolios, hiring, and Knowledge Capture.

review audits Claude Code auto-memory in MEMORY.md to find promotion candidates, stale references, duplicates, consolidation opportunities, and health checks for Context Engineering workflows.

promote graduates proven Claude auto-memory patterns from MEMORY.md into CLAUDE.md or .claude/rules/ so useful behaviors become durable project rules. Use it with /si:promote to confirm evidence, choose the right target, and write scoped instructions for self-improving Context Engineering workflows.

extract is a Skill Authoring utility that turns recurring fixes, workflows, or debugging patterns into a reusable SKILL.md with clear scope, triggers, workflow, examples, and optional references.

report is a lightweight Playwright test reporting skill that checks existing artifacts, runs tests when needed, parses results, and generates Markdown, Slack, TestRail, or CI-ready summaries.