GitHub collection

jamditis/claude-skills-journalism

Imported from GitHub — is this yours?

59 skills imported from this repository.

View on GitHub
399 64 MIT
Claude Skill dev-toolkit

accessibility-compliance

Web accessibility patterns for news and academic sites. Use for WCAG audits, alt text, accessible data viz, and assistive tech.

LLM Mart

Claude Skill dev-toolkit

claude-md-updater

Scans the session for lessons and workflows, then proposes scoped CLAUDE.md edits. Use for save this lesson or add to context.

LLM Mart

Claude Skill dev-toolkit

context-engineering-fundamentals

Manages attention and evidence in long agent sessions. Use for lost instructions, dropped evidence, or large multi-agent contexts.

LLM Mart

Claude Skill dev-toolkit

director

Directs the current request through configured lower-tier agents. Use only for explicit /director or /dev-toolkit:director invocation.

LLM Mart

Claude Skill dev-toolkit

mobile-debugging

Remote JavaScript console and debugging on mobile. Use for phone/tablet console errors, responsive testing, Eruda, and vConsole.

LLM Mart

Claude Skill dev-toolkit

one-way-door

Flags irreversible decisions before commit. Use for data models, infra, auth boundaries, API contracts, event schemas, CI/CD.

LLM Mart

Claude Skill dev-toolkit

python-pipeline

Python data pipelines with modular architecture. Use for content workflows, batch jobs, or Google Sheets/Drive integration.

LLM Mart

Claude Skill dev-toolkit

test-first-bugs

Enforces a test-driven bug-fixing workflow. Use when a user reports a bug, failing code, an error, or asks to fix something.

LLM Mart

Claude Skill dev-toolkit

vibe-coding

AI-assisted coding with Claude Code, Cursor, Copilot, Codex, Aider, or Windsurf. Use to build or debug generated code.

LLM Mart

Claude Skill dev-toolkit

web-scraping

Authorized web scraping with fallback cascades and access-failure handling. Use for social media, yt-dlp, CAPTCHA or 403 blocks.

LLM Mart

Claude Skill dev-toolkit

web-ui-best-practices

Signs of taste in web UI. Use when building or reviewing web interfaces, dashboards, SaaS apps, or internal tools.

LLM Mart

Claude Skill dev-toolkit

zero-build-frontend

Zero-build frontend development for static apps, browser extensions, maps, and lightweight data-backed interfaces. Use when deployment must not require a build step.

LLM Mart

Claude Skill journalism-core

ai-writing-detox

Eliminates AI-generated writing patterns that erode reader trust. Use when writing or editing articles, docs, or press releases.

LLM Mart

Claude Skill journalism-core

brazil-records-requests

Public records requests under Brazil's Access to Information Law (LAI). Use for Fala.BR filings, e-SIC, and CGU/CMRI appeals.

LLM Mart

Claude Skill journalism-core

crisis-communications

Crisis communication and rapid-response workflows. Use when covering breaking news or coordinating fast fact-checking on deadline.

LLM Mart

Claude Skill journalism-core

data-journalism

Acquire, clean, analyze, verify, visualize, and explain data for journalism. Use for reproducible data reporting, statistical analysis, maps, or public methodology.

LLM Mart

Claude Skill journalism-core

editorial-workflow

Manages newsroom editorial workflows. Use when tracking assignments, managing deadlines, or coordinating editorial calendars.

LLM Mart

Claude Skill journalism-core

fact-check-workflow

Structured fact-checking workflow. Use when verifying claims for publication, rating claims, or setting pre-publication checks.

LLM Mart

Claude Skill journalism-core

foia-requests

FOIA and public records workflows. Use when drafting requests, tracking submissions, checking exemptions, or appealing denials.

LLM Mart

Claude Skill journalism-core

interview-prep

Interview preparation and recording-consent law. Use for research, question frameworks, one-party or all-party consent rules.

LLM Mart

Claude Skill journalism-core

interview-transcription

Transcription, recording management, and quote extraction. Use when processing audio/video or generating timestamped transcripts.

LLM Mart

Claude Skill journalism-core

newsletter-publishing

Email newsletter workflows. Use when creating newsletters, building subscriber lists, designing templates, or tracking engagement.

LLM Mart

Claude Skill journalism-core

newsroom-style

Enforces AP Style and newsroom conventions. Use when writing news, editing drafts, creating headlines, or tightening copy.

LLM Mart

Claude Skill journalism-core

photo-metadata

Embeds photo IPTC/EXIF/XMP metadata, caption, credit, alt text, license, AI-source label, GPS stripping, and C2PA credentials.

LLM Mart

Claude Skill journalism-core

social-media-intelligence

Social media monitoring, narrative tracking, and OSINT. Use when tracking viral spread, coordinated campaigns, or account vetting.

LLM Mart

Claude Skill journalism-core

source-verification

Verify sources, claims, images, video, documents, interviews, and synthetic media with SIFT and a durable evidence trail. Use before relying on uncertain material.

LLM Mart

Claude Skill journalism-core

story-pitch

Crafts story pitches for different outlets. Use when pitching editors, writing query letters, or shaping feature or op-ed angles.

LLM Mart

Claude Skill okf-wiki

okf-wiki

Builds an Open Knowledge Format (OKF) knowledge base from existing docs, notes, or a repo. Use to scaffold an OKF wiki.

LLM Mart

Claude Skill pdf-design

pdf-design

Designs PDF reports and proposals from HTML with previews and branding. Use to create, export, or securely upload a PDF.

LLM Mart

Claude Skill pdf-playground

document-design

Creates print-ready HTML that exports to PDF. Use to make a proposal, report, one-pager, newsletter, slides, or flyer.

LLM Mart

Claude Skill project-templates-toolkit

project-memory

Generates CLAUDE.md project memory files that transfer institutional knowledge. Use when setting up projects or onboarding.

LLM Mart

Claude Skill project-templates-toolkit

project-retrospective

Generates LESSONS.md files capturing institutional knowledge and failures. Use when closing out projects or investigations.

LLM Mart

Claude Skill project-templates-toolkit

template-selector

Selects the correct CLAUDE.md or LESSONS.md template via decision trees. Use when starting a project or unsure which fits.

LLM Mart

Claude Skill research-toolkit

academic-writing

Scholarly writing and research compliance. Use for CRediT, preregistration, Plan S, Nelson Memo, preprints, ORCID, LLM disclosure.

LLM Mart

Claude Skill research-toolkit

content-access

Legal methods for paywalled and geo-blocked content. Use for paywalls, academic papers, or open access via Unpaywall.

LLM Mart

Claude Skill research-toolkit

digital-archive

Digital archiving with AI enrichment and entity extraction. Use when building content archives or knowledge graphs.

LLM Mart

Claude Skill research-toolkit

free-apis-catalog

Curated free APIs with verified free-tier limits. Use when suggesting APIs or finding free weather, news, finance, or sports data.

LLM Mart

Claude Skill research-toolkit

web-archiving

Web archiving and retrieval via Wayback Machine and Archive.today. Use to preserve content, reach dead pages, or save evidence.

LLM Mart

Claude Skill security-toolkit

api-hardening

API hardening for Express, FastAPI, and serverless. Use for rate limiting, CORS, input validation, API keys, or OWASP API Top 10.

LLM Mart

Claude Skill security-toolkit

secure-auth

Secure authentication patterns (OWASP, NIST). Use for login, registration, password reset, sessions, JWT, OAuth, MFA, passkeys.

LLM Mart

Claude Skill security-toolkit

security-checklist

Pre-deployment security audit organized by OWASP Top 10. Use when reviewing code before shipping or going to production.

LLM Mart

Claude Skill security-toolkit

supply-chain-hardening

Install-time cooldowns for npm/bun plus a sandboxed pre-install scan for bypasses. Use for supply-chain attacks or npm security.

LLM Mart

Claude Skill superjawn

brainstorming

Explores intent and design before implementation. MUST use before creating or modifying any feature, component, or behavior.

LLM Mart

Claude Skill superjawn

dispatching-parallel-agents

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

LLM Mart

Claude Skill superjawn

executing-plans

Use when you have a written implementation plan to execute in a separate session with review checkpoints

LLM Mart

Claude Skill superjawn

finishing-a-development-branch

Presents options for merge, PR, or cleanup. Use when work is complete, tests pass, and you must decide how to integrate.

LLM Mart

Claude Skill superjawn

receiving-code-review

Verifies review feedback with technical rigor, not blind agreement. Use when receiving review before implementing suggestions.

LLM Mart

Claude Skill superjawn

requesting-code-review

Use when completing tasks, implementing major features, or before merging to verify work meets requirements

LLM Mart

Claude Skill superjawn

subagent-driven-development

Use when executing implementation plans with independent tasks in the current session

LLM Mart

Claude Skill superjawn

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

LLM Mart

Claude Skill superjawn

test-driven-development

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

LLM Mart

Claude Skill superjawn

using-git-worktrees

Creates isolated git worktrees with smart directory selection and safety checks. Use when starting isolated feature work.

LLM Mart

Claude Skill superjawn

verification-before-completion

Runs verification commands and confirms output before success claims. Use before claiming work done or committing or PRs.

LLM Mart

Claude Skill superjawn

writing-plans

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

LLM Mart

Claude Skill superjawn

writing-skills

Use when creating new skills, editing existing skills, or verifying skills work before deployment

LLM Mart

Claude Skill video-toolkit

video-dashboard

Aggregates transcript and frame data into an interactive web dashboard. Use for content, topic, or sentiment analysis.

LLM Mart

Claude Skill video-toolkit

video-download

Collects videos from public social accounts. Use to download or scrape from Twitter, TikTok, YouTube, Instagram, or Facebook.

LLM Mart

Claude Skill video-toolkit

video-transcribe

Batch Whisper transcription of video or audio (WAV, podcasts) with a re-runnable provenance record. Use to transcribe recordings.

LLM Mart

Claude Skill visual-explainer

visual-explainer

HTML explainers, diagrams, architecture, timelines, source maps, slide decks, comparison tables, recaps, plan and diff reviews.

LLM Mart

Agents (1)

Claude Agent

autocontext-curator

Validates and structures lesson candidates before persisting to lessons.json

Commands (22)

  • /diff-review — Generate a visual HTML diff review, before/after architecture comparison with code review analysis source
  • /event — Create event materials (flyers, posters, signage) with your organization's branding source
  • /evolve — Evolve skill files by integrating validated lessons from real usage source
  • /fact-check — Verify the factual accuracy of a document against the actual codebase, correct inaccuracies in place source
  • /generate-slides — Generate a stunning magazine-quality slide deck as a self-contained HTML page source
  • /generate-visual-plan — Generate a visual HTML implementation plan, detailed feature specification with state machines, code snippets, and edge cases source
  • /generate-web-diagram — Generate a beautiful standalone HTML diagram and open it in the browser source
  • /hotpatch — Sandboxed pre-install scan plus cooldown bypass for urgent npm/bun installs. Use when a package must ship despite the cooldown. source
  • /init — Initialize .autocontext/ in the current project for knowledge persistence source
  • /newsletter — Create an HTML email newsletter with your organization's branding source
  • /onepager — Create a single-page fact sheet or program overview source
  • /plan-review — Generate a visual HTML plan review, current codebase state vs. proposed implementation plan source
  • /preview — Launch interactive preview for document editing source
  • /project-recap — Generate a visual HTML project recap, rebuild mental model of a project's current state, recent decisions, and cognitive debt hotspots source
  • /proposal — Create a multi-page funding proposal with your organization's branding source
  • /report — Create a program report or annual report with your organization's branding source
  • /review — Interactively review and curate accumulated project lessons source
  • /setup — First-run configuration for the autocontext plugin source
  • /share-page — Deploy a generated visual-explainer HTML page and return a live Vercel URL source
  • /slides — Create HTML presentation slides with your organization's branding source
  • /status — Show knowledge stats for the current project source
  • /update — Check for updates and install the latest version source