A skill is a portable file you drop into Claude Code, Cursor, Windsurf, Copilot, or any AI coding assistant — and immediately gain a repeatable capability. Every skill in the Forge includes two things you won't find in a generic tutorial: why it works (the rationale — what makes this reliable and when to reach for it) and how it works (concrete steps and prompt patterns you can adapt to your own project).
Browse by category, download in the format your tool expects, and check the community compatibility notes before you commit. Built something worth sharing? Contribute it to the Forge.
Literature Map Builder
Cluster a set of papers into a topic map with methodology and findings per cluster, then surface the whitespace where nobody is working yet.
Competitor Feature Matrix
Turn a list of competitor URLs into a normalized feature and pricing matrix you can paste into a deck — without the 'plan names mean different things at each company' problem.
Statistical Claim Checker
Validate every quantitative claim in an article against the source data it cites, flagging numbers that are unsupported, outdated, or selectively quoted.
Draft Tightener
Cut 20 percent of a draft while preserving the argument, using sentence-level surgery instead of paragraph deletion.
Tone Translator
Rewrite the same content across four target tones — formal, casual, authoritative, friendly — while preserving every fact and callout, for multi-channel posting from a single source.
Fact-and-Source Annotator
Annotate every factual claim in a draft with a source URL and confidence level, blocking publication until each claim is cited or marked opinion.
Migration Plan Writer
Draft an incremental database migration plan with rollback gates from a before/after schema diff — no single-shot migrations that can't be reversed.
Test Gap Finder
Combine coverage data with mutation-testing survivors to produce a ranked list of untested behaviors — the ones most likely to ship bugs.
API Changelog Generator
Diff two OpenAPI specs into a human-readable changelog with breaking-change flags, ready for release notes.
Receipt OCR Normalizer
Extract vendor, line items, tax, and total from a photo of a receipt into a single clean JSON row — ready for expense systems.
HTML-to-Dataset Extractor
Turn a repetitive HTML listing page (directory, catalog, search result) into a flat CSV with a self-verifying schema — no per-site selectors to maintain.
Email Thread Reducer
Collapse a long email thread into a deduped timeline of decisions, open questions, and action items — for when you're added to a 40-message chain.
Standup Note Synthesizer
Merge individual standup bullets from multiple people into a single team digest with blockers surfaced to the top.
Runbook Skeleton
Produce a first-draft runbook from a postmortem — detection, diagnosis, mitigation, rollback — so the next incident has a template to follow.
OKR Draft Critiquer
Score draft OKRs against SMART criteria and the outcome-not-output rule, with suggested rewrites for each failing key result.
Brand Voice Extractor
Sample existing marketing copy to produce a voice guide — do/don't, vocabulary, rhythm rules — that new drafts can be checked against.
Accessibility Contrast Audit
Walk a page's color tokens and flag every pair that fails WCAG AA, with a suggested minimal adjustment to pass.
Ad Creative Variant Generator
Generate headline and body variants respecting platform character limits and style rules, then rank them on a clarity and hook rubric.
Vector Index Health Check
Probe a vector index for near-duplicate embeddings, orphaned chunks, and stale source docs — the three silent killers of RAG quality.
Query Reformulation Expander
Expand a user query into 3-5 rewrites plus a HyDE-style synthetic passage, then aggregate retrieval results for measurably better recall.
Citation Neighborhood Walker
Given a seed paper, build a 2-hop citation graph and rank neighbors by relevance to a given thesis — a literature survey that's actually grounded.
Long-Running Task Checkpointer
Wrap an agent loop so every step snapshots state to disk, letting a crashed agent resume from the last good state instead of restarting from scratch.
Tool-Call Budget Guard
Cap an agent's tool calls with per-tool budgets and graceful degradation when exhausted — so runaway agents don't blow through API quotas.
Self-Correcting Schema Agent
An agent that retries JSON generation with schema violation feedback until the output validates — or a budget is exhausted.
Podcast Chapter Generator
From an episode transcript, produce timestamped chapter markers with topic labels ready for Apple Podcasts and YouTube chapters.
Speaker Diarization Cleanup
Correct auto-diarized transcripts by merging short speaker swaps and relabeling anonymous speakers from known-voice samples.
Audio Silence Trimmer
Find and remove long silences, ums, and ahs in raw audio with configurable thresholds — for podcast and voiceover cleanup.
B-Roll Gap Finder
Scan a video edit for long talking-head stretches without visual variety and suggest b-roll clips by topic.
Thumbnail A/B Generator
Generate 5 thumbnail variants for a single video using a brand template and a topic prompt — ready for YouTube multi-variant testing.
Product-Shot Background Swap
Replace a product photo's background using a reference palette while preserving the product's reflections and shadows.
Landing Page Copy Audit
Score landing page copy on clarity, CTA strength, and conversion fundamentals — deliver a prioritized rewrite plan in one pass.
PDF Structure Extraction
Parse a PDF into a structured outline (sections, tables, footnotes) without losing layout semantics.
SQL Query Writer
Turn natural-language questions into validated, safe SQL against a known schema — with dry-run support.
Academic Paper Review
Structured critical review of a paper (method, claims, threats to validity) in the voice of a third reviewer.
Codebase Map
Compress an entire repo into a single LLM-digestible context bundle with an import graph and hot-file list.
Meeting Summary Template
Turn a raw transcript into a decision-focused recap: outcomes, owners, deadlines, open threads.
Prompt A/B Evaluator
Run two prompt variants against a fixed test set, score with a rubric LLM, and tell you which wins (and why).
JSON Schema Builder
Generate a valid JSON Schema from example data, with nullability and enum detection baked in.
Voice Clone Safety Check
Run a set of consent + provenance checks before a voice cloning job is accepted.
Browser Testing Agent Loop
Agentic loop that exercises a web app like a new user, files bug reports with screenshots + reproduction steps.
Diffusion Prompt Library
A curated, tagged prompt library for diffusion models with negative-prompt presets and CFG/sampler defaults.
Quote Attribution Verifier
Check every quoted sentence in a draft against the original source to catch misattribution and paraphrasing.
Editorial Style Matcher
Rewrite a draft to match a target publication's house style (sentence length, voice, diction) without changing meaning.