Claude Skills by OutlineDriven

Use when exploration needs heterogeneous noticings captured before structure. Useful noticings are preserved without premature synthesis. Not for beat-by-beat assembly from selected sources — use writing-beats; not for paragraph-by-paragraph shaping — use writing-shape.

Use when shaping a source document paragraph by paragraph without modifying it. Produces an approved, grounded document with named gaps for rejected paragraphs. Not for selected-beat assembly — use writing-beats; not for fragment capture — use writing-fragments.

Use when the user knows what they mean but cannot express it completely or clearly. Turns a vague intended thought into a faithful, audience-ready statement, preserving scope and identity, surfacing unsupported choices, and inventing no goals or facts. Not for discovery, ideation, or style-only editing — use unslop for style.

Use when the user asks for branded or style-governed output. Produces a deliverable that follows a fetched brand authority and states the material constraints that shaped it. Not for remote, credential, publish, deploy, or irreversible changes.

Use when a user asks to design or review a bottom-of-article call-to-action. Maps article context, audience, and funnel stage to a CTA archetype with copy, form, mechanism, A/B test plan, and accessibility check. For general copywriting use copywriting; for hooks or ledes use copywriting-hooks.

Use when a user asks for a hook, lede, or accroche for long-form content. Not for CTA design, use copywriting-cta; not for general copywriting, use copywriting.

Use when asked to write or fix product/marketing copy, landing pages, CTAs, UI strings, brand voice, or remove AI writing tells. Not for end-of-article CTA design — use copywriting-cta; not for hooks — use copywriting-hooks.

Use when the user supplies French text that reads like AI output and asks to naturalize it. One pass removes AI tells while preserving register; returns the rewritten French text. Not for English STE rewriting — use humanizer-en-asd-ste100.

Use when asked to rewrite technical English for STE compliance, stripping ambiguity and AI-style patterns so non-native readers and downstream agents parse every sentence. Not for French de-AI-ification — use humaniseur-fr.

Use when a user provides a founder story or result and asks for a LinkedIn post with a chosen hook and humanized body. No file or credential mutations. Don''t use for tasks that require source or remote-system changes.

Use when a user asks to write or announce a press release for any occasion or region. Delivers a regionally-compliant inverted-pyramid release, angle justification note, journalist pitch email, and social teasers. Adapts to release type, target region, and media format.

Use when asked to ghostwrite Substack newsletters and web posts from structured intake. Delivers formatted drafts with subject lines, SEO metadata, Notes teasers, and optional social posts. Don''t use for tasks that require source or remote-system changes.

Use when a user asks to write a technical article or blog post incorporating external references. Fetches and validates reference URLs, applies idea-quality gates, drafts an evidence-based body with explicit citations and a single objective, then runs a humanization pass. Not for source-code changes or landing-page copy.

Use when prose is drafted or edited, reviewed for AI tells, or the user asks to remove AI patterns, humanize, or add voice. Runs 20 pattern-replacement checks across prose files; dedash mode purges em-dashes by grammatical role; detool mode neutralizes incidental tool names in portable artifacts. For code debris use deslop.

Generate radically-different module or API contract designs in parallel, then compare on depth, simplicity, and ease-of-correct-use. Trigger when the user is shaping a new module surface, exploring contract options, comparing module shapes, or applying "design it twice" to a first-pass sketch.

Grill against the existing domain model. Stress-test a plan's terminology against `CONTEXT.md` and ADRs; update both inline as decisions crystallise. Trigger when user proposes a feature/refactor that touches business concepts and the project has documented domain language to honor — or when domain language is missing and needs capture.

Hybrid interview that probes AI-engineering mastery by tip-vocabulary depth — entity referencing, loop closure, observability, harness improvement — not by token usage or LOC. Start collaborative (two-way tip exchange), escalate to adversarial probing when depth is lacking. Trigger when the user says "interview me on AI", "stress-test my Claude usage", "evaluate this candidate's AI engineering", or otherwise asks for an AI-collab skill assessment. User-only — never auto-invoke.

Adversarial relentless interview against any plan or design until shared understanding is reached. Walk the decision tree, resolve dependencies one answer at a time, recommend a default per question. Trigger when the user says "grill me", "stress-test this", "interview me about this design", or otherwise asks for hostile-but-fair scrutiny of a proposal. General-purpose — no domain anchor required.

Conversational QA mode — user reports bugs in plain language, agent clarifies minimally, files GitHub issues that survive refactors. Trigger on "QA", "QA session", or ad-hoc bug reporting without a fixed deliverable shape. Distinct from branch-scoped and PR-scoped review.

Plan a refactor as a sequence of tiny, working commits via adversarial interview. Default output is a markdown plan at `<project-root>/docs/refactor-plans/<name>.md`; pass `--emit-issue` to also file a GitHub issue. Trigger on structural refactors (rename, extract, move, split, dedupe) — NOT new features.

Decompose a plan, PRD, or spec into independently-grabbable vertical-slice issues (markdown file by default, GitHub issues via flag). Trigger when the user wants implementation tickets, work decomposition, or to convert an implementation plan into parallelizable work. Takes a plan file and emits atomic vertical slices.

Synthesize current conversation context and codebase understanding into a PRD artifact (markdown file by default, GitHub issue via flag). Trigger when the user asks for a PRD, requirements doc, feature spec, or wants to crystallize an in-flight discussion into a durable artifact before planning. PRD precedes implementation planning.

Extract a domain glossary from the current dialogue; flag ambiguities, propose canonical terms, persist to `UBIQUITOUS_LANGUAGE.md`. Trigger when the user is hardening domain terminology, building a glossary, or fresh domain concepts surface in conversation without documented language.

Author a single new skill — produce a SKILL.md plus optional bundled references and scripts following Anthropic's progressive-disclosure conventions. Trigger when the user asks to "write a skill", "create a skill", "draft a SKILL.md", or "add a skill" for a specific capability. Distinct from repo onboarding workflows that write AGENTS.md and project conventions.

Install a Claude-Code PreToolUse hook that blocks destructive git commands (push variants including force-push, hard reset, force clean, branch -D, checkout/restore overwrites) before Bash runs them. Use when the user wants git safety rails, force-push prevention, or repository-wipe protection.