Turn a brief-shortform or brief-app-preview into a multi-runtime export bundle — manifest, per-shot prompts, production-lane scaffolds, and a post (assemble · grade · subtitle)…
Use when the user asks to "package our proof points", "build reusable stat cards and case snippets", or "put proof where each pillar makes its claim"; turns claims-ledger-approved…
Writes rigorous mathematical proofs for ML/AI theory. Use when asked to prove a theorem, lemma, proposition, or corollary, fill in missing proof steps, formalize a proof — from…
Run deterministic render checks, local creative gates, adversarial critique, and independent evidence-backed acceptance against a built infographic before shipment.
Backfill this project's recall memory store from past Claude Code session transcripts, mining prior conversations for durable learnings and deferred work.
Run the feature-reflector subagent (Layer 4b — top-down product-owner reflection) over one composed feature flow.
Syncs latest release content to NotebookLM and HQ Knowledge Base after version tagging. Reads CHANGELOG, CLAUDE.md, and hook README, updates notebook sources, and ingests release…
Identify and remove phrasing, structure, and word choices that signal AI authorship. Runs iterative passes through fresh voice-agent instances with the orchestrator acting as…
Assemble a submission-ready replication package to the AEA Data and Code Availability Standard (DCAS) / openICPSR / Social Science Reproduction Platform expectations — standard…
Transform content across X formats. Convert posts to threads, threads to posts, blog posts to threads, announcements to multiple angles, etc.
Research technical solutions, analyze architectures, gather requirements thoroughly. Use for technology evaluation, best practices research, solution design, scalability/ — from…
Research technical solutions, analyze architectures, gather requirements thoroughly. Use for technology evaluation, best practices research, solution design, scalability/ — from…
Reference for the OpenAI Responses API (/v1/responses), OpenResponses open standard, and Codex CLI. Covers the request/response schema, previous_response_id, Conversations API,…
Run a section-focused resume review panel. Routes to a curated subset of the 12 reviewer sub-agents based on the section argument (work-experience, skills, projects, formatting,…
The watchdog-watchdog — one read-only pass that proves the resume watchdog (the n¹ layer that revives dead autonomous Claude sessions) is itself ALIVE, TICKING, and reviving…
Processes meeting transcriptions and calendar data to generate a structured summary with key points, agreements, attendance table, and Word document deliverable.
Review a draft article for academic/technical journal submission. Gives structured feedback on clarity, contribution, structure, novelty, and journal fit.
기술 블로그 포스팅의 구조와 콘텐츠를 검토합니다. 글 작성 완료 후 발행 전에 사용하세요. Use when user mentions "블로그 검토", "포스팅 검토", "글 구조", "구조 리뷰", or asks to "review blog", "check structure", "검토해줘", "구조 확인".
Analyze a session transcript with AI and generate structured insights (prompt quality, strategy critique, key decisions, takeaways) for the rewind viewer. — from bang9/ai-tools
Analyze a session transcript with AI and generate structured insights (prompt quality, strategy critique, key decisions, takeaways) for the rewind viewer.
Use when the user wants a Traditional Chinese (Taiwan) language review of Markdown or plain-text files — flagging genuinely comprehension-breaking grammar faults (missing subject,…
Find and stress-test rhymes with Pat Pattison's discipline — identity check, stability-tier walk, vowel triangle, song-world vocabulary, mosaic/multi-word rhyme, cliche scan.
Execute XML tasks from todo.md wave by wave (Phase 3 only — no understand, no plan, no PR). Use when resuming a story that already has a task plan.
Take an in-flight retrospective checkpoint mid-session: spawn a subagent to analyze the session transcript so far (reusing retro's parser), classify each finding by category and…
Maintains screens (dynpros) in a SAP system via SE51 using SAP GUI Scripting. Two modes: (a) FLOW LOGIC — create new screens or update an existing screen's flow logic (PROCESS…
Unified vault-mapping pipeline. Extracts structured metadata from every typed file in your vault (books, meetings, people, articles, goals, etc.), optionally runs knowledge-graph…
Stage 3 of the content-seeding pipeline. Consumes a user-approved import plan and scaffolds project triads (PRD.md / Context.md / Updates.md) under each project candidate's…
Generate AI videos using ByteDance Seedance. Use when the user wants to: (1) generate videos from text prompts, (2) generate videos from images (first frame, first+last frame,…
Generate AI videos using BytePlus Seedance API (International). Use when the user wants to: (1) generate videos from text prompts, (2) generate videos from images (first frame,…
Analyze session transcripts to extract data, diagnose anti-patterns, and generate GitHub issues from findings.
Backfill structured session summaries from Claude Code .jsonl transcripts into the vault's per-project Sessions folder.
Surface prior investigations from past Claude Code sessions on the current topic. Greps ~/.claude/projects/*/memory/ and recent transcripts for keyword matches.
Render a Salesforce planning document (plan, requirements, brainstorm) in Every's Proof editor for human-in-the-loop review and comment-driven iteration.
Dump a Claude Code session transcript as navigable Markdown. Use when user wants to review, analyze, or export a session transcript.
Transform text into Shanghainese （上海話 / 滬語） — the Wu Chinese variety spoken in Shanghai, belonging to the Taihu subgroup （太湖片） of Wu （吳語）.
Package a verified infographic demo for the public gallery and, after explicit user opt-in, prepare a community pull request without merging it.
Translation audit — single page (with argument) or full project i18n consistency check (no argument). Verifies completeness, quality, and consistency of all translations.
Rédiger du contenu original long format — articles de blog, guides informationnels, éditoriaux — adapté à la marque, l'audience et la voix de l'auteur du projet
Optimize short promotional video scripts and product tagging strategies for Shopee Video.
Use when the user asks to "script this short video", "write a TikTok / Reels / Shorts script", "给这条抖音或视频号视频写脚本", or "fix the hook — viewers drop off in the first seconds";…
Create polished self-contained HTML showcase pages and section screenshots for demos, launch posts, social media, article illustrations, and visual presentations.
Editorial planning for the edition. Reads sheet-primary canon (Oakland_Sports_Feed, Riley_Digest, Initiative_Tracker, Simulation_Ledger) + canon archive + NEWSROOM_MEMORY +…
Extract all entity types (interventions, pathways, biomarkers, conflicts) from Google Drive transcript analyses using a three-stage LLM pipeline with Claude Opus 4.5 for…
Build and maintain an entity-centric cell signaling knowledge base from lecture transcripts. Uses a three-stage LLM pipeline (Opus 4.5 extraction, Opus 4.5 semantic dedup, Haiku…
Transform text into Singlish (Colloquial Singaporean English) — an English-based creole shaped by Hokkien, Malay, Cantonese, Mandarin, and Tamil.
Use to find agent skill installs, duplicate skills, cross-dependencies, invocations, and cross-references across the local machine.
Multi-step workflow to create presentation slides from content (academic papers, articles, notes). Reads the source (splitting PDFs, extracting text from Word/RTF, or reading…
Generate slides.md from a script/voiceover file and source document. Maps narrative sections to typed slide outlines with real data, chart specs, and animation directives.
One repeatable RSI pass over CODE SLOP — the slop the compiler can't see. Runs the code-slop scorecard (tools/code_slop_scorecard.py), reads the slop-debt work-list, retires debt…
Use when the user asks to "build our social posting calendar", "set weekly slots and queue depth per channel", or "plan the evergreen recycle rotation"; produces the always-on…
Use when the user asks to "turn this idea into posts for every platform", "write the X thread / LinkedIn post / 小红书 note", or "spec the carousel slides"; turns one idea into N…
Use when the user asks to "audit our social presence", "is this batch safe to publish", or to run the pre-publish go/no-go before queued posts ship; computes the goal-weighted…
Build and balance song structure with Pat Pattison's methods — section identification (verse/chorus/bridge/refrain), forms (AABA, verse/chorus, verse/refrain), the candy-bar…
Use when: converting books, articles, documentation, notes, transcripts, or other source material into reusable agent skills; extracting frameworks, decision rules, workflows,…
Run a draft through a structured multi-pass editorial review — high-level scope check, citation verification (via sst-fact-checker sub-skill), claim segmentation, fact-correction…
Verify a list of factual claims via web search. For each claim, runs targeted searches, visits the most relevant pages, and decides verified / corrected / unverified with cited…
Draft long-form content from a prompt and iteratively improve it through internal critique cycles. Each iteration calls the sst-literary-critic skill, applies its feedback, and…
Provide constructive feedback on a draft of written content. Analyzes content, style, structure, themes, voice, and overall quality.
Generate short cinematic videos (typically 5-10 seconds, with audio) from a text prompt and optional seed image, using whatever video-generation API the project has wired up.
Per-task router that picks which sub-skills to invoke for a complex multi-step request, sequences them, passes outputs between them, and synthesizes a final result.