1.1K skills · sorted by relevance
Generate review drafts of master agreements from a shared template and a JSON file for each counterparty. Select clauses by business role, produce Markdown or DOCX drafts, and follow agreement-specific procedures for adding opportunities to Schedule A.
Inspect Solana wallet balances, token holdings, transactions, and NFTs with USD pricing. Check portfolio value, token details, recent activity, large SOL transfers, and network statistics through eight commands that require no API key.
Review support requests, rank urgency by impact and timing, and identify the responsible internal team. Record evidence, next actions, and response deadlines, then prepare customer reply drafts and an escalation summary organized by urgency.
Analyzes the user's own sent emails, messages, and documents to capture characteristic phrasing, sentence rhythm, and audience-based tone changes. It saves a personal writing profile as a skill for future drafts in the user's voice.
Prepare interview scheduling drafts by matching Greenhouse interview plans with every panelist’s calendar. Produce two or three available time options, a candidate email, and individual invitation drafts for a coordinator to review and send.
Research new HubSpot leads and prepare personalized follow-up email drafts using the team's sales guidance. Include one tailored qualifying question and an available call time, save research to HubSpot, and hold drafts for human review.
Draft weekly check-in emails to outside counsel using matter records, covering progress, deadlines, pending decisions, and budget. Save a Markdown draft for each matter and create Gmail drafts when an authenticated connection is available.
Turn recent X bookmarks into quote-post drafts with source links. The skill studies up to 100 recent posts by the author to match their voice, then organizes suggestions into a dated queue for review and revision.
Create and distribute NFTs and tokens on Solana, or register blockchain identities for agents. The skill guides selection of Metaplex tools and explains when to use its command-line interface or SDKs, libraries for writing application code.
Fix SQLite "database disk image is malformed" errors caused by corrupted FTS5 indexes. Use when: (1) UPDATE/INSERT fails with "stepping, database disk image is malformed" but PRAGMA integrity_check returns "ok", (2) Only specific records fail to update while others succeed, (3) Records contain dirty text with tabs, newlines, or unusual characters that were inserted into FTS5-indexed columns. The misleading error message suggests disk corruption, but the actual issue is FTS5 index corruption from malformed text content.
The English summary is being prepared. Showing the original description.
Map observed site vegetation, species lists, land-cover descriptions, or plant management PFTs to EcoSIM vegetation codes using templates/ecosim_pftpar_20260303.nc.cdl. Use when choosing or validating EcoSIM pft_type values, pfts entries, pfts_short categories, pfts_long plant type meanings, or the combined short-code plus Koppen climate numerical code used by plant management inputs.
The English summary is being prepared. Showing the original description.
Set up human approval for agent-drafted messages to customers or partners. Bind decisions to exact text and destinations, record delivery evidence, and prevent outdated approvals or competing workers from triggering unintended sends.
Research purchases and gifts against needs, budget, fit, and delivery deadlines. Compare exact products, stock, full costs, and return terms, then prepare a cart or complete an order within the user’s authorization.
Use AltoRank to check whether search engines and AI assistants can read a site, review stored Search Console data, research keywords, and create SEO article drafts. Drafts enter a review queue where a person decides what to publish.
Run context-mode diagnostics to check runtimes, hooks, full-text search support, plugin registration, and npm and marketplace versions. Results appear directly in the conversation with clear status labels, with a CLI fallback if the MCP call fails.
Find previously indexed project files, documentation, and session memory in context-mode's persistent full-text search database. Search related questions together and narrow results to a named project or source without rereading raw material into the conversation.
Turns sales and stock data into a reorder plan with quantities, costs, and estimated stockout dates. Prepares supplier purchase orders, email drafts, and accounting memos for later invoice checks, while flagging slow stock and requiring approval before sending.
Bring together public reviews, complaints, and customer activity to identify recurring issues and customers who may leave. Produce evidence-backed themes, review reply drafts in the owner's voice, and personalized messages to win back inactive customers.
Investigate and maintain documented workflows using Screenpipe evidence and shared drafts. Review whether recorded actions support each procedure, preserve verified steps, and add timing measurements only when clear start and end evidence is available.
Find recurring questions in resolved Plain support tickets that existing knowledge articles do not cover. Draft articles from actual resolutions, avoid previously drafted topics, and open a pull request for human review.
Prepare social post drafts from upcoming Notion calendar entries for LinkedIn, X, and Instagram. Group them with scheduled dates in Slack for human review, and mark drafted entries to prevent duplicates. It never publishes social posts.
Prepare a first-pass review of incoming NDAs, or confidentiality agreements, against a team's standard positions. The skill saves the document, drafts suggested clause changes, and prepares a counsel summary without signing or sending anything.
Monitor public news, social platforms, and forums for new brand mentions. Remove previously reported results, classify sentiment, and send a Slack digest with response drafts for negative or notable mentions, leaving public replies to people.
Examine writing for familiar AI patterns, statistical features, Pangram detection scores, and hidden character signatures. Compare drafts against known human writing to interpret the evidence, with explanations and limitations rather than a definitive authorship claim.