Product & Planning

abelski Skill

Fetch unresolved user-reported issues from this project's issue tracker, filter out spam/test noise by checking each against real data, and draft a bugfix plan per confirmed issue into plans/triage/active/ — using the same frontmatter/checklist shape ralph-implement already drives. Use when asked to triage a backlog of user-reported issues, process bug reports, or sync triage plan files with tracker state. Pairs with fix-issue-from-triage, which executes one drafted plan.

wundercorp Bundle

llama.cpp local GGUF inference + HF Hub model discovery.

wundercorp Bundle

Drug discovery: ChEMBL search, drug-likeness, interactions.

patsnap Skill

化合物库反向靶点发现工作流。给定化合物 SMILES，依次执行 ADMET 成药性过滤、骨架分析、结构相似检索、靶点情报验证、FTO 专利风险扫描、SAR 构效关系提取，输出优先级靶点-化合物改造方向清单，支持生成 PPT 与 PDF 报告。

patsnap Skill

Design and generate a configurable single-file enterprise patent-portfolio operations workspace with a dashboard, asset register, fee/deadline view, outside-counsel analytics, competitor monitoring, FTO workflow intake, patent-value screening, and novelty-search intake. Use when a technology or life-sciences company wants a portfolio-management prototype, refreshed portfolio view, phased IP-operations roadmap, or HTML workspace based on authorized patent data.

patsnap Skill

Identify, structure, screen, and route potentially patentable inventions from R&D projects, technical improvements, standards work, existing innovations or portfolios, competitor patents, design-around needs, cross-domain technology transfer, or emerging opportunity hypotheses. Use when engineers or IP teams need a quick or deep four-block, ten-step invention-mining workflow with patent/prior-art evidence, checkpoints, innovation cards, a six-month roadmap, and Markdown or HTML reporting.

patsnap Bundle

Evaluate a supplied technology or scoped technology portfolio, identify and rank evidence-backed potential licensees, acquirers, commercialization partners, or joint-development partners, assess transfer readiness and risks, and generate an auditable HTML decision-support report. Use for technology transfer, research commercialization, licensing partner discovery, technology-to-company matching, or recipient prioritization.

patsnap Bundle

Build, refine, govern, and apply an evidence-based taxonomy to patents, scientific literature, product records, technical intelligence, customer requirements, and other structured text. Use for open label discovery, semi-open or closed-set classification, label definitions and decision rules, pilot labeling, full CSV/XLSX labeling, adjudication queues, taxonomy backlogs, quality assurance, and selective Patsnap MCP evidence enrichment.

patsnap Bundle

Identify candidate patent white-space signals from a patent map, technology-effect matrix, technology-application matrix, cluster map, roadmap, or sparse portfolio region; test whether the signal is a search or classification artifact; assess the value of the underlying problem; diagnose route breaks and primary contradictions; and propose two to four principle-level resolution directions. Use for structured innovation-opportunity exploration from patent-map evidence. Require explicit user confirmation after candidate selection and after problem-value assessment; do not perform downstream technical validation, commercial validation, FTO, patentability, or filing-strategy justification.

patsnap Skill

央企科技成果对外输出——对接对象发现工具。用户输入拟输出的专利号或技术描述，先调用智慧芽MCP提取资产技术特征，再识别输出路径（许可/转让/作价入股/质押佐证），执行三轨检索并输出有专利证据支撑的目标企业短名单及推荐对接路径。

little-grebe-inc Bundle

Financial data and research API for US, China and Japan equities, built by drillr from primary filings (SEC EDGAR, cninfo, EDINET); every figure links to the passage it was filed in. 29 REST endpoints: ticker resolution, natural-language company discovery, filing lists and full-text filing search (EN/ZH/JA), the three statements as reported plus valuation metrics, earnings calendar and structured call summaries, US insider trades and 13F holdings, corporate-event timelines (financings, deals, executive changes, corporate actions, 13D/G stakes), executive rosters and pay, analyst ratings and consensus, and research signals (industry inflections, enterprise AI adoption, news storylines). Use whenever the user asks about a listed company's fundamentals, filings, earnings, ownership, events or analysts, wants companies by description, or follows market news. Handles API-key onboarding, then calls gateway.drillr.ai/api/v2; points MCP-capable clients at the MCP server.

cspoerer62 Skill

Run a sales pipeline end to end — stage definitions, qualification, discovery, objections, and closing — without a CRM. Use for any conversation with a potential buyer, for deciding who to spend time on, and for moving a "maybe" to a decision. Triggers on "follow up with", "they went quiet", "how do I close", "discovery call", "qualify", "pipeline", "objection", "quote", "proposal".

yuji-tt Bundle

Coordinate objective auditing, mechanistic deepening, and structural transfer for open-ended research, algorithm design, engineering, product, or optimization problems. Use to diagnose a plateau or choose the next informative experiment, not to burden well-defined routine tasks with reframing.

stofancy Bundle

Search the web through SearXNG-cli with task-aware engine selection, pagination, deduplication, and structured results. Use for current facts, source discovery, targeted engine queries, or any request that requires web search through a configured SearXNG instance.

ryanalexanderbrashear Skill

Turn a description of a project's end goal into a project plan — success criteria, milestones, and a numbered work breakdown that plan-work can pick up item by item. Covers both a new codebase built from nothing and a large body of work inside an existing one. Use when the user describes something they want to build or change at the scale of weeks rather than hours, wants to start a new app, service, tool, or library from scratch, asks for a roadmap, wants an epic or initiative broken down, or asks how to approach a project.

gabson0x Skill

External research synthesis from Trail of Bits, SlowMist, ConsenSys, Immunefi, and Cyfrin. Use this for advanced audit methodology, Echidna/Medusa fuzzing setup, Slither custom detector writing, attack pattern deep dives, or the 4-phase learning roadmap.

mimmo-the-root Skill

Scrive patch notes, annunci di update e roadmap per mappe Fortnite in modo chiaro, accattivante e orientato a far tornare i player. Usa quando l'utente deve comunicare aggiornamenti.

tahr-security Bundle

Perform an evidence-backed, pentester-style security review of an application from source, configuration, specifications, tests, and optionally an explicitly authorized local or staging runtime. Use for comprehensive app security audits, pentest readiness, pre-release reviews, dangerous-flaw discovery, or coordinating the Tahr specialist skills; also use when a prior scanner or LLM review created confidence that needs independent verification.

tahr-security Bundle

Map the real security-relevant surface of a web application or API from source, specifications, JavaScript, browser behavior, and authorized traffic. Use for pre-pentest reconnaissance, security-review scoping, hidden route or parameter discovery, undocumented API inventory, role-aware surface comparison, or judging whether an existing review actually covered the application.

rifteo Bundle

Full JavaScript analysis methodology for pentesting and bug bounty JS file discovery, secret extraction, endpoint mapping, DOM XSS, prototype pollution, postMessage abuse, client-side logic flaws, source map extraction, and hardcoded credential hunting. Trigger when the user wants to analyze JavaScript files from a target, asks to find endpoints/API routes/hidden parameters in JS bundles, wants to hunt for secrets or credentials in JS source, asks to test DOM XSS/prototype pollution/postMessage vulnerabilities, wants to deobfuscate or extract source maps, asks about client-side logic flaws or insecure storage, or mentions webpack/React/Angular/Vue/Next.js.

rifteo Bundle

Complete SSRF detection and exploitation methodology injection point discovery, cloud metadata theft (AWS/GCP/Azure), internal network enumeration, protocol handler abuse, filter bypass techniques, blind SSRF via OOB, and report structure. Trigger when the user sees any parameter that accepts a URL, hostname, IP, or path, wants to check if a server fetches external resources, is testing cloud-hosted applications for metadata endpoint access, or wants to probe internal services through a compromised SSRF point.

gabson0x Skill

Web2 recon pipeline — subdomain enum, URL crawling, JS analysis, temp emails, directory fuzzing. Trust-first asset discovery.

rifteo Bundle

Complete open redirect detection and exploitation methodology parameter discovery, 30+ bypass techniques, OAuth token theft, SSRF chaining, CSP abuse, phishing escalation, and report structure. Trigger when the user asks to test for open redirect or unvalidated redirect/forward, sees a parameter like ?next=/?url=/?redirect=/?return=/?goto= in a URL, wants to steal OAuth tokens via redirect_uri manipulation, needs to chain open redirect into SSRF/CSP bypass/account takeover, sees a 30x response with a controllable Location header, or wants to bypass a redirect allowlist.

gabson0x Skill

AI-powered tools for Web3 bug bounty automation. Use when you want to automate recon, run autonomous audits, or use AI agents for vulnerability discovery.

rifteo Bundle

Convert a security finding or vulnerability into a prioritized step-by-step remediation plan with effort estimates per step. Trigger when the user provides a vulnerability, finding, or bug needing a fix plan, asks "how do we fix this?" or "what's the remediation for X?", wants to estimate the work involved in addressing a finding, or needs a remediation roadmap to present to developers or stakeholders.

ankit1598 Bundle

Two-phase local PRD workflow — discovery interview to PRD, then PRD to phased implementation plan. All outputs go to .artifacts/. Use when planning a new feature, writing a PRD, creating an implementation plan, or when the user says "write a PRD", "plan this feature", "document requirements", or "create an implementation plan".

ankit1598 Skill

Keeps project .artifacts/ in sync after implementation — updates PRDs, plans, status, references, and diagrams that drifted from the code. Use when finishing a feature slice, closing a plan phase, code diverges from a PRD/plan, or the user says "update the artifacts", "sync artifacts", or "keep docs current".

agentcorp-inc Bundle

Required reading before writing any HogQL/SQL or calling execute-sql against PostHog. Use whenever the user wants to search, find, or do complex aggregations PostHog entities (insights, dashboards, cohorts, feature flags, experiments, surveys, hog flows, data warehouse, persons, etc.) and query analytics data (trends, funnels, retention, lifecycle, paths, stickiness, web analytics, error tracking, logs, sessions, LLM traces). Covers HogQL syntax differences from ClickHouse SQL, system table schemas (system.*), available functions, query examples, and the schema-discovery workflow.

gwyntel Bundle

Find vetted free media sources using the FMHY catalogue. Ships an offline greppable mirror of the FMHY wiki (references/atlas) with per-category source picks, unsafe-site avoidance, and release-quality checks. Source discovery only — no torrent-client operation or transcoding.

sumanjeet0012 Skill

Research and assemble the highest-yield LeetCode practice questions for any DSA topic (BFS, DFS, Dynamic Programming, Two Pointers, Monotonic Stack, Sliding Window, Tries, Graphs, etc.). Curates battle-tested problem sets grouped by core pattern and difficulty (Easy/Medium/Hard), with direct URLs, frequency signals, key takeaways, and a structured 7-to-14 day practice sequence. Use when the user asks for "best LeetCode questions for X", "practice questions for DP / graphs", "what LeetCode problems should I do to master sliding window", or wants a curated problem roadmap.

agentcorp-inc Bundle

Guide the user through connecting a new data warehouse source — Postgres, MySQL, Stripe, Hubspot, MongoDB, Salesforce, BigQuery, Snowflake, and so on. Use when the user wants to "connect Stripe", "import data from Postgres", "add a new data source", "sync my warehouse tables", or wants to pick sync methods for each table. Walks through source-type discovery, credential validation, table discovery, per-table sync_type selection, and the final create call. Also covers picking a good prefix and what to do right after creation.

vroind-ausm-all Bundle

Survey a codebase's animation and motion code as a senior motion advisor, then produce a prioritized audit and self-contained implementation plans for other agents (or cheaper models) to execute. Read-only on source code — it plans improvements, it does not apply them. Use when the user asks to "improve the animations", "audit the motion", "make this app feel better", or wants a roadmap of animation fixes rather than a review of a single diff.

silviobeer Bundle

Reproduce, diagnose, plan, implement, and verify reported software bugs, regressions, broken UI flows, incorrect behavior, and production defects. Use whenever a user asks to fix a bug or regression, investigate why behavior is wrong, or explain why existing tests missed a defect. Reproduce browser-facing bugs in a real browser when safe and available, prove the regression test fails before the fix, dispatch a narrowly scoped implementer, run a bounded Ralph verification loop, and document the test-escape cause. Not for feature requests, speculative refactors, or QA-only discovery without a requested fix.

silviobeer Bundle

Route a concept, PRD set, architecture, implementation plan, QA evidence, or curated documentation to the provider opposite its author for an adversarial, read-only review. Used by requirements-engineer before PRD handoff, inside QA for its required evidence review, and after creating a concept, architecture, wave plans, or P7 curated docs. Works before P0 without state.json. Not a replacement for runtime QA or form/size caps.

silviobeer Bundle

Route a concept, PRD set, architecture, implementation plan, QA evidence, or curated documentation to the provider opposite its author for an adversarial, read-only review. Used by requirements-engineer before PRD handoff, inside QA for its required evidence review, and after creating a concept, architecture, wave plans, or P7 curated docs. Works before P0 without state.json. Not a replacement for runtime QA or form/size caps.

silviobeer Bundle

Run a human checkpoint as a structured reconcile loop: present a compact review package, collect feedback point by point (adopt/change/reject/defer), write the decision log, cascade every change through all affected planning artifacts, and seal the result in state.json. Use when: (1) architecture + wave plans are ready for Checkpoint 1 approval before any execution, (2) PR review comments need reconciling at Checkpoint 2 (invoked via delivery), (3) intake bootstrap drafts need validation (via the intake skill, 0b). Not for: producing the plans themselves (use writing-plans), resolving PRD reviews on the discovery track (use review-reconcile), P0 setup (use setup).