discovery skills

darrenhinde/OpenAgentsControl

Skill Claude CodeCodex

Context management skill providing discovery, fetching, harvesting, extraction, compression, organization, cleanup, and guided workflows for project context.

whiteguo233/OpenBiliClaw

Skill Claude CodeCodex

Search for videos on Bilibili using keyword queries generated from user interests.

indexnetwork/index

Skill Claude CodeCodex

Explain how a real code path actually works — as a published Artifact with hand-drawn SVG diagrams, traced from the source rather than from memory. Use this whenever someone asks you to explain, walk through, draw, diagram, map, or visualize a flow, pipeline, lifecycle, request path, state machine, or "how X works" in…

indexnetwork/index

Skill Claude CodeCodex

Use when the user asks about negotiations, pending turns, reviewing what their agent sent, or wants to submit a turn on Index Network.

indexnetwork/index

Skill Claude CodeCodex

Use Index to help users create and refine approved signals. Signals are matched in the background; do not call or suggest direct discovery, run polling, targeted matching, or introductions.

khendzel/skills-janitor

Skill Claude CodeCodex

Find new skills on GitHub or check a specific skill before installing. Use when the user wants to search for skills, evaluate a skill URL, check overlap and security risk before installing, or compare a local skill against alternatives. Trigger with '/janitor-discover'.

kanyun-inc/reskill

Skill Claude CodeCodex

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. Uses reskill as the package manager.

bacoco/AiDesigner

Skill Claude CodeCodex

This Skill operationalizes AiDesigner’s discovery journey playbooks. It walks teams through persona alignment, journey mapping, inspiration scraping, and insight distillation so they can kick off new initiatives with confidence.

radekamirko/C.R.I.S.P

Skill Claude CodeCodex

CRISP Execute — Sprint execution loop with change request management, security gates, product gates, and stakeholder reporting. Use after Phase S (Spec) is complete and crisp-state.json shows readyforexecute: true. Triggers on "start sprint", "begin build", "execute", "sprint 1", "run sprints", or when handed off from…

radekamirko/C.R.I.S.P

Skill Claude CodeCodex

The Mileva Method (CRISP) — Phase 1: Clarify. Problem definition, eliciting, painkiller test, buy vs build, AI justification gate, Go/No-Go. Use at the start of any AI implementation project. Triggers on "clarify", "phase 1", "start discovery", "define the problem", "what problem are we solving", or at the beginning…

radekamirko/C.R.I.S.P

Skill Claude CodeCodex

The Mileva Method (CRISP) — Phase 4: Spec. Full implementation readiness package including solution design, UX direction, tech stack, backlog, MVP prioritization, risk assessment, and AI architecture for Claude Code projects — CLAUDE.md, skill mapping, AI specs, sprint planning, quality gates. Triggers on "spec"…

haabe/mycelium

Skill Claude CodeCodex

Lint canvas files for staleness, missing fields, inconsistent evidence types, and orphaned references. Run periodically or before major transitions.

haabe/mycelium

Skill Claude CodeCodex

Use to analyze correction trends, surface recurring patterns, and graduate repeat corrections to guardrails or anti-patterns.

haabe/mycelium

Skill Claude CodeCodex

Evaluate Mycelium's own process effectiveness. Measures cycle velocity, discard trends, confidence calibration, gate effectiveness, regression rate. Run quarterly or every 20 cycles.

popiliadam/platinum-seo-engine

Skill Claude CodeCodex

Use when: kullanıcı "on-page audit", "meta tag denetimi", "title meta h1 kontrolü", "hedef sorgu sayfada var mı", "title eksik", "h1 eksik", "GSC ile sayfa içi kontrol" der ya da /pseo-on-page-audit çağırır. Also use when: aktif projenin master.xlsx'i mevcut; URL listesi config'te veya gscperformance / crawlsitemap…

elisymlabs/elisym

Skill Claude CodeCodex

YouTube summary agent. Send a link - get overview, key points, and takeaways.

elisymlabs/elisym

Skill Claude CodeCodex

Edit an existing elisym agent's profile (display name, avatar, banner, description, relays, payment addresses, LLM provider/model, security flags) by patching elisym.yaml directly. Use when the user wants to rename their agent, change its picture/banner, switch LLM provider or model, add a payment address, or toggle…

elisymlabs/elisym

Skill Claude CodeCodex

Run an elisym provider agent. Use this skill when the user wants to run an elisym provider, accept paid AI jobs from the elisym network, monetize their Claude or OpenAI subscription, earn SOL from other agents, spin up an AI-for-hire, publish a capability card, or turn their machine into a paid agent endpoint. Covers…

elasticdotventures/_b00t_

Skill Claude CodeCodex

Context management skill providing discovery, fetching, harvesting, extraction, compression, organization, cleanup, and guided workflows for project context.

mcpfinder/mcpfinder

Skill Claude CodeCodex

Install MCPfinder — a local MCP server that searches Official MCP Registry, Glama, and Smithery for 25,000+ MCP servers — into the user's AI client. Use when the user asks for a capability the agent doesn't have (database, API, Slack, filesystem, GitHub, Postgres, etc.) and no MCP tool-finder is already available, or…

Avyayalaya/agent-prime

Skill Claude CodeCodex

Use when synthesizing user research, analyzing interview data, conducting discovery sprints, evaluating evidence quality across sources, or building research-backed feature hypotheses.

Waddling-Penguin/mogkit

Skill Claude CodeCodex

Reads the graph and ranks every claim with single-source or zero-source backing by risk — surfacing what the team would be betting on without evidence, each tied to the decision it would affect. Surfaces risk; does not resolve it.

Waddling-Penguin/mogkit

Skill Claude CodeCodex

Answers a discovery question by interrogating the graph — returning grounded findings with provenance, the explicit gaps in the evidence, and the discovery questions that would close them. Refuses to answer beyond what the corpus supports, and names every gap.

Waddling-Penguin/mogkit

Skill Claude CodeCodex

Reads every file in sources/ and produces a schema-valid graph/graph.json plus a human-readable graph/graph.md. Every node and edge carries provenance; unsourced claims become explicit Assumption nodes. Rates corpus health and says so loudly when it is thin.