419 tagged claude-code-skill, measured the same way as everything else here.
Browse within: claude-ai 72claude-code-skills 68open-source 54marketing-automation 47seo 38ai-marketing 29ai-content 28content-creation 28fullstack 23agentic-framework 18agentic-os 18ai-seo 18claude-plugins 18knowledge-management 15
ezra-y/academic-pdf-translation
Agent
A worker for translating assigned batches of academic-paper text into Chinese. Each batch is a group of frozen text units with source text, page numbers, and required reference points.
ezra-y/academic-pdf-translation
Agent
An independent reviewer that compares an academic PDF with its candidate translation and source-to-translation evidence. It checks whether the translation is complete, accurate, readable, and visually correct.
Agent
Plans component architecture, file structure, and data flows from an approved design system. Produces web-architect-plan.md with per-component specs.
Agent
Implements code from web-architect-plan.md, applying design tokens from MASTER.md. Produces working code files and a build report.
Agent
Generates unique design systems via 4-layer Constrained Generation. Produces design-system/MASTER.md with CSS custom properties, concept narrative, and component priorities.
snowmead/questionably-ultrathink
Agent
Use this agent to build a DAG structure of atomic questions from a complex problem. This agent creates ONLY the question graph - no solving. Examples: Context: User asks a multi-part question requiring synthesis user: "How does React's reconciliation work and how does it compare to Vue?" assistant: "I'll use the…
snowmead/questionably-ultrathink
Agent
Use this agent to generate claims and verification questions for ONE atomic question. This agent does NOT fact-check or research - it only decomposes the question into verifiable claims. The orchestrator will spawn separate cove-verifier agents to research each verification question. Examples: Context: Generating…
snowmead/questionably-ultrathink
Agent
Use this agent to cross-check claims against independent verification answers and create the final answer. This agent reads claims.md and verifiers/.md from the atom directory. It compares original claims to independently-obtained answers and creates answer.md with the verification trace. Examples: Context: After…
Agent
Write-only, headless agent that reads a captured-answers scratch file produced by /su:discover and writes a single Suhail-format plan file. Sole writer of the plan — it does not interview the user, run commands, or modify anything other than the output plan file. Invoked only by /su:discover (Phase 5) after the…
Agent
Implements one Part by writing code per the scout's step list. Generic — runs whatever commands the brief and steps specify. Writes a summary to .suhail/parts/ /execution.md. Never commits. Never deploys. Both are flagged as Manual follow-ups. Invoked only by the suhail orchestrator.
Agent
One-shot project scanner. Reads project manifests, conventions docs, and directory layout, then writes a structured intel cache under .suhail/intel/. Stack-agnostic — discovers conventions on its own. Invoked only by /su:init.
GuillaumeLessard/qector-claude-plugin
Agent
Staff software engineer for QECTOR integrations. Use for wiring MCP servers, stdio JSON-RPC 2.0 client code, high-performance batched/mmap decoding, buildcodefrommatrix, and debugging integrations against qector-decoder-v3 or the Workbench.
GuillaumeLessard/qector-claude-plugin
Agent
QECTOR operations and security administrator. Use for health triage, runtime configuration, environment management, and local-by-default enforcement. The bundled library MCP server is app-free; any optional Workbench must be connected and negotiated separately.
GuillaumeLessard/qector-claude-plugin
Agent
QECTOR governance and verification agent. Use for validating MCP connectivity (tools/list handshake), auditing claims against evidence, enforcing local-by-default rules, verifying artifact integrity and license posture before any action is taken.
Agent
Reviewer for angle X of the self-review loop. Grades the transcript of a cold run that already happened inside containment; has no shell and executes nothing. Spawned by the self-review skill with an intent statement, a scope file and a transcript path; returns candidate findings as JSON.
Agent
Read-only reviewer for one angle of the self-review loop. Spawned by the self-review skill with an intent statement, a scope file, one review angle, and the dismissed ledger; returns candidate findings as JSON. Never edits files.
Agent
Read-only adversarial verifier for the self-review loop. Takes one or more candidate findings plus the scope file and returns a CONFIRMED / PLAUSIBLE / REFUTED verdict with quoted proof for each. Never edits files.
Agent
Audits a superpowers-graph run for the ways these graphs fail: a node result matching zero exit guards, a step recorded as passed that never ran, a retry loop whose counter is not being incremented, an irreversible node entered before its gates, and a decision that exists only in the transcript. Read-only — it…
Agent
Reviews handoff workflows for token efficiency, context hygiene, and avoidable model calls.
Agent
Reviews transcript handoff tooling for secret exposure, command injection, and unsafe launch behavior.
Agent
Reviews handoff workflows for install clarity, command ergonomics, and user recovery paths.