Agent Workflow Claude Skills
4 122 agent workflow skills from 665 authors. They configure the agents themselves: memory, prompts, context and other skills. Half of them fit into 1 844 tokens or less — that is what one costs your context window when the agent loads it. 778 ship runnable scripts rather than instructions alone. 5 of them cannot work without an MCP server, most often task. We also found 589 copies of these same skills sitting in other people's repositories — counted once here, not 589 times.
4 122 unique 665 authors 4 updated this month 506 from vendors
Call a peer agent's A2A JSON-RPC endpoint. Supports tasks/send (send a task message) and tasks/get (query task status).
Fetch an A2A agent card JSON from a given endpoint URL. Tries direct GET first, then falls back to /.well-known/agent.json.
Use when the user wants to browse, inspect, create, or update exploratory testing sessions in TestDino — by state, status, session type, assignee, release, or tags. Covers list_sessions, get_session, create_session, and update_session. Accepts counter-style IDs like SES-12.
> Reprice swap transaction legs under ASC 845 (Nonmonetary Transactions) to ensure clearing accounts apply equal-value exchange to swap legs, run setBatchUseCounterpartyFiatValue, zero out a clearing account, apply ASC 845, fix swap pricing mismatches, ensure no gain/loss on swaps, or close a month where a swaps/trade clearing account has a residual balance. Also trigger when the user mentions "counterparty fiat value", "swap repricing", "clearing account net to zero", or "equal value exchange".
Extract all 3rd-party (non-owned) addresses from a TRES Finance environment and export them as an XLSX workbook to help users build their contacts list. Use this skill whenever the user wants to export, list, or identify 3rd-party addresses, counterparties, or external addresses from their transactions — even if they don't say 'contacts'. Also trigger when the user asks to prepare a contacts import file, find unknown addresses, or build an address book from transaction history. Do NOT trigger for viewing existing contacts or searching the address book — only for extracting NEW 3rd-party addresses from transaction data.
> Query, display, and resolve reconciliation gaps from the TRES Finance MCP connector. Trigger this skill ONLY when the user explicitly requests to view or close reconciliation for today", "plug the reconciliation gaps for ETH", "fix the gaps for USDC and BTC". Do NOT trigger for general balance queries, transaction history, or ledger browsing. fetching gap data, enriching with fiat and on-chain balances, rendering an HTML dashboard where each gap row has copy-prompt buttons (Plug / Auto-fill) — clicking copies a ready-to-paste Claude prompt for that gap. The user pastes it in the chat and Claude executes the action. Ends with a data collect once the user is done.
> Submit feedback about the TRES Claude plugin — bug reports, feature requests, skill improvements, new skill ideas, MCP issues, workflow friction, or positive feedback about what's working well. Use this skill whenever the user wants to share any kind of feedback "report a bug", "request a feature", "suggest an improvement", "I have an idea", "something is broken", "the skill isn't working", "I love this skill", "this worked great", "the MCP is returning wrong data", "the flow is confusing", "can you fix the skill", "file a skill request", "give feedback", "this could be better". Also trigger proactively when the conversation appears to be wrapping up — e.g. the user says "thanks", "that's all", "looks good", "we're done", "nothing else", or any other signal that the task is complete. In that case, offer a brief feedback prompt instead of launching the full guided flow. Do NOT trigger for general questions about how a skill works — only when the user wants to submit feedback or the conversation is ending.
Create (generate) any TRES Finance report end-to-end via the tres-mcp MCP server and GraphQL — trigger the export, verify a report row was actually created (guarding against silent failures), poll until done, and return the download link. Trigger this skill on ANY report creation request, including phrases like "create a report", "generate a report", "export", "run a report", "I need a Transaction Ledger / Balances / Reconciliation / Cost Basis / Roll Forward / Staking / Audit report", "pull the data for", "download a report for", "give me a CSV/XLSX of", or whenever the user wants TRES to produce a report file. Use together with tres-report-advisor when the user is unsure which report they need.
> Analyze a blockchain transaction by its hash using TRES Finance MCP and generate a visual flow diagram showing all asset movements, followed by a plain-language explanation of what happened. Use this skill whenever the user provides a transaction hash and asks to "analyze", "explain", "visualize", "diagram", "show me what happened in", or "tell the story of" a transaction. Also trigger when the user pastes a tx hash (long hex string starting with 0x) and asks anything about it. Always use this skill for transaction hash analysis — do not attempt to answer from memory alone.
Use when red-teaming an agentic AI / LLM application — indirect & zero-click prompt injection, MCP tool poisoning, persistent memory poisoning, excessive-agency tool abuse, multi-turn jailbreaks, PyRIT/Garak/Promptfoo harnesses
Use when starting any offensive-security engagement or task — establishes how to find and invoke the right skill before any action (including clarifying questions, recon, exploitation, or reporting)
Three-phase design review. Chain architect → refiner → critique subagents. Triggers on: 'design review', 'architecture review', '/arc', system design proposals, significant refactoring decisions, new service or module design.
Use when about to ask the user a factual question, propose a solution, diagnose an error, or choose between approaches. Triggers on: 'Do you have X installed?', 'What version?', 'Is X configured?', 'We should...', 'The fix is...', 'Options: 1...', 'Based on my understanding...', 'I believe X supports...'. Before deciding anything, spin up parallel subagents to WebSearch for current docs, community solutions, framework best practices, and GitHub issues. Your memory is stale — verify everything.
FOLLOW THE STATE MACHINE IN SKILL.MD. When user says 'continue': (1) FIRST: Run pwd, (2) Announce STATE: CHECK_STATUS, (3) Read .claude/session.md to check Status field, (4) Route based on Status. NEVER auto-advance tasks. NEVER use TodoWrite. NEVER create git commits.
Explain plugin, skill, command, agent, and hook mechanics used here. Use when authoring or debugging plugins. Do not use for ops; use night-market-operations.
Guide creating Claude Code hooks with security-first design. Use for validation and enforcement.
Detect friction signals; graduate patterns into rules. Use for session retrospectives.
Build composable skill modules with hub-and-spoke loading. Use when token budget is tight.
Surface expert frameworks. Use when creating or evaluating skills, hooks, or agents.
Evaluate Claude Code rules in .claude/rules/. Use for frontmatter, globs, and quality audits.
Guide creating Claude Code skills with TDD and persuasion principles. Use for new skill development.
Evaluate Claude skill quality through auditing. Use when reviewing or auditing skills.
Test skills via TDD in fresh subagents. Use when validating behavior or preventing bias.
Audit Skill() refs; detect hubs, isolates, and dangling targets. Use when auditing skills.
Polishes working code through successive quality passes in fresh subagents. Use after tests pass when code needs multi-dimension refinement before release.
Orchestrates full project lifecycle by auto-detecting state and routing to the correct phase. Use when starting or resuming a project mid-workflow.
Build a project skill library in .claude/skills/ via discovery, parallel authoring, and review. Use when packaging tribal knowledge. Do not use for one skill.
Delegates tasks to Gemini or Qwen with quota tracking and error handling. Use when tasks exceed context window or need cheaper processing.
Coordinates Claude agent teams via filesystem protocol. Use when orchestrating parallel agents with task dependencies. Do not use for single-agent tasks.
Tracks per-agent token usage and flags waste in parallel dispatch. Use when evaluating parallel agent efficiency or after a multi-agent run.
Manages context overflow by handing off to a fresh subagent at 80% usage. Use when context pressure is critical and work must continue uninterrupted.
Recommends context compression strategies for bloated or quota-heavy sessions. Use when context feels sluggish or quota burns faster than expected.
Optimizes context window via MECW principles and memory tiering. Use when context exceeds 30% or before long multi-step tasks.
Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.
Enforces token quota management at session start with conservation and compression checks. Use at the start of every session or before large context loads.
Removes the egregore watchdog daemon and its associated files. Use when stopping automated session relaunching or cleaning up egregore infrastructure.
Makes agent reasoning visible, surfaces tradeoffs, and fades help so humans build judgment. Use when reviewing or learning from agent-written code.
Shapes agent behavior via instruction framing and style transfer. Use when composing dispatch prompts or writing skill instructions for parallel review agents.
Recovers broken agent state via crash recovery, context overflow, and merge conflict protocols. Use when an agent session fails or a worktree is corrupted.
Implements hub-and-spoke lazy loading to minimize token usage in large skills. Use when building multi-module skills that need conditional on-demand loading.
Classifies agent tasks into 4 risk tiers (GREEN/YELLOW/RED/CRITICAL). Use when assessing action reversibility before committing to an approach.
Implements structured usage logging and audit trails for cost and session tracking. Use when adding audit trails, usage analytics, or cost tracking to a skill.
Scores agent actions by expected gain, cost, uncertainty, and redundancy. Use when deciding whether to dispatch an agent or invoke a tool.
> info gaps. Use when verifying session state or summary before handoff or compression.
Builds session-scoped temporary memory palaces for extended conversations. Use when tracking state across interruptions in a multi-step project.
Provisions the oracle ML inference daemon with onnxruntime via uv. Use when setting up local ONNX model inference for skill quality evaluation.
Orchestrates multi-domain review (code, arch, tests, security) in a single pass. Use when thorough pre-release review is needed.
Implements GitHub or GitLab issues via parallel subagents with review gates between task batches. Use when resolving multi-step issues end-to-end.