mcp-integration-reference
Template for skills that integrate with an MCP server. Demonstrates the reference file pattern: Claude reads a domain-specific MCP cheatsheet before making any tool calls, reducing query failures caused by server-specific gotchas. Fork this skill and replace the Sentry example with your target MCP.
What this skill does
# MCP Integration Reference Pattern > This is a template skill. It shows how to structure a skill that wraps an MCP server. Replace `sentry` with your MCP server name and adapt the reference file at `references/sentry-mcp.md`. ## What This Pattern Solves When a skill calls an MCP server without prior context, Claude guesses at the query syntax. This works for simple calls but breaks on anything with non-obvious behavior: pagination quirks, required parameter combinations, rate limits, or subtle format restrictions. The fix: a `references/<mcp-name>.md` file that captures all the gotchas. The skill reads this file before making any MCP call. Zero guessing. Three types of content go in the reference file: 1. Parameter semantics that differ from what the tool name implies 2. Known error patterns and their root causes 3. Working query examples (copy-paste, no thinking required) --- ## Step 1: Read the MCP Reference File **Before doing anything else**, read the full MCP reference: ``` Read: references/sentry-mcp.md ``` This file contains query syntax, known gotchas, and working examples for the Sentry MCP. Do not skip this step. --- ## Step 2: Gather Scope from User Ask the user: - **Time range**: Last 24h? 7 days? Custom range? - **Environments**: `production`, `staging`, or both? - **Projects**: All projects or specific ones? (Default: all) If the user says "just run it with defaults", use: - Time range: last 72 hours - Environment: `production` only - Projects: all --- ## Step 3: Fetch Error Data Using the tool knowledge from Step 1, fetch: 1. **Issue list**: Active unresolved issues, ordered by frequency 2. **Event details**: Full stack traces for the top 5 issues by event count Cap results at 50 issues. If more exist, note the count and focus on the highest-frequency items. --- ## Step 4: Group and Analyze Group issues by root cause, not by error message. Two issues with different messages can share the same underlying cause (shared code path, same external dependency, same config). For each group: - Count of issues in the group - Earliest first-seen date - Affected users count (if available) - Most likely root cause (one sentence, evidence-based) - Relevant file paths from the stack trace --- ## Step 5: Generate Report Output a markdown report with this structure: ```markdown # Error Report: [Project or Scope] **Period**: [start] to [end] **Environment**: [env] **Total active issues**: [N] ## Summary [2-3 sentences: what is the overall health picture?] ## Issue Groups ### Group 1: [Root Cause Label] | Attribute | Value | |----------------|--------------------------| | Issues | N | | Total events | N | | Affected users | N | | First seen | YYYY-MM-DD | | Key file | path/to/file.py:line | **Root cause**: [One paragraph. Specific, evidence-based. Point to file and line.] **Suggested investigation**: [One or two concrete next steps.] --- [Repeat for each group] ## Out of Scope [List issues explicitly excluded and why. Example: "404s on /static/ excluded - expected behavior for SPA asset versioning."] ``` --- ## Scope Rules - This skill detects and describes issues. It does not modify code or create tickets. - If an issue is ambiguous, flag it as "needs investigation" rather than guessing. - Do not include informational logs or warnings unless they correlate directly with errors. --- ## Adapting This Template To fork this skill for a different MCP: 1. Copy this directory: `cp -r examples/skills/mcp-integration-reference examples/skills/<your-skill>/` 2. Rename `references/sentry-mcp.md` to `references/<your-mcp>.md` 3. Replace the reference file content with your MCP's gotchas 4. Update `allowed-tools` in the frontmatter to match your MCP tool names 5. Adjust the analysis steps to match your data domain The pattern works for any MCP that has non-obvious query behavior: Datadog, PagerDuty, Linear, Jira, Posthog, Mixpanel, etc.
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.