improving-mcp-tools
SkillRun an improve-my-MCP campaign: an autoresearch-style loop that measures the MCP agent experience with the eval harness, picks the highest-impact tool problem from production data, makes one bounded fix, and keeps it only if before/after scores improve. Use when asked to "improve my MCP", run an MCP
Install
git clone https://github.com/PostHog/ai-plugin.git ~/.claude/skills/improving-mcp-toolsWhat is improving-mcp-tools?
Run an improve-my-MCP campaign: an autoresearch-style loop that measures the MCP agent experience with the eval harness, picks the highest-impact tool problem from production data, makes one bounded fix, and keeps it only if before/after scores improve. Use when asked to "improve my MCP", run an MCP improvement campaign, fix tool discoverability or descriptions based on evidence, or prepare an eval-backed PR for a tool change. Every shipped change must carry eval evidence; guardrails below are hard rules.
What this can do
Capabilities declared in this component's own frontmatter — not inferred.
Inherit all session tools
Declares no tool restrictions — inherits every session tool
~128 tokens of context used while enabled, before you invoke anything
Documentation
README · ~3 min readImproving MCP tools
An MCP server gets better only in ways you can measure. This skill is the campaign procedure: score the current agent experience, fix the biggest problem, re-score, and only ship changes the numbers justify. It is the operating manual for the "improve my MCP" loop — one iteration per pass, journaled so a later iteration (or a different agent) can resume without repeating work.
The objective function
services/mcp/evals/ is the harness. benchmark/tasks.yaml is a fixed set of
agent tasks with expected_tools and success_criteria; scores are only
Reviews
Log in to leave a review.
No reviews yet — be the first.
Explore related
Other things in this space — across every part of the ecosystem, not just skills.
Skillssimilar to this one
All skills →ECC
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
235.3K stars
claude-md-improver
Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md files. Scans for all CLAUDE.md files, evaluates quality against templates, outputs quality report, then makes targeted updates. Also use when the user mentions "CLAUDE.md maintena
32.8K stars
Anthropic-Cybersecurity-Skills
817 structured cybersecurity skills for AI agents · Mapped to 6 frameworks: MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, D3FEND, NIST AI RMF & MITRE F3 (Fight Fraud) · agentskills.io standard · Works with Claude Code, GitHub Copilot, Codex CLI, Cursor, Gemini CLI & 20+ platforms · 29 security domains · Apache 2.0
26.9K stars
Plugins
All plugins →claude-security
Deep vulnerability scanning of your own code, run entirely inside your Claude Code session at a chosen effort tier, with every finding challenged before it is reported and the verification tally computed in code. Turns surviving findings into targeted patches, each verified by a panel of agents, tha
32.9K stars
claude-md-management
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
32.9K stars
math-olympiad
Solve competition math (IMO, Putnam, USAMO) with adversarial verification that catches what self-verification misses. Fresh-context verifiers attack proofs with specific failure patterns. Calibrated abstention over bluffing.
32.9K stars
Subagents
All subagents →ECC
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
235.3K stars
claude-security
The dedicated Claude Security orchestrator. Hand it an unattended job — "fully scan this repository and patch what you find; I understand it will use a lot of tokens" — and it runs the whole thing itself: capturing the revision, driving the multi-agent scan through the claude-security:scan workflow,
32.8K stars
scan-verifier
Restricted read-only verifier dispatched by the Claude Security scan workflow to vote on one candidate finding; not for direct invocation.
32.8K stars
MCP Servers
All mcp servers →Commands
All commands →modernize-harden
Security vulnerability scan with a reviewable remediation patch — OWASP, CWE, CVE, secrets, injection
32.8K stars
modernize-status
Where am I in the modernization workflow — artifact inventory, staleness, secrets hygiene, next step
32.8K stars
audit-ssl
Audit ZIA SSL inspection rules -- list rules by action (INSPECT, DO_NOT_INSPECT, DO_NOT_DECRYPT, BLOCK), identify bypasses, and assess risk.