Stormix
UserSearch local Cursor, Claude Code, and Codex session transcripts via MCP
Categories
Indexed Skills (20)
changeset
Generate a changeset file describing the current PR's changes. Use when asked to "create a changeset", "add a changeset", "/changeset", or after implementing a feature/fix that needs a changelog entry. Produces a randomly named `.changeset/*.md` file with affected packages, bump type, and an 80-character-max user-facing summary.
humanizer
Remove AI tells from prose so it reads like a person wrote it.
improve-codebase-architecture
Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
logging-best-practices
Logging best practices focused on wide events (canonical log lines) for powerful debugging and analytics
security-review
Finds exploitable application security vulnerabilities in code changes. Use for Warden security scans, appsec review, OWASP-style checks, authentication or authorization bugs, injection, XSS, SSRF, path traversal, secrets, unsafe crypto, webhook verification, open redirects, or sensitive data exposure.
thermo-nuclear-code-quality-review
Run an extremely strict maintainability review for abstraction quality, giant files, and spaghetti-condition growth. Use for a thermo-nuclear code quality review, thermonuclear review, deep code quality audit, or especially harsh maintainability review.
commit
Commit Staged Changes
fix-pr
Fix PR Comments
adversarial-review
Adversarial review of any artifact — a plan, PRD, ADR, design doc, code diff, or the current conversation itself — from a hostile stance that tries to break it rather than improve it. Use when asked to "adversarially review", "red team this", "poke holes in", "attack this plan", "review our discussion", "what did we get wrong", "stress-test this", "steelman then break", "review this ADR/PRD/doc", or "find the flaws". Resolves the target, picks critique lenses per artifact type, self-refutes each candidate finding, and reports ranked findings with concrete failure scenarios. Read-only — never edits the artifact. Escalates to independent subagents (optionally on a different model) on request or for large targets.
agent-browser
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
git-conventions
Git Conventions: Guidelines for commit messages, branch naming, and version control practices
opensrc
Fetch source code for npm, PyPI, or crates.io packages and GitHub/GitLab repos to provide AI agents with implementation context beyond types and docs. Use when needing to understand how a library works internally, debug dependency issues, or explore package implementations.
rebase
Fetch the latest default branch and rebase the current branch on top of it, resolving any merge conflicts automatically. Use when asked to "rebase", "rebase on main", "update branch with main", "sync with main", "rebase onto latest", or "/rebase".
recomposing-commits
Use when commits on a feature branch are messy, out of logical order, mix unrelated changes, or need restructuring before a PR - also triggered by "clean up history", "reorganize commits", "recompose branch", "make commits logical", or similar
show-me
Help the user understand the current topic visually with concise diagrams, code-shape sketches, and focused HTML artifacts.
simplify
Simplify scoped code with parallel read-only review subagents, then apply targeted cleanup fixes without a large refactor.
writing-for-agents
Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.
transcript-search
Search local Cursor, Claude Code, and Codex session transcripts. Use when looking up past agent sessions, choosing grep vs ranked search, building the search index, dumping a session by id, or scoping by cwd and provider.
deslop
Remove AI code slop
calldiff
Generate call-stack diffs with `npx calldiff@latest` and include them when writing a plan, design doc, ADR, PR description, commit body, or summary of a code change, so reviewers can see how call flow changed. Use whenever a change rewires who-calls-whom and a line diff would bury the shape of the change.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.