Claude Skills by tomzx

Curate the agent-maintained blog section (blog.tomrochette.com-content) by following the Daily refresh procedure in agents/AGENTS.md, pulling, working the article queue, updating and fact-checking articles, verifying links, appending to agents/log.md, and committing scoped to agents/. Use when the user says /agents-section-daily-refresh, "refresh the agents section", "daily blog refresh", or asks to run the daily refresh procedure.

Analyze git history to identify high-churn files and suggest targeted improvements such as refactoring, test coverage, dead code removal, or library replacements.

Analyze a set of code changes (diff or files) and produce a structured test coverage report with three parts: introduced tests, change coverage, and uncovered code. Called by review-pr-full as the first step of its review chain (before validate-pr, verify-pr, and review-pr), and delegated to by review-pr, review-implementation, and verify-pr; can also be invoked directly on any diff.

Downloads an arXiv HTML article, converts it to markdown with pandoc, archives it, and returns a structured summary. Use when processing a single arXiv paper given its HTML URL (e.g., https://arxiv.org/html/2504.12345). Called by the arxiv-catchup skill but can also be invoked directly.

Fetches new arXiv cs.AI papers published since the last processed date, processes each paper's HTML version via the arxiv-article skill, and advances the date checkpoint. Use when the user says /arxiv-catchup, catch up on arXiv, or wants to read recent AI papers.

Estimate how risky a GitHub pull request is and how confident that estimate is, then recommend the next action for a human reviewer. Self-contained: it gathers its evidence from the diff, the codebase, and churn of the touched files, so it can run in parallel with the other review skills. Use when the user asks "how risky is this PR", "assess PR risk", "risk and confidence for this PR", "should I review this deeply", or wants to decide what to do next with a PR.

Upload files (images, logs, screenshots) to a dedicated orphan branch in the repository and embed them in a GitHub issue or PR comment or description, so sensitive content stays out of the main branch and out of inline user-attachments. Use when the user says /attach-assets, "attach image to issue", "attach screenshot to PR", "add image to a GitHub comment programmatically", "host issue images on a branch", "upload sensitive images for an issue", or wants to embed files in a GitHub descriptio...

Audit how your time splits between compounding and depreciating activities using the two-year test. Use when the user says /audit-attention, wants to check attention allocation, asks "where is my time going", or wants to know what to delegate vs. protect.

Audit the codebase for compatibility, the ISO/IEC 25010 characteristic covering co-existence (running alongside other software without conflict) and interoperability (exchanging data via standards). Finds hardcoded shared resources, dependency conflicts, missing API versioning, non-standard data formats, and brittle integrations. Use when the user says /audit-compatibility, "interop audit", "co-existence", "API versioning check", "standards compliance", or runs a 25010 sweep via /audit-sdlc. ...

Audit project dependencies for outdated versions, known vulnerabilities, unmaintained packages, and license issues, then produce a prioritized upgrade and replacement plan.

Audit whether the software actually does what it should, completely and correctly. This is the Functional suitability characteristic of the ISO/IEC 25010 software quality model (completeness, correctness, appropriateness). Cross-checks implemented behavior against requirements in .sdlc/ and surfaces stubs, TODOs, skipped tests, and open bug clusters. Use when the user says /audit-functional-suitability, "functional audit", "does it do what it should", "requirements coverage", "completeness ch...

Audit the codebase for maintainability, the ISO/IEC 25010 characteristic covering modularity, reusability, analyzability, modifiability, and testability. Computes architectural metrics (coupling, fan-out, circular dependencies, layering violations, God modules) that the find-* family does not cover, and aggregates find-* results into a single maintainability scorecard. Use when the user says /audit-maintainability, "coupling analysis", "circular dependencies", "layering violations", "modulari...

Identify missing logging, metrics, tracing, and alerting for production services.

Audit the codebase for performance efficiency, the ISO/IEC 25010 characteristic covering time behavior, resource utilization, and capacity. Finds N+1 queries, missing indexes, unbounded operations, blocking I/O in hot paths, algorithmic complexity, and missing backpressure. Use when the user says /audit-performance-efficiency, "performance audit", "find slow code", "resource leaks", "capacity issues", "N+1", or runs a 25010 sweep via /audit-sdlc. Read-only; produces a findings report.

Audit the codebase for portability, the ISO/IEC 25010 characteristic covering adaptability (runs in different environments), installability (easy to install), and replaceability (easy to swap out or migrate off). Finds hardcoded paths/hosts/OS assumptions, config baked into code (violating 12-factor), vendor lock-in, missing containerization/install tooling, and non-standard data formats that block migration. Use when the user says /audit-portability, "lock-in audit", "12-factor check", "can ...

Audit the codebase for reliability, the ISO/IEC 25010 characteristic covering maturity, availability, fault tolerance, and recoverability. Finds swallowed exceptions, missing timeouts on network calls, missing retries/circuit breakers on external dependencies, non-idempotent operations, missing transaction boundaries, and missing graceful-shutdown and health-check handling. The design-side counterpart to observe-production (runtime) and audit-observability (instrumentation). Use when the user...

Run multiple audit skills against the project and produce a unified findings report with prioritized action items.

Scan the codebase for code-level security vulnerabilities including hardcoded secrets, injection risks, missing auth checks, and insecure patterns, then produce a prioritized remediation plan.

Audit the software's interfaces (CLI, API, and web UI) for usability, the ISO/IEC 25010 characteristic covering recognizability, learnability, operability, user error protection, and accessibility. Finds missing help text, inconsistent flags, poor error messages, missing confirmations on destructive actions, and static accessibility gaps. Use when the user says /audit-usability, "CLI UX audit", "API ergonomics", "accessibility check", "error message quality", or runs a 25010 sweep via /audit-...

Analyze what was done in the current session and surface concrete ways the workflow could have been automated to remove the user from the loop. Use when the user asks /automate-session, "how could this be automated?", or "what could we automate from this session?".

Check a GitHub issue for duplicate issues and existing fix PRs before investing effort.

Determine whether a GitHub issue is already addressed in the codebase by extracting its requested behavior and verifying it against the code. Works for feature requests and bug reports in any format, with or without formal acceptance criteria. Use before starting work on an issue, or to triage stale issues, to avoid implementing or fixing something that is already present. Triggers on "is this issue already done", "is this already implemented", "is this bug already fixed", "check issue status...

Orchestrate check-issue-status across a list of issues to find which are already addressed in the code. Supports checking every open issue in a repository, issues authored by a specific user, or issues matching a custom search query, and these scopes combine. Use to triage a backlog for stale or already-implemented issues, audit a user's open reports, or filter a query before investing effort. Triggers on "check these issues", "which issues are already done", "find stale issues", "batch check...

Detect pull requests someone else linked to the issue being worked on, then offer to continue, stop, or review them. Use mid-flow to avoid duplicating in-progress work and to decide whether to depend on an external PR instead.

Shared guidelines for writing concise, high-signal outbound communication the agent posts or drafts on the user's behalf, covering GitHub PR and issue comments, inline review comments, review reports, thread replies, PR and issue descriptions, Slack messages and announcements, and email. Other skills reference this instead of restating concision and tone rules.

Compare skills between two directories (mine and theirs) to identify best practices from "theirs" that can be adopted into "mine". Produces a prioritized list of improvements with concrete suggestions.

Configure the standard label set in a GitHub repository to match the SDLC labeling conventions used by triage and issue management skills.

Write, update, or revise a high-quality article given a target audience and relevant sources. Use when the user wants to write a new article, update or revise an existing article (to keep tone, structure, and style consistent with prior writing), or improve an article's research, clarity, or flow. Produces a structured, well-researched article tailored to the audience's knowledge level and interests, adding visualizations where they aid comprehension.

Record an assumption made during implementation with its basis, risk, and validation plan.

Design the CLI interface for a feature during requirements creation, covering the command tree, commands, options, arguments, exit codes, output behavior, and example terminal sessions that demonstrate the intended experience. Use when a feature adds or changes CLI commands or options, when requirements mention a CLI, or when /create-requirements delegates its CLI surface.

Analyze the existing internal code and architecture a feature will touch, extend, or replace, and assess each part's changeability (reuse, extend, refactor, replace) with rationale, risk, and migration impact.

Record an architectural or implementation decision with context, alternatives considered, trade-offs, and consequences.

Create a GitHub Discussion (for example a feature request in a repository that routes them to Discussions instead of issues) with background, prioritized acceptance criteria (Must/Should), and a justified time budget.

Create documentation for a feature or component following the Divio documentation framework (tutorials, how-to guides, reference, explanation).

Capture the entities, relationships, glossary, invariants, and key quantities of a domain so it is understood structurally before solutioning. Use when the user says /create-domain-model, "model this domain", "what are the entities here", "I do not understand this problem space", or enters an unfamiliar domain during design or architecture work. A standalone skill invoked as a one-off, typically during the design or architecture process.

Survey existing solutions (libraries, products, internal code, standards, prior art) that address the requirements, evaluate their fit, and recommend whether to adopt, extend, or build.

Assess technical, financial, and operational viability of a feature before committing to requirements.

Define project goals, objectives, key results, and KPIs so features align to measurable outcomes.

Implement a feature or task following the specification and plan, producing working, tested code.

Create a GitHub issue with background, prioritized acceptance criteria (Must/Should), and a justified time budget.

Capture learnings after completing a feature, sprint, or project in a structured retrospective format.

Document how resources evolve over time and what causes them to change, covering states, transitions, invariants, and retention.

Create any Mermaid diagram (flowchart, sequence, class, state, ER, C4, architecture, gantt, mindmap, timeline, pie, sankey, and 20+ more) from a description or source material. Use when the user says "diagram", "visualize", "mermaid", "draw a flowchart", "sequence diagram", "ER diagram", "mindmap", "gantt chart", or asks to document architecture, processes, data flows, or relationships as a diagram. Covers selecting the right diagram type, correct syntax, validation, and delivery into Markdow...

Improve a message the user wants to send by removing negative tone, providing positive formulation, and adding actionable suggestions when relevant.

Create UI mockups, wireframes, and screen designs for a feature from its specification, so the visual and interaction design is settled before implementation.

Evaluate whether a proposed feature addresses a genuine need before investing in feasibility or requirements, examining the problem, stakeholders, alternatives, and cost of inaction.

Define logging, metrics, tracing, and alerting for a feature so production health can be monitored from day one.

Create a placeholder GitHub issue for a pending SDLC feature (one created without an issue, with a p-prefixed directory) and promote it to issue-driven form by renaming its directory and rewriting FEAT- cross-references. Use when the user says /create-placeholder-issue, wants to promote a pending feature, wants to back an existing SDLC feature with a GitHub issue, or wants to convert a p-prefixed feature directory into an issue-numbered one. For starting top-down from a feature request, use c...

Create an implementation plan with phases, milestones, dependencies, and risks from a specification or requirements document.

Generate a PR description based on changes. If a repository/issue is provided, use its description to assess issue completeness.