carlkibler

Audit chezmoi dotfiles for drift, unmanaged files, and broken agent skill symlinks across Claude Code, Codex, Gemini, and other harnesses.

Scan Claude/Codex session logs to find agent behavior patterns, Toolsmith adoption gaps, repeated frustrations, and candidates for new skills/tools.

Generate user-facing changelog entries from git history — plain language, audience-segmented, with optional CHANGELOG.md update.

Consolidate/dedupe contacts from macOS, iCloud, Google, Zoho, or VCF with provenance-aware review, backups, and optional approved dossiers.

Capture a technical or product decision with chosen option, rejected alternatives, and rationale — in a format a future agent can read to reconstruct context.

Audit repos for SHA/digest dependency pinning and release cooldowns across Docker, CI, and major language ecosystems; report violations, fix with approval.

Run/triage Django/DRF security smoke checks — settings, throttling, safe HTML, ORM races, model integrity — before shipping or on scanner findings.

Review code through four empathy lenses — user, machine, developer, support — to surface quality issues that pure technical review misses.

Add new functionality by understanding existing patterns and dependencies before writing code. Locates where the feature belongs, studies conventions, implements following precedent, then verifies integration. Use when asked to add a feature, flag, endpoint, component, or module.

Thorough code review using token-efficient context gathering. Analyzes PRs, diffs, or staged changes by checking blast radius, complexity, and dependencies before reviewing the actual code. Use when asked to review a PR, review changes, or do a code review.

Systematically investigate and fix bugs using token-efficient context gathering. Reproduces the issue first, localizes with blame and history, traces the call path, then verifies the fix. Use when asked to fix a bug, investigate an error, or debug unexpected behavior.

Diagnose and fix performance issues by measuring before optimizing. Establishes baselines, identifies bottlenecks through call graphs and complexity analysis, then confirms improvements with numbers. Use when asked to optimize, speed up, reduce memory usage, or fix slowness.

Efficiently explore and understand an unfamiliar codebase using token-lean context gathering. Maps project structure, identifies key files, and builds understanding progressively without reading everything. Use when onboarding to a new project, asked to understand a codebase, or starting work in unfamiliar code.

Migrate frameworks, APIs, or language versions incrementally with verification at each step. Surveys the migration surface, batches work by dependency order, and commits after each verified batch. Use when asked to migrate between frameworks, upgrade major versions, or adapt to new API versions.

Refactor code safely by analyzing blast radius and dependencies before making changes. Covers renaming, moving, extracting, and restructuring code with verification at each step. Use when refactoring, renaming symbols, extracting functions, moving files, or restructuring code.

Upgrade dependencies safely by auditing usage, researching breaking changes, and verifying after upgrade. Scales effort to version jump size — light check for patches, full audit for majors. Use when asked to upgrade, bump, or update a dependency or package.

Long-running iterative development loops with pacing control and verifiable progress. Use when tasks require multiple iterations, many discrete steps, or periodic reflection with clear checkpoints; avoid for simple one-shot tasks or quick fixes.

Long-running iterative development loops with pacing control and verifiable progress. Use when tasks require multiple iterations, many discrete steps, or periodic reflection with clear checkpoints; avoid for simple one-shot tasks or quick fixes.

Build consolidated, consistently-formatted 'falsehoods programmers believe about X' reference docs in the falsehoods repo (~/dev/me/falsehoods). Use whenever the user wants to research, generate, regenerate, or fan out falsehoods/myths/misconceptions documents on a topic (names, addresses, phone numbers, time, unicode, etc.), add a new topic, change the synthesis model or prompt, or produce a new output format from the curated sources. Also use when reviewing or improving the falsehoods pipeline itself.