nlsmdn

Skills

45 in the Claude listing

• Blind spotsSurface consequential decisions a plan, design, or research brief left silently assumed, by interviewing the user in dependency order.
• Check agent logsSearch past Claude Code, Codex, Droid, OpenCode, and Pi session logs to recover context from earlier work across the current project and sibling checkouts.
• Code reviewClean up code comments, then review code with comprehensive and quick modes.
• commitCommit ONLY the changes this session made, never another agent's work in the same checkout.
• Debug logAdd debug logging to trace code execution.
• deslopCopy-edit text to strip AI/LLM writing tells ("slop") and make it read as human-written — overused words (delve, showcase, robust), significance-inflation phrases ("stands as a testament to", "plays a
• docAssess documentation for gaps, staleness, quality, and files outside the defined doc set.
• Evaluate techStructured evaluation before adopting a library, tool, or hosted service — enumerate candidates wide, then score every one against an identical rubric where maintenance health is a mandatory gate, not
• explainGenerate project explanation docs in docs/explain/ covering architecture, flows, syntax, system APIs, infra, and testing, or explain a code diff, commit, branch, or PR directly in the conversation wit
• guideWalk the user through a multi-step task (e.g.
• Hard fixEscalation workflow for stubborn bugs.
• huhExpand an explanation with the surrounding context needed to understand it.
• ideationGenerate ideas with structure when you're stumped — on what to build next, what the real problem is, or how to solve it.
• Improve agent instructionsAudit and improve the always-loaded agent instruction files (AGENTS.md, CLAUDE.md, GEMINI.md).
• Library docsGenerate and refresh a per-repo `library-use` reference — official docs, changelog links, pinned versions, and distilled correct-usage conventions for the repo's fast-moving / niche libraries.
• longshotRun a long autonomous build session from a brief — interview the user with `blind-spots`, prepare the plan, and wait for explicit final approval to start implementation.
• pdfRead, extract, merge, split, rotate, watermark, create, fill forms, encrypt/decrypt, or OCR PDF files.
• Perf testSet up and run performance tests (profiling, load testing, or E2E scenarios), preserving occasional manual procedures and results for future repetition.
• planLightweight planning workflow — delegate read-only planning to an Opus subagent, then implement in auto mode after a single go-ahead gate.
• Pre existingFix any test/lint/type/build/CI failure instead of dismissing it as pre-existing, flaky, or unrelated.
• qaExercise a developed feature through its real user or consumer interface, enumerate paths and edge/error/loading states first, and report evidence and coverage.
• Read docsSearch internal project docs (docs/, README.md, CLAUDE.md, *.md) for patterns, conventions, architecture.
• Release reviewRun a comprehensive pre-release review of a whole product, working through every command, parameter and config surface with the user, one item at a time.
• Research generalResearch a non-technical topic online (science, history, news, policy, regional/regulatory, consumer purchases, personal decisions, fact-check).
• Research techResearch any technical / developer topic online — libraries, errors, best-practice/how-to, tool·library·model comparisons, product capabilities, and ecosystem/community signal.
• Resolve conflictsResolve git conflicts from any operation (merge, rebase, cherry-pick, stash, revert).
• Review architectureReview system architecture — layering, module boundaries, coupling/cohesion, pattern fit, quality attributes (scalability, resilience, evolvability), and architectural smells.
• Review cleancodeReview code for clean-code principles — SOLID, DRY, YAGNI, KISS, code smells.
• Review commentsReview and clean up code comments for necessity, accuracy, non-duplication, clarity, and concise explanation of rationale.
• Review functional
• Review historyAnalyze how code changed over time.
• Review interfacesReview interface design for functions, classes, modules, components — naming, params, encapsulation, YAGNI, usability.
• Review library useReview code for correct use of the repo's third-party libraries — checks the scoped files against the version-specific conventions recorded in the repo's `library-use` reference (docs-derived correct-
• Review logsAnalyze Claude Code session transcripts for failure patterns and suggest fixes.
• Review perfPerformance analysis for algorithmic complexity, memory leaks, N+1 queries, and render issues.
• Review planMulti-agent review of implementation plans.
• Review productReview a product from the user's perspective — build/refine a user persona, map their use cases (jobs-to-be-done), then audit the product for friction, gaps, and things to add or change.
• Review securitySecurity audit for vulnerabilities, secrets, and unsafe patterns.
• Review todoTurn a completed code review into a persistent workflow that immediately proposes the complete ordered implementation plan, waits for whole-plan approval, then implements and commits every accepted fi
• Second opinionGet external AI opinions on a problem or question.
• Skill creatorGuide for creating or improving Claude skills.
• Squash commitsSquash unpushed commits into clean, higher-level feat/fix/chore commits that follow the project commit policy.
• statusReport the current coding-session status: summarize staged, unstaged, and untracked files; identify the last task and whether its work is present or committed; report code-review coverage; summarize a
• tempMake temporary code changes for testing that can be easily undone.
• testAssess test state and run the right action (default, no args): run the suite, then find failures, coverage gaps, and quality issues and route into fix, generate, or review.