agent-plugins

Plugin agent-plugins from marketplace valentin-agent-plugins in ValentinNikolaev/agent-skills. Commands read from the repo's manifest — 3 days ago.

Skills (48)

• ai-detector

  Assess AI-like prose (ai-detector, is-AI), including targeted phrase and structure audits, with improvement advice. A direct human request also runs ChatGPT's detector; calls from other workflows stay local. Not proof of authorship.

• api-and-interface-design

  Design API or module contracts before implementation; not diff review or system-wide architecture review.

• audit-docs

  Audit repository docs read-only for broken links and paths, stale indexes or ADR pointers, duplicate canonical facts, migration gaps, and language or script violations defined by repository policy. Not memory stores, code review, or fixes.

• audit-memory

  Audit an agent memory store read-only for schema or index drift, broken relationships, review-due content or sources, duplicate or conflicting facts, and capacity. Not editing memory or auditing ordinary docs.

• business-viability-assessment

  Assess whether a software product, startup idea, MVP, repository, or PRD is commercially worth building, covering demand, competitors, costs, unit economics, risks, and a GO, VALIDATE_FIRST, PIVOT, or NO_GO verdict. Advisory in chat unless files are requested.

• claude-api

  Build Claude API clients; not Agent SDK, other providers, or read-only review.

• clean-code-comments

  Remove or shorten redundant source-code comments without changing behavior. Use for explicit comment cleanup or dry audits of user-specified files and directories; do not use for general refactoring, documentation generation, or generated-output cleanup.

• code-review

  Review local or PR diffs for defects, including UI/UX and accessibility failures, and test gaps without edits. Route standalone plans, specs, and feedback elsewhere.

• code-simplification

  Simplify existing code while preserving its behavior and contracts. Use for requested refactoring; not read-only review or comment-only cleanup.

• console-ux-design

  Design or improve command-line and console commands (structure, signatures, help, prompts, progress, errors, output, machine formats, automation), including Artisan and Symfony Console. Not GUIs, terminal themes, full-screen TUIs, shell scripting without UX changes, or report-only audits.

• council

  Run independent advisor passes and anonymized peer review for a consequential choice. Use when the user requests a council, debate, or stress test; prefer specialist reviews otherwise.

• create-memory

  Bootstrap the first project-memory baseline from the current repository when no usable memory index exists. Not external imports, routine updates, audits, or replacing a healthy baseline.

• debugging-and-error-recovery

  Diagnose a failing test, build, runtime path, or incident and verify the fix. Use for an observed failure; not a speculative diff review.

• deprecation-and-migration

  Plan or implement a safe API, feature, data, or schema migration. Use when retiring a live contract; not for ordinary code cleanup.

• discussion-reply

  Prepare grounded replies to social-media or forum discussions, from source context through exact-copy review. Not private correspondence, code-hosting replies, original posts, or wording-only edits.

• editorial-writing

  Develop standalone posts or articles from an idea or source through evidence, structure, drafting, and bounded review. Not discussion replies, private correspondence, profile copy, or wording-only edits.

• fastapi-development

  Implement FastAPI APIs and streaming; not diff review or generic Python.

• fix-pr

  Triage existing GitHub PR comments and apply valid minimal fixes; not for a fresh code review.

• github-pages-audit

  Audit a rendered GitHub Pages site or production-equivalent build and report UX and accessibility findings without edits. Use for Pages verification, not source-only review or implementation.

• github-pages-content

  Organize GitHub Pages content, reader tasks, navigation, copy, and local search from verified repository sources. Use for Pages content work, not general product information architecture.

• github-pages-create

  Build or repair GitHub Pages sites from repository evidence. Use for immediate implementation and authorized delivery configuration. Staged proposals and resuming approved GP- IDs belong to github-pages-improve.

• github-pages-design

  Design or refine GitHub Pages direction, composition, tokens, themes, and responsive styling. Use for Pages visual work and critique, not generic product design or a full rendered UX audit.

• github-pages-improve

  Propose GitHub Pages improvements for approval before any edits, then coordinate the approved changes. Use for an explicitly staged workflow and for resuming approved GP- IDs; immediate changes go to github-pages-create.

• go-benchmark

  Measure and compare Go benchmarks or profiles; not PR review or optimization.

• go-security-audit

  Audit Go security across named trust boundaries; not PR review or fixes.

• humanizer

  Humanize existing prose while preserving voice and meaning, including targeted English pattern edits. Not drafting or translation. Use ai-detector for analysis.

• ingest-memory

  Import or refresh durable memory from an explicitly supplied external source (URL, record, document, pasted text, or bounded tree) with provenance. Not bootstrap, routine updates, or audits.

• linkedin-featured-proof

  Plan or create LinkedIn Featured case studies, PDFs, and PNG proof cards from verified work; not profile rewrites or feed content.

• linkedin-profile-optimizer

  Audit or rewrite LinkedIn profiles and role keywords from verified evidence; not CVs, letters, feed posts, or asset files.

• monitor-ci

  Follow a GitHub Actions run to a verified outcome, including required jobs and skipped work.

• php-modernization

  Modernize PHP runtimes, types, or tooling with scoped previews and compatibility checks; not diff review.

• plan-review

  Review an implementation plan for feasibility and gaps without edits. Use review-spec for designs and code-review for diffs.

• planning-and-task-breakdown

  Create an ordered implementation plan with dependencies and observable completion criteria. Use for planning work; not reviewing an existing plan.

• prove-checks

  Verify that a passing test or CI check exercised its target and could detect the claimed failure.

• review-arch

  Review system boundaries and architecture tradeoffs; not line-level code review.

• review-retrospective

  Analyze completed code or prose review runs, verified feedback, upstream misses, timing, and limit usage. Propose project lessons, skill improvements, or model changes without silently applying them.

• review-spec

  Review proposed specifications for feasibility, gaps, and testability; not plans or code conformance.

• test-driven-development

  Implement behavior test-first with red, green, refactor; not auditing existing green checks.

• typescript-type-design

  Implement and test advanced TypeScript types and inference; not diff review or runtime validation.

• update-memory

  Record durable facts from completed project work (decisions, fixes, migrations, milestones) in an existing memory store. Not initial bootstrap, external-source ingestion, audits, or temporary notes.

• uv-project-workflow

  Manage uv dependencies, locks, environments and CI; not unrequested migrations.

• verify-impl

  Trace authoritative spec requirements to existing code evidence; not general diff or design review.

• vet-dependency

  Evaluate a candidate library against this project's required version, behavior, and maintenance evidence.

• wrap-agent-skill

  Import, recover, normalize, or sync reusable skills into canonical sources and generated copies; not project memory.

• write-adr

  Record a specific architecture decision, alternatives, and consequences. Use to write an ADR; not to audit documentation or review architecture.

• write-cover-letter

  Create, tailor, revise, or critique cover, motivation, and job-application letters from job requirements and verified candidate evidence; not CVs, LinkedIn profiles, recommendations, or generic correspondence.

• write-spec

  Draft testable requirements and boundaries for a proposed change. Use to create a specification; not to review one or verify code against it.

• zod

  Implement version-aware Zod schemas and runtime parsing; not diff review or library selection.

Similar plugins