agent-skills

Runs the conversational clarification layer for workflow orchestration. Use for plan-wide upfront clarification or task-level pre-execution critique while delegating artifact analysis, manifest assembly, and file updates to bundled subagents.

This skill embodies the principles of "Clean Code" by Robert C. Martin (Uncle Bob). Use it to transform "code that works" into "code that is clean."

Master effective code review practices to provide constructive feedback, catch bugs early, and foster knowledge sharing while maintaining team morale. Use when reviewing pull requests, establishing review standards, or mentoring developers.

Implement proven backend architecture patterns including Clean Architecture, Hexagonal Architecture, and Domain-Driven Design. Use this skill when designing clean architecture for a new microservice, when refactoring a monolith to use bounded contexts, when implementing hexagonal or onion architecture patterns, or when debugging dependency cycles between application layers.

Produces a verified, read-only snapshot of a repository's recent state from local Git evidence: what changed, what is risky, and whether a branch is ready to continue, review, merge, or hand off. Use when asked what changed recently, what happened on this branch, where things stand, whether the branch is ready, or how to resume work from the current repo state. Does not review code line by line or draft PR feedback (use review-pull-request), and does not write a handoff file from conversation history (use generate-handoff-document). Runs no tests, merges, or repository mutation; writes no file and returns the snapshot as response text.

Implement secure API design patterns including authentication, authorization, input validation, rate limiting, and protection against common API vulnerabilities

Creates reviewable atomic git commits from an explicit list of files or folders after the user asks, in words, to commit. Use when the user says commit these files, commit only src/x, split my changes into atomic commits, commit the ticket work, or keep unrelated work out of the commit. Shows the exact commit plan for approval before any commit and preserves unrelated staged and unstaged work. Does not push, amend, or rewrite history. Does not open pull requests (use pr-creator). Does not summarize recent project state (use analyzing-recent-project-state).

Runs a structured nine-seat council deliberation on an idea, project, business, startup, goal, or objective, then writes a full decision handoff file with a compact recommendation summary and reusable mental-model teaching cards. Use when a user asks to stress-test a decision, get adversarial review, classify a decision as reversible or irreversible, or wants multiple independent perspectives on a course of action.

Creates or reconciles GitHub child task issues or Jira subtasks from an approved Phase 4 task plan, then updates docs/<KEY>-tasks.md with validated remote linkage. Use after the task plan has been clarified and the user has approved the exact platform writes plus scoped plan-file update. Does not plan tasks, implement code, commit changes, or mutate unrelated tracker state.

Diagnoses runtime bugs, crashes, regressions, failing CI/CD pipelines, and underspecified user reports through read-only, evidence-first root-cause analysis with traceable reports and bounded subagent workflows.

Use when you have a written implementation plan to execute in a separate session with review checkpoints

Executes exactly one planned Jira or GitHub work-item task after critique approval. Use when a numbered task should move through kickoff, implementation, documentation, requirements verification, clean-code, architecture, and security gates, targeted fix cycles, tracker finalization, and a final report without continuing to the next task. Does not plan tasks or select the next task.

Retrieves a Jira ticket or a GitHub issue into docs/<KEY>.md as a read-only, validated Markdown snapshot for downstream workflow phases. Use when a Jira URL, a GitHub issue URL, or owner/repo/number coordinates need the Phase 1 fetch-work-item step. Detects the platform from the input and loads the matching playbook just-in-time.

Creates, refines, repairs, or decomposes Markdown plus Mermaid workflow diagrams (flowchart or stateDiagram) with explicit approval gates, staged writes, empirical Mermaid validation, and compact run reports. Use when generating process flows, Mermaid flowcharts or state diagrams, agent operating procedures, human-in-the-loop gate maps, or decomposing a skill package flow diagram.

Generates or updates a resumable cold-start handoff package from an in-progress conversation, review, debugging session, or investigation, with transcript materialization, verified structured artifacts, update-mode backups, and bounded review repair. Use when the user says create a handoff doc, save this for later, document what we found, update the resumption file, or prepare a fresh agent to resume without chat history.

Refines raw ideas into sharp, actionable concepts through structured divergent and convergent thinking. Use when an idea is still vague, when you need to stress-test assumptions before committing to a plan, or when you want to expand options before converging on one. Triggers on "ideate", "refine this idea", or "stress-test my plan".

Adversarially audits and improves existing first-party agent-skill packages through approval-gated edits, focused subagent reports, baseline diff validation, and outcome-dependent evidence preservation. Use when improving, hardening, or repairing a skill definition, subagent architecture, flow diagram, package hygiene, or prompt sufficiency.

Improve existing test suites into minimal, high-signal behavior-focused harnesses with approval-before-mutation, conformance checks, guarded validation, bounded repair, and auditable handoff statuses. Use when asked to improve, trim, rewrite, delete, review, or harden tests around public contracts, business logic, schemas, security behavior, failures, edge cases, readability, or maintainability.

Extracts what the user actually wants instead of what they think they should want. Achieves this through one-question-at-a-time interview until ~95% confidence about the underlying intent. Use when an ask is underspecified ("build me X" without "for whom" or "why now"), when the user explicitly invokes ("interview me", "grill me", "are we sure?", "stress-test my thinking"), or when you catch yourself silently filling in ambiguous requirements before any plan, spec, or code exists.

Validates answers that depend on current external facts, including prices, versions, policies, rankings, recommendations, documentation, and availability. Use when the user asks for current, latest, verified, fact-checked, or up-to-date answers. Coordinates recency-checker and claim-verifier subagents to produce a current, qualified final answer.

Coordinates consent-gated, evidence-isolated, behavior-preserving simplification refactors. Use when simplifying, splitting, renaming, moving, deduplicating, or clarifying existing code while preserving the canonical protected surfaces.

Review one Jira or GitHub work item for implementation readiness and produce one tracker-facing refinement comment or draft. Use when asked to refine, review, assess, or prepare a Jira ticket, Jira epic, GitHub issue, or GitHub epic-style parent issue; optionally post the exact approved comment after preview, authorization, tooling, and idempotency gates pass.

Assess and respond to pull request review comments through a status-gated workflow: collect comments, evaluate feedback, draft replies, write a verified local report, and optionally post exact approved replies to supported GitHub review-comment threads.

Coordinate an end-to-end Jira or GitHub work-item workflow from initial fetch through per-task implementation. Use this skill when the user provides a Jira ticket URL, a GitHub issue URL, owner/repo/issue coordinates, says "work on ticket PROJECT-123", "work on issue owner/repo#42", "resume <work-item-key>", "continue this workflow", or asks for status without naming a specific phase. This top-level coordinator detects the platform from the input, loads the matching playbook just-in-time, keeps SKILL.md as a routing layer, and dispatches execution-heavy work to downstream skills or co-located utility subagents.

Plan a codebase restructuring through read-only architecture mapping, DDD and Screaming Architecture analysis, reference quarantine, bounded review repair, and a persisted decision report. Use when a user wants an evidence-backed restructuring plan without implementing file moves or refactors.

Plans how to execute exactly one already-selected numbered Jira or GitHub task by producing an execution brief, implementation plan, behavior-oriented test specification, and scoped refactoring recommendation. Use for Phase 5 task-execution planning with a workflow key and TASK_NUMBER. Does not decompose the parent work item, plan multiple tasks, implement code, or advance to the next task.

Plans a Phase 1 Jira ticket or GitHub issue snapshot into staged, validated Phase 2 task-plan artifacts with deterministic branch names. Use when an orchestrator or user asks to decompose docs/<KEY>.md, plan Jira tasks, plan GitHub issue tasks, or re-plan a work item after critique. Does not fetch work items, create subtasks or child issues, implement tasks, or mutate the work-item platform.

Forces the laziest solution that actually works, simplest, shortest, most minimal. Channels a senior dev who has seen everything: question whether the task needs to exist at all (YAGNI), reach for the standard library before custom code, native platform features before dependencies, one line before fifty. Supports intensity levels: lite, full (default), ultra. Use on ANY coding task: writing, adding, refactoring, fixing, reviewing, or designing code, and choosing libraries or dependencies. Also use whenever the user says "ponytail", "be lazy", "lazy mode", "simplest solution", "minimal solution", "yagni", "do less", or "shortest path", or complains about over-engineering, bloat, boilerplate, or unnecessary dependencies. Do NOT use for non-coding requests (general knowledge, prose, translation, summaries, recipes).

Create review-ready pull requests or merge requests from the current branch through a fork-aware, idempotent, preview-first, user-approved workflow. Use when the user asks to create, open, draft, or submit a PR, pull request, merge request, or code review request, or says their branch is ready for review.

Convert prose prompts into compact, structured XML prompt contracts through staged passes. Use when a user asks to structure, harden, formalize, debug, revise, or convert a prompt; mentions XML tags, agent drift, ambiguity, hidden assumptions, success criteria, anti-patterns, autonomous prompts, or prompt suites; or provides natural-language instructions that need to become a reliable agent contract.

Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation

Review one pull request through a standalone, progressively disclosed workflow. Use when the user asks to review a PR, audit a pull request, prepare GitHub review comments, draft request-changes feedback, write a PR review file, or optionally post approved review comments. This skill handles exactly one PR; ask the user to choose one PR when multiple PR URLs are supplied.

Reviews and tailors a software engineer CV or resume against a job posting. Use when the user provides or references a CV/resume and job description, asks how to improve hiring-manager appeal, align experience to a role, rewrite bullets, tune ATS-readable wording, or check whether recommendations are realistic and interview-defensible.

Rewrite existing Python, TypeScript/JavaScript, or Go code for strict static typing, boundary validation, and maintainable idioms while preserving behavior. Use when the user asks to harden code, remove unsafe escape hatches, add validation, or align with mypy, Pyright, tsc, go vet, or Staticcheck. Coordinates baseline mapping, strategy, approved implementation, and review through co-located subagents and just-in-time language references.

Creates specs before coding. Use when starting a new project, feature, or significant change and no specification exists yet. Use when requirements are unclear, ambiguous, or only exist as a vague idea. Use when a single requirement spans several independently testable capabilities and needs decomposing into a capability map of modules before specifying.

Remove AI writing patterns from prose. Use when drafting, editing, or reviewing text to eliminate predictable AI tells.

Use when executing implementation plans with independent tasks in the current session

Use when implementing any feature or bugfix, before writing implementation code

Cut AI tells from any writing. Must always apply.

Audits an implementation plan for requirements traceability, avoidable complexity, risky assumptions, and evidence gaps. Use when reviewing an AI-generated or human-authored plan, design proposal, implementation outline, task breakdown, or architecture plan and the user wants a standalone audit report without overwriting the source plan.

Vitest fast unit testing framework powered by Vite with Jest-compatible API. Use when writing tests, mocking, configuring coverage, or working with test filtering and fixtures.

Converts repeatable workflows, existing prompts, or skill packages into portable agent-skill artifacts or review reports with staged writes, bounded review repair, resume packets, and canonical validation. Use when creating, extending, refactoring, or reviewing skills for Claude Code, Cursor, OpenCode, or Agent Skills-compatible runtimes.

Use when you have a spec or requirements for a multi-step task, before touching code