xp-developer-skills

In the author's own words, from each skill's SKILL.md.

• atdd

  Pragmatic Acceptance Test-Driven Development — agree concrete examples with stakeholders (Discuss), capture them as executable acceptance checks (Distill), then implement with outside-in delivery (Develop). Works in two modes — API-only (HTTP/CLI/event/in-process seam, the default) or E2E (browser, full stack, Page Objects) — with Gherkin/Cucumber when it helps, code-first acceptance tests, and c…

  skills/atdd/SKILL.md on GitHub (opens in a new tab)

• bugfix

  Use when fixing bugs, regressions, failing tests, or unexpected behavior. Applies a strict test-first bugfix workflow with minimal safe changes, isolated commits, and language-agnostic verification strategies.

  skills/bugfix/SKILL.md on GitHub (opens in a new tab)

• increment-review

  Fast, single-pass review of one just-finished increment — target under 60 seconds of work. Reads the new-increment mini-journal and that increment's diff only, checks against docs/code-review.md, and returns approved / changes-requested / bug-found with a short targeted fix brief. This is the default reviewer new-feature invokes after new-increment — not skills/refactoring directly. Use immediate…

  skills/increment-review/SKILL.md on GitHub (opens in a new tab)

• legacy-testing

  Michael Feathers–style legacy code change — treat code without automated tests as legacy, then follow identify change points, find test points, break dependencies, add tests (often characterization), and only then modify or refactor. Covers seams (object/link/preprocessing), sensing vs separation, fakes/mocks, sprout/wrap, pinch points, effect sketches, and dependency-breaking patterns. Composes…

  skills/legacy-testing/SKILL.md on GitHub (opens in a new tab)

• montecarlo-epic

  Previsione Monte Carlo per UN gruppo di work item (epic, progetto, iniziativa, release) — "quando finiamo questi N item?" e, opzionalmente, "quanti item completiamo entro una scadenza?". Campiona il throughput storico (periodi a zero inclusi) per 10.000+ trial e restituisce date con probabilità 50/70/85/95. Usala per un solo gruppo; per un solo item usa montecarlo-single-item, per più gruppi in s…

  skills/montecarlo-epic/SKILL.md on GitHub (opens in a new tab)

• montecarlo-epics

  Previsione Monte Carlo per una LISTA ORDINATA di gruppi (epic, progetti, iniziative) lavorati uno dopo l'altro — "quando finisce ciascun gruppo della roadmap e quando finisce tutto?". In ogni trial campiona il throughput in modo continuo lungo tutta la sequenza e registra quando si raggiungono i conteggi cumulativi, così ogni gruppo ha la sua distribuzione di fine senza sommare percentili. Usala…

  skills/montecarlo-epics/SKILL.md on GitHub (opens in a new tab)

• montecarlo-single-item

  Previsione per UN singolo work item (card, ticket, storia, bug) — "quando sarà pronto questo item?". Usa la distribuzione storica dei cycle time (o lead time) e restituisce una Service Level Expectation con percentili 50/70/85/95, anche per un item già in corso. Non simula il throughput. Usala quando la domanda riguarda un solo item; per un gruppo/epic usa montecarlo-epic, per più gruppi in seque…

  skills/montecarlo-single-item/SKILL.md on GitHub (opens in a new tab)

• new-feature

  Slice a whole capability into ordered releasable increments (increment backlog in increments/<stem>.md). Delegate each slice to skills/new-increment, review via skills/increment-review — do not implement slices or review them yourself. Confirms the plan before executing (wait in step mode, ~2min pause in automatic). Default step mode stops after each increment for feedback; automatic mode (explic…

  skills/new-feature/SKILL.md on GitHub (opens in a new tab)

• new-increment

  Deliver one releasable increment from increments/<feature>.md — strict TDD by default (one test-lists/<feature>.md, unit tests). ATDD only when a real outer seam exists (API/UI/contract). One increment per invocation; RED before GREEN; all project verify steps green before done; commit then stop. Not for whole-feature planning (skills/new-feature).

  skills/new-increment/SKILL.md on GitHub (opens in a new tab)

• refactoring

  Martin Fowler–style refactoring — change the internal structure of code without changing observable behavior. Baby steps on a green baseline: one mechanical transformation at a time, tests stay green, revert on red. Also executes an increment-review fix brief, or runs the legacy manual post-increment review mode on direct user request (explain commits, suggest small in-scope refactors/tests) — sk…

  skills/refactoring/SKILL.md on GitHub (opens in a new tab)

• spike

  XP-style spike — time-boxed experiment on an isolated branch; code is disposable. Answer one technical or design question (feasibility, library fit, performance bound, integration). Use automated checks only when they help prove the goal — no delivery test pyramid, no ATDD/TDD discipline on the spike branch. Explicit promotion to skills/atdd, skills/tdd, or skills/legacy-testing when learning is…

  skills/spike/SKILL.md on GitHub (opens in a new tab)

• tdd

  Applies strict Test-Driven Development with a repo-local Markdown test list (default `test-lists/<slug>.md` unless the project defines another folder), Robert C. Martin’s Three Laws, deterministic tests and stable seams (unit vs narrow integration), Arrange–Act–Assert test shape, micro-iterations, refactor proximity (production and test code), fast feedback, and git micro-commits (`test:` / `feat…

  skills/tdd/SKILL.md on GitHub (opens in a new tab)

• tweak

  Small, targeted change to the feature already on the current branch — copy/text, a color or style, a small logic change, or a small new file. Scoped edit, scoped tests, scoped lint, one commit on the current branch. No increments file, no feature branch, no PR. Use for a quick follow-up tweak right after new-feature/new-increment finished, not for a new capability or a multi-file feature (use ski…

  skills/tweak/SKILL.md on GitHub (opens in a new tab)

No skill matches that filter.

Similar skills

• reaby morluto Reverse engineer anything with agents, from app behavior down to native binaries. 431k stars · 5 skills
• skillsby mattpocock Skills for Real Engineers. Straight from my .agents directory. 313k stars · 30 skills
• superpowersby obra An agentic skills framework & software development methodology that works. 312k stars · 15 skills
• ECCby affaan-m The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Cod… 297k stars · 30 skills
• andrej-karpathy-skillsby multica-ai A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls. 230k stars · 1 skill
• skillsby anthropics Public repository for Agent Skills 187k stars · 19 skills