claude

contributing

How a contribution to a repository is written up: pull requests, decision records, requirements, changelogs and release notes.

0 on GitHubby Luis Burgosv0.4.0MITupdated 1 month agoengineering
/

Plugin contributing from marketplace luisburgos in luisburgos/skills. Commands read from the repo's manifest — 1 month ago.

What it installs

Skills (20)

  • drafting-release-notes

    Draft curated GitHub Release notes for an existing tag — themed sections, PR and commit references, a collapsible full commit list, a compare link — as a draft the user approves before it goes public. Use when the user wants to cut a GitHub release, write notes for a tag or version, publish a releas

  • generating-changelogs

    Generate a release's CHANGELOG.md entry from Conventional Commits with conventional-changelog, in the version bump, or set a repository up to do so. Use when bumping a version or a build number, adding a changelog to a repository, "update the changelog", "generate the changelog", backfilling entries

  • writing-adrs

    Write or review an architecture decision record, and check first that the decision needs one. Use when recording a decision, writing or reviewing an ADR, or before creating a file where the repository keeps its decision records, often docs/adr/. Also use when a repository has no decision records yet

  • writing-prds

    Draft, fill in or review a product requirements document: what a part of the product does, its flows, edge cases and acceptance criteria. Use when writing a PRD, starting a new effort, "draft a spec", reverse-engineering a PRD from something already built, or before creating a file where the reposit

  • writing-pull-requests

    Write or rewrite a pull request description, and check first that the change is one pull request rather than several. Use when opening a pull request, filling in a pull request template, splitting a change into pull requests, or reviewing a description before it goes out. Also use when a repository

  • drafting-store-notes

    Draft the store copy for a mobile release: the Google Play release notes (en-US and es-419 by default, 500 characters each) and the TestFlight "What to Test" text, from the release's CHANGELOG.md entry, approved in conversation before any file is written. Use when "generate the store notes", "draft

  • assessing-cycle-goals

    Measure a cycle against the goals it started with, score the estimates that were made, and close the cycle by appending to history.

  • collecting-cycle-data

    Collect what actually happened in a cycle — git across the configured repos, plus an optional task export — into the cycle's primary record.

  • configuring-cycle-tracking

    One-time setup for cycle tracking — writes the config and an empty history so the first cycle can begin.

  • naming-skills

    Name a new skill, or audit existing skill names against this repo's taxonomy. Use when choosing what to call a skill or renaming one, or when checking a tree of skills for naming drift. Also use when another skill needs the taxonomy to justify a name it is producing.

  • reaim

    Set the coming cycle's goals — draft 3 to 5 goals with theory and practice confidence estimates, carry or drop what did not land, and force a decision on anything unlikely to actually happen. A thin facade over setting-cycle-goals.

  • recap

    Close out a finished cycle's record — collect what happened into the primary record, then optionally write the readable review. A thin facade over collecting-cycle-data and writing-cycle-review.

  • recheck

    Close a finished cycle against the goals it started with — judge each goal, score the estimates, write the assessment, and freeze the cycle into history. A thin facade over assessing-cycle-goals.

  • reviewing-cycle-trends

    Read across many cycles for the patterns a single cycle cannot show — carried goals, estimate calibration, and gaps in the record.

  • setting-cycle-goals

    Draft the next cycle's goals, each with the plan that would produce it and theory and practice confidence estimates of that plan, and force a decision on any goal you are unlikely to actually do.

  • weekly-cycle-model

    The shared model of the weekly cycle — the sequence, the artifact contract, and the rules every cycle skill obeys. Read before running any of them.

  • writing-cycle-review

    Write the readable narrative of a cycle — charts and prose over the collected data, for the person who lived it.

  • auditing-ui-blueprint-implementations

    Audit an existing component or page implementation against its blueprint, and report each gap with where its fix starts.

  • deriving-component-blueprints

    Derive a stack-agnostic component blueprint from a mockup or from existing code.

  • deriving-ui-page-blueprints

    Derive a stack-agnostic page blueprint from a mockup, naming the components it is built from and the data it shows them.

View source on GitHub

More from luisburgos/skills

All 4 plugins →

Personal workflow and skill authoring: the weekly cycle, and naming skills.

20 skills

0

mobile

claude

Releasing a mobile app to Google Play and TestFlight, whatever it is built with: the store copy for a release.

20 skills

0

ui

claude

Stack-agnostic UI blueprints, for web or mobile: deriving component and page blueprints from a mockup, and auditing an implementation against them.

20 skills

0

Similar plugins

Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).

39 skills

mattpocock/skills 323,108

agents-md

claude

AGENTS.md as project instructions, by one option. Under claude-md-or-agents-md a project with no instruction files of its own gets its AGENTS.md files instead: a prompt.context hook asks $.fs.ancestors for every AGENTS.md and .claude/AGENTS.md from the filesystem root down to the working directory and hands them to the engine as project instruction files, which it renders, announces and withholds from agents exactly as it does CLAUDE.md, skipping any file the engine already loaded by import or link; a tool.call hook on Read attaches the ones under the project root as the engine attaches a nested CLAUDE.md. Under claude-md-and-agents-md every AGENTS.md is loaded beside CLAUDE.md. Under managed-only the project's and the person's instruction files are dropped and the organization's managed ones kept. Under claude-md the engine's walk stands alone. claude-md-or-agents-md is the default.

anthropics/claude-code 155,476

agent-skills

claudecodex

Production-grade engineering skills covering every phase of software development: spec, plan, build, verify, review, and ship.

25 skills · 4 agents

addyosmani/agent-skills 116,782

Agentic QE (external: maintained in proffesor-for-testing/agentic-qe, pinned to v3.15.17): a quality-engineering fleet with 11 QE agents, 9 skills, 9 commands, the agentic-qe MCP server pinned to the plugin version, and the aqe-mod guard that refuses destructive operations on AQE learning data

9 skills · 9 commands · 11 agents · 1 MCP server

ruvnet/ruflo 81,589

Install the "AAS Security Engineer" workflow plugin from Agentic Awesome Skills.

12 skills

sickn33/agentic-awesome-skills 49,620

Binary reverse engineering, malware analysis, firmware security, and software protection research for authorized security research, CTF competitions, and defensive security

4 skills · 3 agents

wshobson/agents 42,461

Maintain contributing?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins4 plugins