alexmond

84 mods across 2 repositories, 10 stars between them.

alexmskills

01

alexmond/alexmskills

Plugin Claude Code

A curated marketplace of reusable, self-improving Claude Code skills and agents. Each skill is an independently versioned plugin.

6 yesterday A tokens not measured original MIT

alexmskills

02

alexmond/alexmskills

Settings file Claude Code

Agent settings configuring enabledPlugins.

6 yesterday A tokens not measured copy · 100% MIT

alexmond/alexmskills

Instructions file

Instructions for alexmond/alexmskills, covering alexmskills, layout, catalog (see readme for descriptions), conventions and gotchas (load-bearing).

6 yesterday B 5,570 tokens original MIT

brainstorm-panel

04

alexmond/alexmskills

Plugin Claude Code

Assemble a task-specific panel of role-specialized agents and run a generate-critique-refine loop until the work converges on a strong result.

6 yesterday A tokens not measured original MIT

brainstorm-panel

05

alexmond/alexmskills

Skill Claude CodeCodex

Given targeted work — a problem, a deliverable to improve, an idea to develop — assemble the right panel of role-specialized agents, pick a coordination style suited to the task, and run a generate-critique-refine loop until it converges. The skill picks the team and process from the work itself. Use when the user…

6 yesterday A 125 tokens original MIT

dev-crew

06

alexmond/alexmskills

Plugin Claude Code

A self-evolving delivery crew: it composes a task-fit roster of role subagents (each on its own model tier) and runs them as a gated relay to deliver a target, with editable rosters and a per-repo learning loop. architect → dev → qa → deployer is just one example lineup.

6 yesterday A tokens not measured original MIT

dc-architect

07

alexmond/alexmskills

Agent

Use this agent for the architect phase of a dev-crew run. Invoke before any implementation on features, refactors, schema changes, or anything touching more than one module. Reads the task brief and codebase; produces the plan and the interface/done-criteria contract the rest of the crew builds against.

6 yesterday A 66 tokens original MIT

dc-deployer

08

alexmond/alexmskills

Agent

Use this agent for the release phase of a dev-crew run, only after qa returns an overall PASS. Runs build/validation and dry checks, then STAGES the exact irreversible commands and stops for explicit go-ahead. Never auto-executes a deploy.

6 yesterday A 57 tokens original MIT

dc-dev

09

alexmond/alexmskills

Agent

Use this agent for the implementation phase of a dev-crew run. Invoke after the architect has produced CONTRACT.md, or directly for small bugfixes. Reads the plan and contract; writes the code and a verification handoff for qa.

6 yesterday A 51 tokens original MIT

dc-lead

10

alexmond/alexmskills

Agent

Use this agent for deep root-cause or multi-system investigation in a dev-crew run — stubborn, ambiguous, or circling failures that span subsystems, or a bugfix/debug loop that has already exceeded two passes. Reads the symptom and the codebase; produces a diagnosis and a contract the dev role can implement.

6 yesterday A 69 tokens original MIT

dc-qa

11

alexmond/alexmskills

Agent

Use this agent for the verification phase of a dev-crew run, after dev has written CHANGES.md. Reads the contract and the changes; writes/runs tests and returns a pass/fail verdict per done-criterion. Read-only on source so it can't rewrite what it's checking.

6 yesterday A 61 tokens original MIT

dc-scout

12

alexmond/alexmskills

Agent

Use this agent when dev-crew initializes in a repo (first run in a repo, or on "re-profile") to scan the project and produce its profile: languages, build tool, frameworks, test and static-analysis stack, CI, deploy targets, and conventions. Read-only and cheap. Writes /.claude/dev-crew/PROFILE.md, which drives…

6 yesterday A 93 tokens original MIT

PreToolUse

13

alexmond/alexmskills

Hook

Runs before the agent uses a tool for Task tool calls, executing check-handoffs.py via python3. From alexmond/alexmskills.

6 yesterday A tokens not measured original MIT

dev-crew

14

alexmond/alexmskills

Skill Claude CodeCodex

Use this to take a delivery task through a task-fit roster of role subagents — composed for the work and run as a gated relay (architect -> dev -> qa -> deployer is one example lineup; the roster is dynamic), where each role runs as a subagent on its own model tier. Trigger on "run the crew on", "ship this feature"…

6 yesterday A 159 tokens original MIT

evolving-claude-md

15

alexmond/alexmskills

Plugin Claude Code

Turn CLAUDE.md into a living Decisions & Learnings log that stays bounded: a format contract enforced at write time by a PreToolUse lint, four downward pressures (strike-through, merge, graduation, quarterly archive), staleness detection against the tree, and a tree-grounded coverage check for the essentials a file…

6 yesterday A tokens not measured original MIT

evolving-claude-md

16

alexmond/alexmskills

Skill Claude CodeCodex

Set up CLAUDE.md to maintain a living Decisions & Learnings log that stays bounded as the project evolves — a format contract enforced at write time, four pruning pressures, and a coverage check for the essentials. Use when the user says "make CLAUDE.md evolve", "self-updating CLAUDE.md", "add a learning mechanism to…

6 yesterday A 177 tokens original MIT

implement-issue

17

alexmond/alexmskills

Plugin Claude Code

Drive a GitHub issue from branch to pull request with a language and build-tool agnostic workflow.

6 yesterday A tokens not measured original MIT

implement-issue

18

alexmond/alexmskills

Skill Claude CodeCodex

Drive a GitHub issue from branch to pull request — read the issue, create a feature branch, implement the change, run the project's build and tests, then commit, push, and open a PR. Language and build-tool agnostic. Use when asked to implement, fix, or resolve a GitHub issue by number.

6 yesterday A 69 tokens original MIT

learn-on-failure

19

alexmond/alexmskills

Plugin Claude Code

Automatically captures learnings to per-project memory whenever a task takes more than one fix cycle to resolve.

6 yesterday A tokens not measured original MIT

learn-on-failure

20

alexmond/alexmskills

Skill Claude CodeCodex

Save a learning to project memory. Invoke automatically (without the user asking) whenever a task required more than one fix cycle to resolve — e.g. a test failed and needed a second attempt, a compile error required a correction, an API behaved unexpectedly, or an assumption proved wrong mid-task. Also invoke when…

6 yesterday A 100 tokens original MIT

maven-quality

21

alexmond/alexmskills

Plugin Claude Code

Format, static-analysis, coverage, and pre-commit skills for Maven/Java projects. codestyle (spring-javaformat + Checkstyle), pmd (ruleset, plugin wiring, report triage by priority, CPD, and suppression at the right scope), jacoco (coverage gate + gap analysis), and precommit (all of it before a commit).

6 yesterday A tokens not measured original MIT

codestyle

22

alexmond/alexmskills

Skill Claude CodeCodex

Coding standards and formatting for Maven/Java projects using spring-javaformat and Checkstyle. Use when the user says "fix the code-style violations", "reformat this module", "the build is failing on Checkstyle", or asks what the project's formatting and naming rules are. For PMD static analysis specifically, see the…

6 yesterday A 73 tokens original MIT

jacoco

23

alexmond/alexmskills

Skill Claude CodeCodex

Check JaCoCo code coverage for a Maven/Java project against a gate, then drill into per-module, per-class, and per-line gaps to target tests. Use when the user says "what's our test coverage", "check coverage", "which classes need tests", "are we above the coverage gate", or is planning tests to reach a threshold.

6 yesterday A 75 tokens original MIT

pmd

24

alexmond/alexmskills

Skill Claude CodeCodex

Set up, run, and triage PMD static analysis on a Maven/Java project — the ruleset, the plugin wiring, parsing the report by rule and priority, copy-paste detection, and how to suppress a finding at the right level. Use when the user says "run PMD", "PMD is failing", "fix the PMD violations", "add static analysis"…

6 yesterday A 110 tokens original MIT