gitapex

Links

• github.com/tvna/gitapex
• plugin.json (manifest)

Skills · 29

auditing-agent-product-scope

Use when classifying which agent tools, git-hosting platforms, or dependency middleware a repository assumes or targets, and updating that repository's own scope-definition doc to match. Formalizes a research-classify-document procedure: fetch a candidate's primary documentation directly, classif…

battle-testing-a-skill

Use when adversarially stress-testing whether a SKILL.md holds up under hostile or low-quality input, probing a skill file for prompt-injection susceptibility, rubber-stamp or false-pass bias, over-broad mis-routing triggers, and missing rejection or escalation paths, especially to carry that adv…

diagnosing-a-failure

Use to establish why something is actually failing before fixing it, a general-purpose, in-session debugging procedure covering reproduction, boundary-scoped evidence collection, hypothesis testing, and a disconfirmation check, ending in one Diagnosis Verdict handed back to the caller. Never writ…

drafting-a-pr-to-merge

Use when a pull request has just been opened, or has an open CI failure or review thread, before closing the turn. Checks first for a still-executing owner's ownership-signal label and defers without acting if present; otherwise drives the PR through auto-subscribe, fix, review-thread resolution vi…

drafting-a-skill

Pipeline-only task, dispatched by executing-a-branch-plan (Step 6, agentType branch-plan-task) for a brand-new or existing SKILL.md, or by scorer-gated-skill-edits's own Step 3 for one bounded gate-loop iteration or Step 9 for its pre-ship review, never invoked directly, never the entry point for…

drafting-an-adr

Use when a decision affecting architecture (structure, non-functional characteristics, dependencies, interfaces, or construction techniques) needs to be recorded before or after it's made. Applies Nygard's architecturally-significant criteria to judge warrant, then drafts an ADR from a MADR-derived…

drafting-issues

Use when the user, or the current workflow itself, mid-task, needs to open, file, or draft a brand-new GitHub issue for a feature, fix, or refactor and no issue exists yet, or needs to append new findings to an ACM issue this skill already drafted. Elicits the change from the requester and draf…

eliciting-a-design

Turn an underspecified idea into an approved design doc through collaborative dialogue, informed by Domain-Driven Design elicitation and convergence techniques (Domain Storytelling, Scenario Casting, Core Domain analysis). Use when a feature, component, or behavior change has no agreed design yet a…

establishing-ubiquitous-language

Use when a project's terminology is inconsistent or undefined across code, docs, and issues, before introducing a new domain concept, naming a module or skill, or writing glossary/ADR content. Elicits candidate terms from code, docs, and issue history, flags synonyms describing the same concept,…

evaluating-context-channel-maturity

Review whether a non-skill, non-gate instruction channel, CLAUDE.md (root or subdirectory), a Subagent definition, an Output style, a system-prompt-append configuration, or Auto-memory content, is engineered to a mature standard on five points, ownership/review gating, bounded growth, placeme…

evaluating-deterministic-gate-quality

Review a deterministic gate, a git hook, an agent-harness hook, a CI/CD job step, or an MCP-server-level check, for whether it is well-placed and well-built, separating deterministic shape from probabilistic maturity, citing concrete evidence per dimension, and closing with a coverage-attestati…

evaluating-skill-quality

Review a SKILL.md (and its references/) against a nine-dimension quality rubric, separating deterministic shape from probabilistic maturity, citing concrete evidence per dimension. Use when reviewing any SKILL.md, this repository's own or one vendored from elsewhere, before merging, vendoring,…

executing-a-branch-plan

grounding-in-primary-sources

invoking-gitapex

merge-retrospective

outward-artifact-preflight

planning-a-branch-from-an-issue

ranking-the-open-queue

responding-to-a-fresh-arrival

reviewing-an-artifact

scanning-attack-surfaces

scanning-ci-workflows

scanning-leaked-secrets

scorer-gated-skill-edits

screening-a-low-trust-contribution

setup-gitapex-toolchain

stop-and-replan

untrusted-input-triage

Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.

Category

Agent Tooling. Assigned by this directory. Agent Plugins 1.0.0 has no category field, so no manifest declares one.

Related by publisher and keywords

• worldmonitorkoala73

  World Monitor agent plugin: live global-intelligence MCP servers plus task-focused agent skills for country risk, conflict, markets, chokepoints, energy, climate, and related situational awareness.

• mem0mem0ai

  Cross-session memory and token savings for coding agents.

• context7upstash

  Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.

• chrome-devtoolsChromeDevTools

  Reliable Chrome automation, debugging, and performance analysis for AI agents.

• agentic-bundle-aas-accessibility-inclusive-uxsickn33

  Portable skills-only "AAS Accessibility & Inclusive UX" plugin from Agentic Awesome Skills.

• agentic-bundle-aas-ai-product-evaluation-opssickn33

  Portable skills-only "AAS AI Product & Evaluation Ops" plugin from Agentic Awesome Skills.