Claude Skills by domengabrovsek

Establishes a repo's quality bar as CONSTRAINTS.md: numbers with a command behind each, ratcheted so they never regress, guarded against quiet weakening. Use when no quality bar is written down, when the user says 'set up constraints' or 'define our standards', or when an agent keeps silencing checks or skipping tests to reach green.

Read and write Jira work items through the acli CLI. Use when the user mentions a Jira ticket, issue, story, bug, or epic, drops a Jira key like SER-123, or pastes an atlassian.net/browse URL.

Instruments a feature so production behavior is diagnosable before the first incident: structured logs, RED/USE metrics, traces, symptom alerts. Use when adding logging, metrics, tracing, or alerting, when shipping a feature that runs in production, or when a PR adds I/O, retries, queues, or cross-service calls.

Builds a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.

Reviews code exclusively for over-engineering and lists what to delete: reinvented standard library, unneeded dependencies, speculative abstractions, dead flexibility. Use when the user says 'review for over-engineering', 'is this over-engineered', or invokes /prune. Complements correctness-focused review; this one only hunts complexity.

Starts Phase 1 (Research) for a topic: reads every relevant file, optionally runs a panel of Explore teammates, and saves a research artifact to .claude/state/research/. Use when the user says 'research <topic>' or '/research', or before planning work in unfamiliar code. Research only - proposes no solutions.

Resolves an in-progress git merge or rebase conflict by recovering each side's intent from commits, PRs, and issues. Use when a merge or rebase stops on conflicts, or when the tree contains conflict markers.

Fetches and digests Sentry issue data (summary, tags, stack trace, breadcrumbs, latest event) by short ID, numeric issue ID, or sentry.io URL, for any Sentry org the local token can access. Use when the user mentions a Sentry issue or short ID (e.g. MY-PROJECT-4X2), pastes a sentry.io issue URL, or asks to investigate a Sentry error.

Summarizes the current session's work into a diary entry at .claude/state/sessions/ and runs worktree auto-cleanup. Use when the user says 'summarize' or '/summarize', or when closing out a completed work session.

Runs the comprehensive quality gate before declaring work done: discovers the checks CI actually runs, executes them in order, then reviews git status and the session diff. Use when the user says 'verify done' or '/verify-done', or before pushing any branch.

Stop. That last message did not land: re-pitch it.

Plans a huge chunk of work - more than one agent session can hold - as a shared map of decision tickets in a local file, and resolves them one at a time until the way to the destination is clear. Use when the user invokes /wayfinder on an effort too big for a single session.

Generates an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking a third-party dashboard, or running a one-off migration or cutover. Not for steps the agent can perform itself.

Cleans up a worktree after its branch has been merged: removes the worktree directory and deletes the local branch. Use when the user says '/worktree-merge' or asks to clean up a merged worktree.

Creates an isolated git worktree for the current task and switches into it, resolving cross-session collisions before they happen. Use when the user says '/worktree <slug>' or wants an isolated working copy for a new task.

Audits and optionally prunes git worktrees: current repo by default, cross-repo scan under ~/dev/ with --all. Use when the user says '/worktrees', 'audit worktrees', or 'prune worktrees'.

Edits prose to cut the patterns that read as machine-written: puffery, vague attribution, forced triads, synonym cycling, inline-header lists, and sentences that name a feeling instead of a mechanism. Use when writing or revising a doc, ADR, spec, research artifact, PR description, or any prose longer than a few lines.

Monitor the CI pipeline for the current branch via a background Monitor script (GitHub or GitLab), reacting to pass, fail, and manual-gate states. Use when the user says 'watch CI', 'monitor the pipeline', 'is CI green', or after pushing a branch or creating a PR/MR.

Implement code incrementally with quality gates. Use when the user says 'build', 'implement', or when starting the implementation phase of an approved plan.

1. **Detect VCS platform**: `.gitlab-ci.yml` -> glab, `.github/` -> gh 2. **Start a Monitor** with the matching script: - GitHub: `bash ~/.claude/skills/ci/scripts/gh-ci-monitor.sh` - GitLab: `bash ~/.claude/skills/ci/scripts/glab-ci-monitor.sh` - Use `persistent: false`, `timeout_ms: 3600000` (1 hour ceiling — CI pipelines can be long) - Description: "CI pipeline on <branch-name>" 3. **React to Monitor notifications**: - `no-runs|<branch>`: no CI runs found for this branch — info

Structured production-incident investigation. Forces evidence-first hypothesis ranking before any code change. Use when given an error message, Sentry alert, failing log, or 'investigate <X>' request.

Create or update a diagram. Picks mermaid vs drawio per rules/diagrams.md, writes the source file, previews via MCP. Use when the user says 'diagram', '/diagram', or asks for a flowchart/architecture/sequence/state diagram.

Create or refresh technical engineering docs in the current repo's /docs/ tree. Diataxis layout, mermaid diagrams, ADR support, drift audit. Use when the user says 'write docs', 'document this', 'audit the docs', or '/document'.

Drive a fleet of MRs/PRs to done with a manager loop plus the built-in /goal command. Use for multi-lane / multi-MR work (often spanning sibling repos) where one session plans file-isolated lanes and a fresh manager session sets a /goal, then delegates ALL edit / review / rebase / conflict work to worktree-isolated domain-expert subagents. Use when the user says 'drive fleet' / 'drive the fleet', has 2+ independent lanes to drive in parallel, or wants a hands-off manager that stops only when ...

Investigate and fix a GitHub issue. Use when given an issue number or URL, or when the user says 'fix issue'.

Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.

Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.

1. **Run `/verify-done` first**: hard-fail on any failure. Do not proceed to push, title generation, or PR ceremony if lint, typecheck, test, or build is broken. This pre-empts the most common CI failures (lint, format, typecheck) before they cost a CI run. 2. **Detect VCS platform**: check for `.gitlab-ci.yml` (-> glab) or `.github/` (-> gh) 3. **Determine base branch**: - Default for GitLab repos: `main` - Default for GitHub repos: `develop` - If the user specifies a different target,

Review a pull request with structured severity-based feedback. Use when asked to review a PR, code review, or given a PR number/URL.

Pre-launch validation and release workflow. Use when the user says 'ship', 'release', 'deploy', or 'ready to merge'.

Define requirements before planning. Use when starting a new feature, when requirements are ambiguous, or when the user says 'write a spec' or 'define requirements'.

Write tests using TDD workflow. Use when the user says 'write tests', 'add tests', 'TDD', or 'prove-it pattern'.

Break a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bullet vertical slices. Use when user wants to convert a plan into issues, create implementation tickets, or break down work into issues.

Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.