Claude Skills by Alexander-Tyagunov

Systematic performance profiling and optimization with a mandatory baseline-first gate — measure before changing, re-measure after. Use when something is slow or you need to hit a latency/throughput target.

One-time workspace setup — creates the .workspace/ structure, .gitignore entries and a lean CLAUDE.md, then suggests relevant MCPs and permission rules you can add yourself with /permissions. Writes no Claude Code settings. Run once per project.

Blameless post-mortem / RCA — gathers facts, reconstructs a timeline, runs 5-Whys, defines action items, writes the post-mortem file and commits it. Use after an incident or outage.

Converts an approved spec into a TDD task plan with a parallelism map (PARALLEL vs SEQUENTIAL), saved to .workspace/shared/plans/. Use after a spec is approved, before implementation.

Full verification loop — tests, types, lint, build, and a Playwright browser check for UI projects; collects evidence before any success claim. Use to verify a change is actually green.

Memory & context steward — view session history, manage the global reference store (repos, projects, ideas), check context size, and record or consolidate project learnings. Use to review past sessions, remember/recall/forget a reference, check how full the context is, or capture/consolidate learnings.

Work with Confluence over its REST API — "check/read/open confluence", "search confluence", "summarize this confluence page", "find the <X> doc/page", "the <name> page/space", "create/update a confluence page", "comment on a page", "add a label". Any read/search/create/update on Confluence pages, including references to a remembered space, page, or doc. Uses the bundled `confluence` CLI (Confluence REST over HTTPS).

Structured design dialogue with a visual companion — produces an approved spec and design artifacts before any implementation begins. Use at the start of a feature, before writing code.

CI/CD pipeline management — creates, updates, and monitors GitHub Actions, GitLab CI, and CircleCI pipelines. Use to set up or fix CI/CD.

Thorough, research-grounded code review of a change, PR, or MR — multi-lens (correctness, security, simplification, tests), severity-ranked with impact + fix, configurable depth, optional PR comments. Use when asked to review code, "do a code review", "review this PR/MR", "review my changes/diff/branch", or audit a changeset before merge.

Creates a new reusable project skill from a workflow worth capturing, written to .claude/skills/<name>/SKILL.md in the current repo. Use to scaffold a new SKILL.md.

Work with Jira over its REST API — "check/fetch/get jira", "look up a ticket", "search jira / JQL", "my board / my sprint", "the <team> board", "create a jira / story / bug", "comment on a ticket", "@mention / tag someone on a ticket", "ask a clarifying question on a ticket", "transition / move / change status", "log time", "is there an MR/PR for this ticket", "clone the repo for this ticket". Any read/search/create/update/transition on Jira issues, including references to a remembered board,...

Local code knowledge-graph + cache for fast, cheap, targeted retrieval — "knowledge graph status", "kg status", "index this repo / build the code graph", "refresh/rebuild the graph", "reset the knowledge graph", "graph stats", "blast radius of <file>", "what depends on <file/symbol>", "find the code for <thing>". A per-repo SQLite graph of symbols + relationships at ~/.claude/magician/knowledge-graph; query it for ranked file:line instead of grepping and reading whole files. No MCP, no networ...

Use when the user asks to research, investigate, analyze, find out, explore, examine, audit, or evaluate something — structured multi-source research with consulting, library-doc search, web search, and guided output delivery.

Full autonomous SDLC — design, plan, implement, review, and ship with 4 human approval gates

Drives full multi-agent implementation from a blueprint — fans out parallel-safe tasks into waves, runs sequential tasks in order, resolves conflicts, then verifies. Use to execute an approved plan.

Creates a git worktree for isolated feature work (and documents cleanup post-merge); respects the disableGit preference. Use to isolate a feature on its own branch/worktree.

Multi-agent code review AND remediation — dispatches correctness, security, and simplification reviewers in parallel, consolidates findings, then fixes criticals/highs. Use when reviewing a diff or PR before shipping.

Ships a feature — simplify pass, certify, commit, PR, CI monitoring, review loop, merge. Use when a feature branch is verified and ready to ship.

Security scan — OWASP Top 10, credential/secret detection, injection surfaces, dependency audit, git-history secret scan, auth spot-check. Never modifies code; produces a severity-ranked report. Use to audit a codebase for vulnerabilities.

Enable, configure, or disable the Magician CLI status line ("Magician Claude CLI UI") — a lightweight bar showing live context %, a context-rot warning, a token-flow sparkline, model · git · cost, the active skill/workflow/loop, the reasoning effort/mode, the bundled-lore state, and the output-brevity "voice" level. Also sets the output-brevity voice (warrior/scribe/bard) and removes permission entries left by older magician versions. Use when the user says "enable/turn on the magician UI / s...

Comprehend an existing feature, then PORT it to another app (optionally upgrading it) or INTEGRATE/transform it in place — including swapping the vendor behind the scenes while preserving the exact user experience. Use when the user says "port / re-implement / recreate / clone / replicate this feature or flow into <app>", "copy this feature from <url/app> into ours", "swap / replace / migrate the vendor / 3rd-party / provider behind <feature> but keep the UX", "change how <feature> talks to <...

Systematic debugging with a mandatory hypothesis preflight — no code changes before evidence; one change at a time, then a regression test. Use whenever a problem is reported or something misbehaves — "I have a bug / it's broken / not working / crashing", an error/exception/stack trace, a regression, a test failure, or a production issue/outage when the app is deployed. Grounds the investigation with /magic + the knowledge graph (kg query/blast) for comprehensive root-cause research.

TDD engine and enforcer — red/green/refactor, one behavior at a time. Use while implementing any feature or bugfix, or to execute a specific blueprint task with TDD.

Compose and run a large delivery as ONE native Workflow with magician's guardrails — use for big multi-item work: "implement these N stories/tickets/tasks", "deliver the epic", "build out all these features/endpoints", "migrate X across the codebase", "do all of the following", any batch/sweep of similar units. Picks the structure adaptively (per-item pipeline, parallel fan-out, orchestrator-worker, evaluator-optimizer) but always keeps TDD, kg grounding, certify, multi-lens review + adversar...