yacb2

yacb2/claude-restart

Command

Restart Claude Code session (exit + auto-resume).

yacb2/aidex

Skill Claude CodeCodex

Use when the user wants to assess the state of a feature, flow, or module — a UX, security, performance, or accessibility audit; cataloging bugs, gaps, and opportunities; retesting open findings; escalating a finding to the backlog; or updating audit methodology. Fires on "I want to do a UX / security / performance /…

yacb2/aidex

Agent

Detect audit-like folders in .context/plans/ using file-presence heuristics. Read-only. Used by /aidex-audit migrate to propose candidates.

yacb2/aidex

Agent

Read scattered findings from legacy audit folders and generate canonical 00-inventory.md rows. Used by /aidex-audit migrate after folders have been moved.

yacb2/aidex

Skill Claude CodeCodex

Use when the user wants to capture or defer something for later without acting on it now — add it to the backlog, park it, shelve it, queue it, track it, "we'll do this later", "not now but don't forget", a tech-debt entry, or moving an audit finding to the backlog. Fires on "add to the backlog", "add to the backlog…

yacb2/aidex

Skill Claude CodeCodex

Use when fixing a bug, resolving a reported issue, or when something is broken and needs a test-driven fix — investigate root cause, write a failing regression test (RED), implement the minimum fix, confirm the test passes (GREEN), then commit test and fix together. Fires on "fix this bug", "this is broken", "it's not…

yacb2/aidex

Agent

Investigates bug root cause by tracing code paths, reading error messages, checking recent changes, and identifying the exact source of the problem.

yacb2/aidex

Agent

Verifies that a bug fix doesn't introduce regressions by running test suites, checking types, and validating lint.

yacb2/aidex

Agent

Discovers existing tests, testing patterns, and frameworks in the project to recommend the best approach for writing a regression test.

yacb2/aidex

Skill Claude CodeCodex

Use when the user wants to log or draft a real communication with a person — capture an email/WhatsApp that was received, log a meeting or call that happened, or draft a message/email to send — as a written .context/communications/ entry, kept in the communication's native language. Fires on "log this email", "save…

yacb2/aidex

Skill Claude CodeCodex

NOT auto-invoked. Shared documentation-canon hub for the aidex- family — holds the .context/ convention references (references/.md) that the single-purpose sibling skills delegate into. Routing — plan multi-step work → aidex-plan; record a decision/ADR → aidex-decision; capture a stakeholder/client request →…

yacb2/aidex

Agent

Boundary scenarios drawn from real usage-retro evidence, each run through the durability-arbiter agent (sonnet). Re-run by spawning the agent with the agent file as prompt + each consultation. First run 2026-06-22: 8/8 correct.

yacb2/aidex

Agent

Consulted by a running executor at an ambiguous would-stop boundary to decide CONTINUE / ASK / STOP, so the run keeps going autonomously instead of interrupting the user. Plays the user's standing posture with criterion. Read-only and fast.

yacb2/aidex

Command Claude Code

Review the current diff for correctness bugs.

yacb2/aidex

Command Claude Code

Create a git commit for the current changes.

yacb2/aidex

Command Claude Code

Bump version and cut a release.

yacb2/aidex

Skill Claude CodeCodex

Use when writing, placing, or running tests in any project — which layer a behaviour belongs in ("unit or E2E for X", "component test or browser test"), which tests to run for a change instead of the whole suite, when to extract a fixture, setting up an isolated disposable E2E environment, or the per-project testing…

yacb2/aidex

Skill Claude CodeCodex

Use when the user wants an interactive HTML dashboard/render/board of .context/ data — the backlog board, a plan's progress, an audit inventory, the coverage matrix — or says "render X as HTML", "generate the dashboard", "show this as a page". Not for: authoring content (the markdown stays canon); publishing without…

yacb2/aidex

Skill Claude CodeCodex

Use when the user has made an architectural, technical, or product decision and wants it recorded as a written .context/decisions/ ADR — what was chosen, why, the alternatives, and the consequences — so the team does not re-litigate it later. Fires on "we decided X", "document this decision", "write an ADR", "record…

yacb2/aidex

Skill Claude CodeCodex

Use when the user wants to design, scaffold, or choose an agentic LOOP that repeats one task until a check passes — iterate-until-green automation, a long-running unattended build, or picking which loop engine fits — landing as a written .context/loops/ loop-spec (goal + verifiable stop condition + guardrails + chosen…

yacb2/aidex

Skill Claude CodeCodex

Use when the user asks to execute, implement, or continue a written multi-phase plan — typically a .context/plans/ document or any plan with checkboxes/phases. Fires on "implement the plan", "execute plan X", "let's execute the plan", "continue with phase Y", "resume the plan", "run the plan phase by phase". Enforces…

yacb2/aidex

Skill Claude CodeCodex

Use when implementation work should become a written .context/ plan before coding starts — either multi-phase work (a feature build, a migration, a refactor spanning backend/frontend/infra) or a single scoped change where only the file list and acceptance criteria need pinning down; a triage step picks which. Fires on…

yacb2/aidex

Skill Claude CodeCodex

Use when the user wants to document how an existing, settled part of the system works as an evergreen .context/references/ module — architecture, configuration, an operational runbook, a how-it-works guide. Fires on "create a reference for X", "document how X works", "write up the X architecture", "document the X…

yacb2/aidex

Agent

Adversarial close-gate for a reference module. Given a module path, tries to REFUTE its claims against the code, the database and the tree. Returns a verdict per claim. Never rewrites the document.