cc10x

Use when a cc10x agent starts a task: the shared preamble for the memory protocol, the contract format, and the output rules.

Greenfield architecture design: map functionality flows, draw components, design APIs, classify dependencies, plan observability. For multi-component, API, schema, auth, or integration-heavy work. For retrofitting existing code, use codebase-hygiene instead.

Use when writing production code test-first: the RED-GREEN-REFACTOR cycle, false-RED detection, vertical slicing, scope escalation, test process discipline, and code generation patterns.

Answers questions about cc10x itself — what it is, how to install and configure it, how the router, workflows, memory, and hooks operate, and how to troubleshoot. Use this skill when: the user asks ABOUT cc10x — "what is cc10x", "how do I configure cc10x", "why isn't cc10x activating", "how do cc10x workflows work", "how does cc10x memory work", "cc10x troubleshooting". NOT for performing work: "set up cc10x for me", build, debug, review, or plan requests route to cc10x-router. "Update cc10x" / "upgrade cc10x" route to the update skill. This skill answers questions; it never edits project code, never writes files, never runs workflows. Triggers: what is cc10x, cc10x help, cc10x guide, how to use cc10x, configure cc10x, cc10x setup, cc10x faq, cc10x troubleshooting, cc10x not working, cc10x not activating.

Routes build, debug, review, plan, QA, and triage requests through the cc10x workflows (task graphs, workflow artifacts, gates); it is the single entry point for cc10x code work. Activates when the user asks to implement, fix, review, plan, test, refactor, or continue code work. Trigger keywords: build, implement, create, write, add, review, audit, debug, fix, error, bug, broken, plan, design, architect, spec, brainstorm, test, refactor, optimize, update, change, research, cc10x, c10x. Hand-off: questions about cc10x itself belong to `cc10x-guide`, and "update cc10x" belongs to the `update` skill.

Two-mode skill: (1) adversarial review — spec compliance + code quality + security, confidence-scored findings with file:line evidence; (2) receiving review — verify-before- agreeing discipline for acting on external/human review feedback.

Canonical deep-module vocabulary (module, interface, depth, seam, adapter, leverage, locality) for designing a module's shape — a lot of behaviour behind a small interface at a clean seam, testable through that interface. The single source of truth for these terms; other skills (architecture, codebase-hygiene) point here instead of restating them. Use when designing or improving a module's interface, finding deepening opportunities, deciding where a seam goes, or making code more testable.

Two-mode skill: (1) find semantic duplicates — functions doing the same thing under different names, invisible to copy-paste detectors; (2) deepen shallow modules — thin wrappers and pass-through layers that spread complexity. Advisory and read-only; changes route through BUILD with full gates.

Use when diagnosing a defect or regression: feedback loop FIRST, root cause before fix, blast radius after fix. Covers the 10-rung construction ladder, LSP-powered tracing, hypothesis quality criteria, and four-phase investigation.

Use when a BUILD phase completes, a commit is staged, or a PR is about to be created, and the diff has not yet been reflected in documentation. Also use when the user says "update docs", "sync docs", "document this", or asks whether documentation is up to date.

Use when changing or sharpening a project's domain model: challenge terms against the glossary, sharpen fuzzy language, stress-test with edge-case scenarios, update CONTEXT.md inline, and offer ADRs sparingly. In read-only mode it reads CONTEXT.md and obeys it, emitting a proposal on contradiction rather than resolving it. See the Active vs read-only section for which mode applies.

Two-mode exploration skill: (1) design dialogue — turn rough ideas into validated designs through collaborative interview before planning; (2) spike — throwaway code answering ONE design question, deleted or absorbed, never shipped. Router invokes mode via dispatch context.

Two-mode frontend skill: (1) authoring — accessibility, responsive layout, loading/error states, performance, DESIGN.md authoring, visual direction; (2) critique — READ-only scored review of built UI against anchored rubric, AI-slop detection, two isolated assessments. Router invokes mode via context.

Use when a research task needs a single tool from a named MCP server that is not already mounted, and the `mcp` CLI (github.com/f/mcptools) is the way to call it. Not for servers already mounted, general MCP questions, or installing MCP servers.

Two-mode skill: (1) session memory — load/persist durable workflow state under .cc10x/ (activeContext, patterns, progress) so context survives compaction; (2) handoff package — portable, secrets-redacted export for a coworker, different tool, or fresh non-cc10x session.

Use after saving a non-trivial plan or decision RFC when a fail-closed feasibility, completeness, and alignment review must block execution.

Use when writing an execution plan or a decision RFC: task decomposition, context references, validation levels, risk-based testing, ADR format, plan completeness gate, and functionality flow mapping.

Use when designing or checking a QA test system: choosing the right tier, scenario matrices with pipeline-wide observation points, test-environment topology and isolation, fixture lifecycle, and flake sources. Also the coverage lens for reviewing a QA plan (it reaches a plan reviewer as a file to Read in the task scaffold, not as a SKILL_HINTS entry).

Use when research files (web or GitHub findings) are available and must be synthesized into a recommendation. Synthesis guidance only; it does not execute research.

Use when a git merge or rebase reports conflicts and the operation is in progress.

Safe cc10x upgrade through the Claude Code plugin CLI. Lists every installed scope, refreshes the marketplace, updates each scope, and optionally carries local patches over to the new install. Use this skill when: updating cc10x, upgrading, pulling latest cc10x, syncing plugin, refreshing cache, or checking for new versions. Triggers: update cc10x, upgrade cc10x, pull cc10x, sync plugin, refresh cc10x, check for updates, new version, update plugin, upgrade plugin.

Use when judging whether a task reached its goal, not just finished: the gate function, self-critique gate, validation levels, evidence array protocol, and goal-backward lens. Task completion is not goal achievement.