pair

Determines the most relevant next action for your project by reading adoption files and PM tool state. Suggests which skill to invoke next. Use at the start of a session, when switching tasks, or whenever you need guidance on what to work on.

Determines the most relevant next action for your project by reading adoption files and PM tool state. Suggests which skill to invoke next. Use at the start of a session, when switching tasks, or whenever you need guidance on what to work on.

Builds the classification matrix by applying the quality model (KB default + `tech/risk-matrix.md` adoption delta) — from the story context in refinement, from the code/diff in review (confirm-or-raise, never lower). Emits chromatic tags only when the adoption declares the matrix→tag projection. Composed by /pair-process-refine-story (refinement context) and /pair-process-review (review context); invoke directly to classify a card or PR on demand.

Records a decision — ADR (architectural), ADL (non-architectural), DDR (domain, 3-criteria gate), or an analysis-log entry ($type: analysis, written as Category: Analysis, decision-log/) — and is the sole writer of adoption/context-map files. Invoke directly to record or backfill a decision already made ('write that down as an ADR'). Composed by /pair-process-implement and /pair-process-review.

Refines a user story from Todo to Refined — Given-When-Then acceptance criteria, technical analysis, sprint readiness. Composes /pair-capability-write-issue. Not for sizing an already-refined story (use /pair-capability-estimate).

Reviews a pull request through 6 sequential phases (5 review + optional merge with parent cascade) — validation, technical review, adoption compliance, completeness, decision — to decide whether it merges. Not a quick build/test sanity check (use /pair-capability-verify-quality). Composes /pair-capability-classify, /pair-capability-verify-quality, /pair-capability-verify-done, /pair-capability-record-decision, /pair-capability-analyze-debt, /pair-capability-assess-security (required), /pair-capability-verify-adoption, /pair-capability-assess-stack (optional).

Builds the classification matrix by applying the quality model (KB default + `tech/risk-matrix.md` adoption delta) — from the story context in refinement, from the code/diff in review (confirm-or-raise, never lower). Emits chromatic tags only when the adoption declares the matrix→tag projection. Composed by /refine-story (refinement context) and /review (review context); invoke directly to classify a card or PR on demand.

Records a decision — ADR (architectural), ADL (non-architectural), DDR (domain, 3-criteria gate), or an analysis-log entry ($type: analysis, written as Category: Analysis, decision-log/) — and is the sole writer of adoption/context-map files. Invoke directly to record or backfill a decision already made ('write that down as an ADR'). Composed by /implement and /review.

Refines a user story from Todo to Refined — Given-When-Then acceptance criteria, technical analysis, sprint readiness. Composes /write-issue. Not for sizing an already-refined story (use /estimate).

Reviews a pull request through 6 sequential phases (5 review + optional merge with parent cascade) — validation, technical review, adoption compliance, completeness, decision — to decide whether it merges. Not a quick build/test sanity check (use /verify-quality). Composes /classify, /verify-quality, /verify-done, /record-decision, /analyze-debt, /assess-security (required), /verify-adoption, /assess-stack (optional).

Writes and resumes a self-contained progress checkpoint (story, branch, tasks done, decisions, remaining todos) so work survives a context reset. Invoke directly to save or resume progress ('save our progress on #313', 'resume story #256'); composed by a future closing phase of /pair-process-implement and consumed by /pair-capability-publish-pr (via $mode=resume).

Publishes a completed story branch as a pull request: runs the quality gate, creates or updates ONE PR from the pr-template (conditional sections filled only when pertinent), copies the story's classification tags, marks it ready-for-review, and updates the board state. Standalone — driven by a handoff/checkpoint, not by /pair-process-implement having run in the same session. Composed by a future closing phase of /pair-process-implement; reused by hotfix and automation loops. Composes /pair-capability-verify-quality, /pair-capability-checkpoint, /pair-capability-write-issue.

Writes and resumes a self-contained progress checkpoint (story, branch, tasks done, decisions, remaining todos) so work survives a context reset. Invoke directly to save or resume progress ('save our progress on #313', 'resume story #256'); composed by a future closing phase of /implement and consumed by /publish-pr (via $mode=resume).

Publishes a completed story branch as a pull request: runs the quality gate, creates or updates ONE PR from the pr-template (conditional sections filled only when pertinent), copies the story's classification tags, marks it ready-for-review, and updates the board state. Standalone — driven by a handoff/checkpoint, not by /implement having run in the same session. Composed by a future closing phase of /implement; reused by hotfix and automation loops. Composes /verify-quality, /checkpoint, /write-issue.

Produces a technical debt report — categorized items (code, design, test, documentation, infrastructure), prioritized by impact x effort. Composed by /pair-process-review; invoke directly to catalog and prioritize debt on demand. Output-only: writes no files, creates no backlog items, never blocks a PR.

Evaluates and recommends AI development tools — coding assistants (Copilot, Claude Code, Cursor), agent frameworks, MCP integrations, models — when the choice is open. Output-only: emits a proposal + target for /pair-capability-record-decision to persist.

Evaluates and recommends an architecture pattern (layered, hexagonal, microservices, modular monolith, etc.) when the choice is open. Output-only: emits a proposal + target for /pair-capability-record-decision to persist.

Evaluates and recommends infrastructure strategy — cloud provider, CI/CD pipeline, deployment pattern, IaC, environments — when the choice is open. Output-only: emits a proposal + target for /pair-capability-record-decision to persist.

Evaluates and recommends the development methodology (Scrum, Kanban, Lean, SAFe, hybrid) — iterations, ceremonies, flow — when the choice is open. Output-only: emits a proposal + target for /pair-capability-record-decision to persist.

Evaluates and recommends the observability strategy — monitoring, logging, tracing, alerting, telemetry — when the choice is open. Output-only: emits a proposal + target for /pair-capability-record-decision to persist.

Evaluates and recommends which project management tool fits this project (Jira, Linear, GitHub Projects, etc.) when the choice is still open — proposes a choice, doesn't configure anything. /pair-capability-setup-pm configures the tool once picked; otherwise the caller persists the proposal via /pair-capability-record-decision.

Assesses security posture against resolved rules (KB global + per-service + per-web-app + adoption project rules): `$mode: review` — composed by /pair-process-review to produce a 1-line verdict + collapsed findings feeding the risk matrix's security dimension (D22), CHANGES-REQUESTED on vulnerabilities the PR introduces; `$mode: audit` — one-shot codebase scan against OWASP Top 10, writes a report to .pair/working/reports/security/ and proposes project rules for /pair-capability-record-decision to persist. Deterministic secret-scanning is a separate CI layer (see /pair-capability-setup-gates) — this skill never scans for committed secrets itself (D24).

Evaluates and recommends the tech stack — languages, frameworks, database, libraries, versions — when the choice is open: full evaluation at bootstrap, a single new dependency during implementation ('should we add Redis', 'is this new dependency consistent with our stack'), or composed by /pair-process-review when it finds an unlisted dependency in code. Doesn't audit code already written (that's /pair-capability-verify-adoption). Output-only: emits a proposal + target for /pair-capability-record-decision to persist.

Evaluates and recommends the testing strategy — framework, pyramid distribution, coverage targets, TDD approach — when the choice is open. Doesn't write tests itself. Output-only: emits a proposal + target for /pair-capability-record-decision to persist.

Designs a manual test suite — critical path files + suite README — for post-release validation, by analyzing released artifacts, architecture, and deployment targets. Not for planning the automated-testing approach (use /pair-capability-assess-testing). Prerequisite for /pair-capability-execute-manual-tests.

Interviews one question at a time, always with a recommendation, after exploring the KB/codebase first; sync mode drives systematic AI-human alignment on a story until shared understanding is confirmed. Invoke directly to interview on any topic ('grill me on the requirements'). Composed by /pair-process-refine-story and a future /brainstorm (planned — #230). Write-free — returns the synthesis, never writes adoption or issues.

Maps subdomains to DDD bounded contexts and derives the integration pattern between them (integration strength, socio-technical distance, volatility), scoped to items just touched. Composed by /pair-process-refine-story, /pair-process-plan-tasks, a future /brainstorm (planned — #230); full-scope re-mapping only via /pair-process-bootstrap.

Classifies business capabilities into DDD subdomains (core, supporting, generic) with a volatility rating, scoped to items just touched. Composed by /pair-process-refine-story, /pair-process-plan-initiatives, /pair-process-plan-epics, a future /brainstorm (planned — #230); full-scope re-mapping only via /pair-process-bootstrap.

Detects conformity/non-conformity of already-written code and configuration against the project's adopted decisions (architecture, tech-stack, infrastructure, etc.), for a given scope — a compliance audit, not a new-choice evaluation (that's /pair-capability-assess-stack and siblings). Detection-only; resolution is the caller's. Composed by /pair-process-review and /pair-process-implement; invoke directly to audit a scope on demand.

Orchestrates full project setup — PRD verification, project categorization, checklist, standards, quality gates, PM tool — for a brand-new project, end to end. Composes /pair-process-specify-prd, /pair-capability-setup-pm, /pair-capability-record-decision, assess-* (optional).

Implements a refined user story task-by-task, via a 5-step cycle per task (context, branch, implementation, quality, commit), and opens one PR when the story completes. Composes /pair-capability-verify-quality, /pair-capability-record-decision.

Breaks a strategic initiative into epics — each delivering end-to-end value in 2-4 sprints — through structured analysis and validation. Composes /pair-capability-write-issue. Not for filing a single epic issue from text you already wrote (that's /pair-capability-write-issue directly).

Turns a PRD into prioritized (P0/P1/P2) strategic initiatives through structured analysis and validation. Composes /pair-capability-write-issue.

Slices an epic into user stories via vertical slicing and INVEST validation, each sized for one sprint. Composes /pair-capability-write-issue.

Breaks a refined user story into implementation tasks — checklist, dependency graph, AC-coverage table — added to the story body; no separate task issues are created. Composes /pair-capability-write-issue.

Creates or updates an issue in the adopted PM tool from a type-specific template (bug, story, epic, etc.), including topical labels (e.g. tech-debt) for deliberate promotion. Invoke directly to create/update one issue on demand. Composed by /pair-process-refine-story, /pair-process-plan-tasks, /pair-process-plan-initiatives, /pair-process-plan-epics, /pair-process-plan-stories.

Creates or updates an issue in the adopted PM tool from a type-specific template (bug, story, epic, etc.), including topical labels (e.g. tech-debt) for deliberate promotion. Invoke directly to create/update one issue on demand. Composed by /refine-story, /plan-tasks, /plan-initiatives, /plan-epics, /plan-stories.

Breaks a strategic initiative into epics — each delivering end-to-end value in 2-4 sprints — through structured analysis and validation. Composes /write-issue. Not for filing a single epic issue from text you already wrote (that's /write-issue directly).

Slices an epic into user stories via vertical slicing and INVEST validation, each sized for one sprint. Composes /write-issue.

Breaks a refined user story into implementation tasks — checklist, dependency graph, AC-coverage table — added to the story body; no separate task issues are created. Composes /write-issue.