Generate status reports for GitHub PRs with severity assessment and resolved-comment audit

Review GitHub PRs using LLM-powered analysis with configurable prompts and checklists

Decompose large tasks into self-contained phase files

Migrate OpenSpec artifacts to Cypilot SDLC documents with code-verified traceability

Create/update artifacts or implement code

Analyze Cypilot artifacts against templates or code against design requirements with traceability verification (tool invocation is validate-only)

Invoke when user asks to do something with Cypilot, or wants to analyze/validate artifacts, or create/generate/implement anything using Cypilot workflows, or plan phased execution. Core capabilities: workflow routing (plan/analyze/generate/auto-config); deterministic validation (structure, cross-refs, traceability, TOC); code↔artifact traceability with @cpt-* markers; spec coverage measurement; ID search/navigation; init/bootstrap; adapter + registry discovery; auto-configuration of brownfield projects (scan conventions, generate rules); kit management (install/update with file-level diff); TOC generation; agent integrations (Windsurf, Cursor, Claude, Copilot, OpenAI). Kit sdlc: Artifacts: ADR, CODEBASE, DECOMPOSITION, DESIGN, FEATURE, PR-CODE-REVIEW-TEMPLATE, PR-REVIEW, PR-STATUS-REPORT-TEMPLATE, PRD; Workflows: migrate-openspec, pr-review, pr-status.

Create/update artifacts or implement code

Decompose large tasks into self-contained phase files

Invoke when user asks to do something with Cypilot, or wants to analyze/validate artifacts, or create/generate/implement anything using Cypilot workflows, or plan phased execution. Core capabilities: workflow routing (plan/analyze/generate/auto-config); deterministic validation (structure, cross-refs, traceability, TOC); code↔artifact traceability with @cpt-* markers; spec coverage measurement; ID search/navigation; init/bootstrap; adapter + registry discovery; auto-configuration of brownfield projects (scan conventions, generate rules); kit management (install/update with file-level diff); TOC generation; agent integrations (Windsurf, Cursor, Claude, Copilot, OpenAI). Kit sdlc: Artifacts: ADR, CODEBASE, DECOMPOSITION, DESIGN, FEATURE, PR-CODE-REVIEW-TEMPLATE, PR-REVIEW, PR-STATUS-REPORT-TEMPLATE, PRD; Workflows: migrate-openspec, pr-review, pr-status.

Multi-repo workspace setup — discover repos, configure sources, generate workspace config, validate

Analyze Cypilot artifacts against templates or code against design requirements with traceability verification (tool invocation is validate-only)

Artifacts: ADR, CODEBASE, DECOMPOSITION, DESIGN, FEATURE, PR-CODE-REVIEW-TEMPLATE, PR-REVIEW, PR-STATUS-REPORT-TEMPLATE, PRD; Workflows: migrate-openspec, pr-review, pr-status

Turn an accepted kitsoki proposal (or an epic + its children) into a validated, reviewed YAML decomposition of right-sized agent briefs. Use when the user wants to decompose work into briefs, "break this proposal into tickets/tasks", produce a decomposition.yaml, or check out the brief-manifest shape from docs/proposals/work-decomposition.md before that pipeline is built as a story. Drives discovery → manifest → deterministic structural lint → adversarial feasibility/completeness review, by hand.

Drive a Kitsoki story as a skeptical practitioner and validate the exploratory QA path against local project corpora. Use when asked to inspect a product flow, run a skeptical walkthrough, or validate an exploratory QA pass against one or more open source projects with reproducible evidence and a written report.

Drive a kitsoki story's tests + features from real Claude Code transcripts. Mine the intents users actually drove, recover each command's real outcome and whether the user corrected it, then map each in-scope intent to a coverage verdict (CONFORMS / DIVERGES / FIXTURE-GAP / COVERAGE-GAP / OUT-OF-SCOPE) and ticket the gaps. Use when the user says "what does <story> actually cover", "mine transcripts for <story> gaps", "drive <story>'s fixtures from real sessions", "what is <story> missing or getting wrong", or wants evidence-backed conformance for a story. This is STORY-DRIVEN coverage mining — distinct from session-idea-mining (topical scatter) and the shareable pattern-mining in tools/session-mining/README.md.

Write, review, and validate Starlark — the small deterministic Python dialect (go.starlark.net runtime) embedded in kitsoki as the `host.starlark.run` glue capability. Use when authoring or debugging a `.star` glue script for a kitsoki story (the `main(ctx) -> dict` contract, the `.star.yaml` sidecar, `ctx.inputs`/`ctx.world`/`ctx.http`, HTTP cassettes), embedding the Starlark interpreter in Go (Thread, FileOptions, custom Value types, exposing Go builtins), choosing a validation toolchain (buildifier / starcheck / starlark CLI / `kitsoki test flows`), or diagnosing a "this is valid Python but errors in Starlark" surprise (strings aren't iterable, no while/recursion/classes/exceptions, globals can't be reassigned).

Reconstruct "what we've been working on lately" from the current repo's actual Claude Code transcripts. Use when the user opens with "we've been working on…", "what were we doing", "catch me up", "remind me where we left off", or after a /clear and wants recent work restored. Thin trigger that delegates to the Haiku `session-recap` subagent so the transcript bulk never enters this context.

Mine the user's Claude Code chat history for ideas/feedback/pain about a specific topic, synthesize a ranked themed brief, then optionally cross-reference against existing docs and file tickets. Use when the user says "review all my chats/sessions for ideas about X", "what have I said about Y across my history", "mine my conversations for feedback on Z", or wants to harvest scattered design notes / complaints / abandoned threads about a focus area. This is FOCUSED topical mining (local, not shared) — distinct from the shareable pattern-mining in tools/session-mining/README.md.

Build and tune Kitsoki free-text routing fixtures. Use when a user reports a phrase routing to the wrong room, asks to benchmark route quality against a live profile/model, or wants session-mined phrases turned into intent fixtures.