cwijayasundara
- 72 skills
- 0 followers
- 7 hours ago last updated
- ▌ Repo Writer · cwijayasundaraUse this skill when the task requires turning agent work into polished repository artifacts such as reports, design notes, and structured briefs without editing source code.
- ▌ Research Playbook · cwijayasundaraUse this skill when the user asks for a comparison, ecosystem analysis, or synthesis of open versus managed agent harnesses. It helps the agent gather sources, extract tradeoffs, and turn them into durable markdown artifacts.
- ▌ Langchain Agents Deploy · cwijayasundaraUse when productionising or deploying a LangChain / LangGraph / DeepAgents agent. Covers durable execution (checkpointers, thread_id), the production middleware stack, three deploy targets (LangSmith Cloud, Cloud Run, Docker), secrets, scaling, and post-deploy verification.
- ▌ Langchain Agents Scaffold · cwijayasundaraUse when creating a new LangChain / LangGraph / DeepAgents project from scratch. Picks the right scaffolder for graphs vs. DeepAgents vs. LCEL chains.
- ▌ Langchain Agents Workflow · cwijayasundaraUse when starting work on any LangChain / LangGraph / DeepAgents project. Entry point for the develop -> middleware -> evaluate -> deploy lifecycle, mapping each step to the right official tool.
- ▌ Langchain Agents Middleware · cwijayasundaraUse when building or productionising any agent — adding retries, fallbacks, summarization, human-in-the-loop, PII redaction, call limits, or custom hooks. Middleware is THE composition primitive for modern LangChain agents (v1+); covers built-ins plus the custom middleware authoring API.
- ▌ Langchain Agents Observability · cwijayasundaraUse when debugging an agent's behaviour, reading LangSmith traces, setting up tracing in production (LangSmith + OpenTelemetry), wiring distributed tracing across services, or diagnosing common failure modes.
- ▌ Langchain Agents Langchain Code · cwijayasundaraUse when editing a non-agentic LCEL pipeline — composing Runnables, retrievers, embeddings, chat models, parsers, or building a RAG chain. For agents (LLM + tools loop), use the middleware skill instead.
- ▌ Langchain Agents Langgraph Code · cwijayasundaraUse when building a custom-graph LangGraph agent — when `create_agent(...)` + middleware isn't enough and you need explicit StateGraph control (multi-graph workflows, custom routing, non-standard state schemas, parallel branches). For the common case, use `create_agent` first (see middleware skill).
- ▌ Langchain Agents Deepagents Code · cwijayasundaraUse when editing a DeepAgents project — adding tools, sub-agents, modifying the system prompt, choosing a filesystem backend, or composing extra middlewares (retries, fallbacks, HITL) on top.
- ▌ Langchain Agents Langsmith Evals · cwijayasundaraUse when authoring eval datasets, writing evaluators, running evals against a LangChain / LangGraph / DeepAgents project, comparing eval results between runs, or writing unit/integration tests for an agent.
- ▌ UI Mockup · cwijayasundara bundleCreate interactive UI mockups as self-contained HTML files using React 18 + Tailwind CSS (via CDN). Generate clickable prototypes with state management and realistic mock data. Output mockups to `specs/design/mockups/`.
- ▌ Deployment · cwijayasundara bundleSet up local development with Docker Compose, hot reload, health checks, and database migrations. Generate docker-compose.yml, Dockerfiles, .env.example, and document the deployment topology.
- ▌ Spec Writing · cwijayasundara bundleDecompose a Business Requirements Document into epics and user stories with acceptance criteria, estimate effort, and identify hard dependencies for parallel execution. Output stories in `specs/stories/` with dependency-graph.md and story files.
- ▌ Improve · cwijayasundaraEnhance existing features through story-driven development with full verification.
- ▌ Testing · cwijayasundara bundleTesting patterns — Playwright E2E, test structure, fixture management, mock boundaries.
- ▌
- ▌ Evaluation · cwijayasundara bundleEvaluation patterns — sprint contract format, three-layer verification, scoring rubric references.
- ▌ Lint Drift · cwijayasundaraScan codebase for pattern drift and generate targeted cleanup PRs. Entropy control for agent-generated code.
- ▌ Architecture · cwijayasundaraLayered architecture rules — one-way imports, module boundaries, file organization.
- ▌ Review · cwijayasundara bundleRun evaluator and security reviewer concurrently for comprehensive quality gate.
- ▌ Brd · cwijayasundara bundle[Internal pipeline stage — run by /build; invoke directly only as a power user.] Create a Business Requirements Document — from a Socratic interview, or grounded in a Functional Requirements Document via --frd (with a deterministic net-new/dropped gate). First step in the SDLC pipeline.
- ▌ Auto · cwijayasundara bundleAutonomous build loop with Karpathy ratcheting, GAN evaluator, and session chaining. Iterates story groups until all features pass or stopping criteria met.
- ▌ Gate · cwijayasundara bundleRun the adaptive pre-merge quality gate: deterministic checks, evaluator, diff review, and security review only when the diff crosses a security/data/API boundary. (Renamed from /review to avoid colliding with Claude Code's native /review PR-review command.)
- ▌ Spec · cwijayasundara[Internal pipeline stage — run by /build; invoke directly only as a power user.] Decompose BRD into epics, stories, dependency graph, and feature list for agent team execution.
- ▌ Test · cwijayasundara bundle[Internal pipeline stage — run by /build and /auto; invoke directly only as a power user.] Generate test plan, test cases, test data fixtures, and Playwright E2E tests mapped to acceptance criteria.
- ▌ Vibe · cwijayasundaraControlled small-change lane for low-risk fixes, docs, tests, and narrowly scoped edits without running the full SDLC pipeline.
- ▌ Retro · cwijayasundaraReview this harness's own recent loop-health signals and recommend scored, evidence-backed improvements to the harness itself (skills, gates, sensors, CLAUDE.md rules) — never to product code. Use after a `/auto`/`/gate` run, on a drift cadence, or on demand when the loop feels off. Interactive-only — recommends and records human decisions; does not apply anything.
- ▌ Advise · cwijayasundaraInvoke the frontier advisor for a structural re-rank / unblock / design pivot. Compact brief only.
- ▌ Change · cwijayasundaraChange the behavior of existing code — story-driven by default, or --issue N for a GitHub bug fix. Test-first, full verification, code review.
- ▌ Deploy · cwijayasundara[Internal pipeline stage — run by /build; invoke directly only as a power user.] Generate Docker Compose stack, Dockerfiles, environment config, and init.sh bootstrap script.
- ▌ Design · cwijayasundara bundle[Internal pipeline stage — run by /build (use --doc-only standalone for an ARB narrative); invoke directly only as a power user.] Generate system architecture, machine-readable schemas, and UI mockups. Spawns planner + generator concurrently.
- ▌ Sprint · cwijayasundaraPRD-per-sprint evolution route for an existing harness-built (or brownfield) system — grounds a new PRD against the prior requirement spine, produces a human-approved design amendment against the living specs/design/ baseline, then runs /auto. Companion to /build (sprint 1) and /feature (single-story changes).
- ▌ Status · cwijayasundaraShow SDLC pipeline progress — a one-shot snapshot, a live watch, or a step timeline. Read-only; aggregates the state the harness already writes. CLI-friendly (Devin-style status/watch/timeline with --json).
- ▌ Clarify · cwijayasundara[Internal pipeline stage — run by the planning stages; invoke directly only as a power user.] Bounded clarification gate for resolving product, domain, API, security, or architecture uncertainty without exhausting the user.
- ▌ Context · cwijayasundaraBuild a bounded, cited context pack from the living DeepWiki/code-map before broad source reads. Use in brownfield lanes and whenever source orientation could otherwise require large file reads.
- ▌ Feature · cwijayasundaraBrownfield change route — take an existing-code feature request from intent to a reviewed PR, scaling from a single /change to an epic via /spec→/design→/auto. Linear-tracked, backed by a committed DeepWiki.
- ▌ Promote · cwijayasundaraImplement an approved /retro recommendation and open a PR against this harness repo. Use after a human has approved a recommendation via /retro --apply-decisions. Merge always stays human — this skill only opens the PR, never merges. Refuses gate-loosen/security-class recommendations outright; those are permanently human-gated and must go through /vibe or /change manually.
- ▌ Code Gen · cwijayasundara bundleCode generation quality principles — TDD, typing, error handling, logging, API integration, LLM integration.
- ▌ Code Map · cwijayasundara bundle[Internal pipeline stage — run by /brownfield and /seam-finder; invoke directly only as a power user.] Build a deterministic dependency graph of an existing codebase. AST-first for Python, React/JS/TS, and Java/C#/Go (stdlib ast + tree-sitter wheels — symbols with line ranges, routes, components, hooks, call/render edges, package-aware import resolution, god-file skeletons, incremental --files patching); regex fallback when python3 or the wheels are unavailable. Outputs JSON + ranked symbol map + Mermaid + metrics for downstream brownfield, refactor, and seam-finder skills.
- ▌ Evaluate · cwijayasundara bundle[Internal pipeline stage — run by /auto and /gate; invoke directly only as a power user.] Run the application and verify sprint contract criteria via API tests, Playwright interaction, and schema validation.
- ▌ Refactor · cwijayasundaraRefactor existing code for quality, performance, or maintainability. Enforces core quality principles with ratchet gate.
- ▌ Implement · cwijayasundara[Internal pipeline stage — run by /auto (follow with /gate); invoke directly only as a power user.] Generate production code and tests for a story group using agent teams for parallel execution.
- ▌ Provision · cwijayasundaraProvision the GitHub security-compliance gates and verify they hold. Three modes — protection (branch-protection ruleset so gitleaks+sast+code-owner review block merges), environments (deploy-approval environment so a deploy pauses for a required reviewer), fleet (retrofit BOTH gates across many repos and report per-repo status). Plan-first, dry-run by default; --apply mutates, --verify checks drift. Use when a repo or org needs an enforced branch-protection or deploy-approval gate wired or updated, when verifying a gate has not drifted, or when auditing/retrofitting a whole fleet.
- ▌ Brownfield · cwijayasundaraDiscover and map an existing codebase before planning or changing it. Add --seams "<goal>" to also rank the safest cut-points for that goal.
- ▌ Pe Ic Memo · cwijayasundara bundleDraft a private equity investment committee memo and render it as a branded PowerPoint deck. Adapted from the installed private-equity vertical's ic-memo skill (same 9-section structure), with PPTX output instead of Word. Use when preparing IC materials, writing up a deal, or creating a formal recommendation as a deck rather than a document. Triggers on "write IC memo deck", "PE IC memo PowerPoint", "IC deck", or "investment committee deck".
- ▌ Pr Respond · cwijayasundaraRespond to CI failures and review comments on a harness-opened PR — poll, classify, fix, push, reply with evidence. Bounded and budget-metered; merge stays human-owned. Use when a harness PR shows red CI or unanswered review comments.
- ▌ React Code · cwijayasundara bundleBuild client-side React apps with Vite — useEffect cleanup and stale-closure bugs, dependency-array gotchas, Context vs. server-state libraries for API data, Vite environment variables, and testing with Vitest. Scoped to Vite+React client-side apps — NOT Next.js (App Router/Server Components/Server Actions need different guidance). Triggers on "useEffect", "React hook", "stale closure", "dependency array", "Vite env variable", "React Vitest testing".
- ▌ Attestation · cwijayasundaraGenerate a per-commit, durable compliance attestation (with a sha256 corruption-detecting integrity checksum) from the harness control inventory, the branch-protection/deploy-gate verify outputs, the gate verdict, and the ratchet baselines — then commit the record. Use at /gate or in CI to produce committed evidence for a commit, or to --verify a stored attestation's integrity checksum. Remappable to the client's evidence format via standard-map.json.
- ▌ Seam Finder · cwijayasundara bundle[Internal pipeline stage — run by /brownfield --seams; invoke directly only as a power user.] Identify the safest cut-points in an existing codebase for a planned change. Reads code-graph.json + a goal, ranks candidate seams by observability + funnel + read/write asymmetry, and outputs a prioritized list with evidence.
- ▌ Fastapi Code · cwijayasundara bundleBuild FastAPI backends — dependency injection with Depends(), Pydantic v2 request/response validation, async vs sync route rules, background tasks, and testing with TestClient. Use for any FastAPI route, dependency, or Pydantic model. Not for database/ORM design (no SQLAlchemy content here) or non-FastAPI Python web frameworks. Triggers on "FastAPI route", "Depends()", "Pydantic model", "FastAPI dependency", "FastAPI testing", "TestClient", "async def vs def FastAPI".
- ▌ Langchain Code · cwijayasundara bundleBuild LangChain agents in Python — create_agent, chat model initialization, tool binding, structured output, and middleware. Use for a single-agent tool-calling loop with a system prompt and a fixed tool list; use langgraph-code instead when the task needs explicit multi-step state-machine control flow, and deepagents-code instead when it needs a pre-assembled filesystem/planning/subagent harness for long-running work. Triggers on "LangChain agent", "create_agent", "chat model", "tool calling agent", "structured output langchain", "bind_tools".
- ▌ Langgraph Code · cwijayasundara bundleBuild stateful, multi-actor LangGraph agents in Python — StateGraph definition, conditional routing, checkpointing/persistence, and human-in-the-loop interrupts. Use when a task needs explicit multi-step control flow, crash/interrupt recovery, or approval gates — not for a single-turn prompt or a simple tool-calling loop (use langchain-code's create_agent for that). Triggers on "LangGraph", "state graph", "stateful agent", "multi-step agent workflow", "checkpointing", "resume from crash", "human in the loop agent".
- ▌ Agent Readiness · cwijayasundaraShow how mature/safe this codebase is for heavy AI-agent use — a synthesis dashboard across 8 pillars, aggregating signals the harness already collects. Read-only report; aggregates state already on disk.
- ▌ Deepagents Code · cwijayasundara bundleBuild long-running, production-ready agents with DeepAgents — the opinionated harness on top of LangGraph/LangChain providing filesystem access, task planning, subagent delegation, and context management out of the box. Use for long-running coding/research/multi-step tasks where you'd otherwise hand-assemble that middleware stack yourself; use langchain-code's plain create_agent instead for a simple single-tool-call loop with no need for planning or filesystem access. Triggers on "DeepAgents", "create_deep_agent", "agent harness", "long-running agent", "coding agent with filesystem", "subagent spawning".
- ▌ Tracker Publish · cwijayasundara bundlePublish approved Claude Harness dependency groups to Linear/Jira-compatible tracker tasks and write the local tracker mapping contract.
- ▌ Portfolio Rollup · cwijayasundaraAggregate per-repo compliance attestations into one integrity-hashed portfolio rollup — verifying each attestation's sha256 integrity, recording an unattested repo as a compliance gap, and computing harness-version drift across the fleet. Use over a local collection directory of attestations, or with --fetch to gather them via fleet.json + gh api. --verify re-checks a stored rollup's own integrity.
- ▌ Reuse Or Justify · cwijayasundaraUse when reuse-scout fires at intake (band ≥ medium, a touched constitution invariant, or a same-release clone cluster) — run the confidence-gated reuse-vs-new dialogue and record the decision + performance budget before code. [Internal discipline — invoked by /change, /feature, and /sprint intake; direct use is a power-user path.]
- ▌ Scaffold Upgrade · cwijayasundaraUpgrade harness control-plane files (hooks, scripts, git-hooks, agents) in a previously scaffolded project without wiping project-manifest or state. Dry-run by default.
- ▌ Mockup · cwijayasundaraCreate a UI mockup, component, or page as a disposable artifact. No SDLC pipeline, no evaluator, no security review.
- ▌ Fix From Diagnostics · cwijayasundara[Internal pipeline stage — run by /auto self-heal and /implement validation when lint/type error volume is high; invoke directly only as a power user.] Turn compiler/linter output into a sharded work queue; fix per package with optional adversarial review — no full monorepo suite mid-shard.
- ▌ Author Prompt Surface · cwijayasundaraUse when creating or editing .claude/agents/*.md, .claude/skills/*/SKILL.md, or .claude/commands/* — apply docs/prompting-standards.md (trigger conditions, model-agnostic bodies, no reasoning-as-text, effort floors).
- ▌ Pinning Down Behavior · cwijayasundaraUse when checking-coverage-before-change reports an UNCOVERED symbol you must edit — writes characterization (pin-down) tests at the nearest observable seam and verifies they bite before any production edit. [Internal discipline — applied automatically by pipeline agents mid-task; direct use is a power-user path.]
- ▌ Arch Doc · cwijayasundaraAuthor a standalone architecture / ARB (Architecture Review Board) narrative document. Disposable artifact — no SDLC pipeline, no planner/generator/evaluator, no schemas or mockups.
- ▌ Research · cwijayasundaraProduce a research / analysis / deep-dive report as a disposable artifact. No SDLC pipeline, no evaluator, no security review.
- ▌ Keeping Refactors Pure · cwijayasundaraUse when committing any change that includes structural work (rename, move, extract, reorder) in an existing codebase — keeps refactor commits behavior-free and behavior commits refactor-free so regressions stay attributable. [Internal discipline — applied automatically by pipeline agents mid-task; direct use is a power-user path.]
- ▌ Upgrading Dependencies · cwijayasundaraUse when bumping a dependency version — package.json, pyproject.toml, requirements, or lockfile changes — in an existing codebase. Classifies the bump, audits the usage surface from the code graph, and isolates the upgrade in its own proven commit.
- ▌ Install Framework Packs · cwijayasundara[Internal pipeline stage — run by /scaffold; invoke directly only as a power user.] Verify agent-framework skill packs declared in project-manifest.json#framework_skill_packs and print normal-terminal install commands for missing packs. Use after /scaffold reports PENDING MANUAL INSTALL, after manually adding a pack to the manifest, or to verify all configured packs are present.
- ▌ Checking Migration Safety · cwijayasundaraUse when a planned change touches persisted data shape — ORM models, migration files, schema definitions, serialized formats, or message contracts — in /change, /refactor, or /implement on an existing codebase. Routes schema changes through expand-contract and proves reversibility before any deploy. [Internal discipline — applied automatically by pipeline agents mid-task; direct use is a power-user path.]
- ▌ Sprouting Instead Of Editing · cwijayasundaraUse when a symbol that must change is UNCOVERED and unpinnable (seam score < 0.5, or a skeletons/-flagged god file with no clean boundary) — adds behavior in a new fully-tested unit instead of editing legacy code in place. [Internal discipline — applied automatically by pipeline agents mid-task; direct use is a power-user path.]
- ▌ Writing Acceptance Tests First · cwijayasundaraUse when a story is about to move from acceptance criteria to implementation — in /test's plan-phase deliverable or /change Step S4, before any production code is written — to write a business-readable acceptance test against a Ports-and-Adapters seam with a test-double adapter, and confirm it fails for the right reason before implementation proceeds. [Internal discipline — applied automatically by pipeline agents mid-task; direct use is a power-user path.]
- ▌ Checking Coverage Before Change · cwijayasundaraUse when about to edit any existing (non-greenfield) symbol — before the first Edit/Write to production code in /refactor, /change, or /vibe — to learn which tests cover it and route uncovered code to pinning or sprouting. [Internal discipline — applied automatically by pipeline agents mid-task; direct use is a power-user path.]