llm-conf

Plugin llm-conf from marketplace llm-conf in jptalusan/llm-conf. Commands read from the repo's manifest — 25 days ago.

Skills (28)

• code-review

  Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/spec asked for?). Runs both reviews in parallel sub-agents and reports them s

• codebase-design

  Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.

• correct-by-design

  A way of writing code where invalid data cannot exist past the point it enters, every change goes back through the checks, and every failure is loud, early and names its cause. Use when designing or writing any non-trivial code in any language, such as a new module, a data loader, an adapter, a writ

• diagnosing-bugs

  Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.

• domain-modeling

  Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a GLOSSARY.md, or recording or editing an ADR.

• implement-spec

  Implement the result of /to-spec and /to-tickets in code.

• implement

  Implement a piece of work based on a plan, spec or set of tickets.

• plan

  Grill the user, then write a reviewed implementation plan to a gitignored file at the repo root.

• pr

  Use when writing a PR body.

• prototype

  Build a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.

• research

  Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading legwork delegated to a background agent.

• setup-repo

  Configure this repo for the engineering skills: set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.

• simple-code

  Write the simplest code that solves the problem, and optimize only after a measurement says so. Use when writing, changing, fixing or refactoring code, choosing a library or dependency, or when the user asks for simpler, shorter or less over-engineered code.

• tdd

  Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.

• to-spec

  Turn the current conversation into a spec and publish it to the project issue tracker: no interview, just synthesis of what you've already discussed.

• to-tickets

  Break a plan, spec, or the current conversation into a set of tracer-bullet tickets, each declaring its blocking edges, published to the configured tracker (edges as text in one file per ticket locally, or native blocking links on a real tracker).

• triage

  Move issues and external PRs through a state machine of triage roles, categorise, verify, grill if needed, and write agent-ready briefs.

• wizard

  Generate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover. Don't invoke this for steps the agent can pe

• git-guardrails

  Set up Claude Code permission rules that make dangerous git commands (push, reset --hard, clean, branch -D, checkout ., restore .) ask the user before they run. Use when the user wants to guard against destructive git operations or add git safety rules.

• flat-prose

  Write straight, succinct prose with no contrasts, no header sentences, no colons/semicolons/em-dashes, no jargon, plain noun headers, and one line per paragraph in files. Use for all text written for people - chat replies, reports, summaries, docs, READMEs, commit messages, PR descriptions, code com

• grill-me

  A relentless interview to sharpen a plan or design.

• grill-with-docs

  A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.

• grilling

  Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.

• handoff

  Save the session to a handoff file outside the repo so a fresh context or another agent can continue the work.

• markitdown

  Read or convert documents and media that aren't plain text - PDF, Word (.docx), PowerPoint (.pptx), Excel (.xlsx/.xls), images, audio, video, EPUB, Outlook .msg, HTML, CSV, Jupyter notebooks, ZIP - into Markdown/text using a fully local, offline toolchain (markitdown, poppler, tesseract/Apple Vision

• model-routing

  Conserve usage only when near a 5-hour or weekly limit by downshifting model tiers and shrinking agent fleets. By default does nothing — Claude uses its normal model and effort. Use when the user asks to conserve or /usage shows you are close to a limit.

• report

  Emit a succinct end-of-task report after an implement and review cycle. Dense and lossless: changed interfaces, files, deviations from the plan, checks run, review rounds, follow-ups, and how many agents were involved by role. Use to close out any coding, PR or issue task.

• writing-for-agents

  Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.

Subagents (2)

• analyst

  Cheap, fast analysis of text and data — summarization, classification, extraction, log/output scanning, and language analysis. Use for anything that does not require hard reasoning. Pinned to Haiku to control cost.

• reviewer

  Independent deep code review for correctness, security, and design. Used by code-review and plan, or standalone for high-assurance review. Pinned to Opus; relies on high-effort reasoning.

Hooks (2)

• SessionStart

  "${CLAUDE_PLUGIN_ROOT}/hooks/session-start-handoff.sh"

• SessionStart

  "${CLAUDE_PLUGIN_ROOT}/hooks/session-start-handoff.sh"

Similar plugins