codekiln

Ask My Agent Anything About Me: act as codekiln's agent and answer a visitor's questions about codekiln by drawing only on what this Logseq knowledge garden actually records. Never speak in codekiln's first person. Use when someone has cloned this repo to get to know codekiln and asks things like "who is codekiln?", "what do they work on / believe / value?", "what are their preferences, principles, or projects?", "what are they reading or thinking about lately?". Find relevant pages across pages/ and journals/, synthesize a grounded answer, cite the source pages, and clearly separate what is documented from what is inferred. Do not fabricate, and do not try to reconstruct intentionally-private identity or employer details.

Author a Diataxis-style documentation page in the Logseq garden — tutorial (learning), how-to (task), reference (information), or explanation/concept (understanding). Use when the user asks to create or restructure a How To, Tutorial, Reference, or Concept/Explanation page, or asks which Diataxis type fits. Adds the right `[[Diataxis/...]]` tag and namespace. Do not use for non-doc pages or to edit existing protected `tags::`.

Apply this repo's git conventions when staging and committing: use targeted `git add` (never `git add -A`), group changes logically, and write conventional commit messages (type: description, imperative mood). Use when the user asks to commit, stage, or write a commit message in this repo. Do not use for branch/PR review workflows.

Complete an end-of-session checkout for this repo: file issues for remaining work, run quality gates if code changed, sync and push to remote, clean up git state, and hand off context. Use when the user says "land the plane", "wrap up", "finish the session", or asks to make sure everything is committed and pushed. Work is not done until `git push` succeeds.

Reference or document AI models in the garden using provider namespaces and singular naming. Use when mentioning a model in passing/changelogs, creating a model stub, or authoring a detailed model page with features, benchmarks, tiers, access, and specs. Covers OpenAI/Anthropic/Google/DeepSeek/xAI model link formats and model-code aliases. Do not use for general entity creation (logseq-entity) or non-model pages.

Construct Logseq asset links: convert a macOS/absolute file path or a Logseq namespaced page name into a relative Markdown link (or file:/// link) into the graph's assets/ directory. Use when the user gives a file path or [[Namespace/Page]] and wants the asset/image/PDF link, an asset filename, or an asset folder path. Do not use for ordinary page wikilinks (logseq-core / logseq-link-hygiene).

Work safely with Logseq block IDs (`id::` properties) and `((uuid))` block references when moving, copying, or removing blocks across graph pages. Use when relocating a block that has an id::, creating a new ((ref)) to a block, deciding whether an id:: can be removed, or diagnosing refs that won't render. Baseline safety (never backtick a live ref/link; keep id:: with its block) is in logseq-core; this skill has the full move/copy/reindex procedures.

Convert standard Markdown (especially pasted from ChatGPT or similar) into Logseq-Flavored Markdown: nest code blocks inside bullets, fix heading-to-indent levels, drop horizontal rules, convert wide tables to label-value bullets, fix footnotes to URL-only, and replace generic link text. Use when the user pastes non-LFM markdown to import, asks to "convert to LFM", or to clean up an AI-generated dump. For table column alignment use logseq-table-formatter; for baseline LFM rules see logseq-core / logseq-lfm.

Create or update a bean entry from handwritten scans while preserving line breaks, handling CompanionComment formatting correctly, maintaining spans, and avoiding low-value boilerplate transcription.

Create a new bean entry with the correct file shape, public identifier, frontmatter, imported images, and Beans-specific markdown conventions.

Close out a Beans work session cleanly by validating work, finishing Beads-managed tasks correctly, landing on main, and pruning closed worktrees.

Capture local dev-server screenshots with Playwright for Beans preview workflows, especially for `/beans/` routes and visual verification of new pages or content edits.

Use when adding, changing, or reorganizing AI guidance in this repository. Prefer Rulesync skills over commands, subagents, or hooks for reusable workflows, and always edit Rulesync sources before generating tool-specific AI config files.

Generates and syncs AI rule configuration files (.cursorrules, CLAUDE.md, copilot-instructions.md) across 20+ coding tools from a single source. Use when syncing AI rules, running rulesync commands, importing or generating rule files, or managing shared AI coding configurations.

Create a new glossary term entry with the correct schema, compact body, and lightly sourced Beans field-guide tone.

Create or update a bean entry from handwritten scans while preserving line breaks, handling CompanionComment formatting correctly, maintaining spans, and avoiding low-value boilerplate transcription.

Manage git worktrees for parallel feature development following Langstar's issue-driven workflow. Create worktrees with correct target branches based on issue hierarchy, handle cleanup after PR merge, and maintain worktree hygiene. Use when setting up parallel development environments, working on multiple issues simultaneously, or when users mention worktrees, parallel branches, or issue-based development.

Enforce project hygiene throughout the PR lifecycle. Use before creating PRs to validate worktrees, branch naming, and issue linking. Use when creating PRs to ensure proper "Fixes

Orchestrate replying to multiple GitHub PR review comments in parallel. Use when the user wants to reply to multiple PR review comments or resolve all unresolved comments on a PR.

Break down GitHub issues into official GitHub sub-issues by parsing task lists from parent issue descriptions. Use this skill when a user wants to convert a parent issue with tasks into linked sub-issues, when managing complex features that need hierarchical breakdown. Accepts issue number as parameter or prompts user if not provided.

Remote control tmux sessions for interactive command-line work. Send keystrokes and scrape pane output from Python REPLs, debuggers, and other interactive terminal applications. Use when working with interactive CLI tools, debugging sessions, or REPL-driven development.

Run Rust cargo tests properly in git worktrees with environment variable sourcing. Use when cargo test fails, when seeing authentication errors, when test results differ between runs, or before running pre-commit checks in worktrees. Essential for integration tests requiring LANGSMITH_API_KEY or ANTHROPIC_API_KEY.

Managing LangGraph Cloud deployments through listing, filtering, and cleanup operations. Use when managing test deployments, cleaning up orphaned resources, filtering by name patterns, or handling bulk deletion. Automatically sources credentials from devcontainer environment.

Create a structured notes directory for studying and documenting remote GitHub repositories. Use this skill when the user wants to set up a workspace for researching, analyzing, or taking notes on an external GitHub repository. Creates separate committed notes/ directory and gitignored code/ directory.

Evaluate whether README.md gives a first-time visitor the information needed to understand, trust, install, and try Clilint, with links to focused details. Use after changing the README or when asked whether it serves its purpose.

Evaluate README.md against Clilint's communication style, including plain language, ambiguity, distracting wording, and progressive disclosure. Use after changing the README or when asked to review its writing.

Assess clilint's pending help-quality rule from captured `--help` evidence, write a versioned assessment document, and have clilint validate and attach it. Use when a clilint report marks `clilint/help/useful-example` as unassessed or when asked whether CLI help teaches a likely task with a useful example.