kevinslin
@kevinslin
Public Skills
dev.new
by kevinslin
Sync a repo to the latest master branch by checking out master and pulling from origin. Use when the user asks to refresh local state before new work.
dev.shortcuts
by kevinslin
Mandatory shortcut trigger and usage guidance. ALWAYS check if shortcut. Applies before responding to ANY coding or development request.
ag-learn
by kevinslin
learn from the current session, run a time-bounded review across sessions,
ag-ledger
by kevinslin
Record and query append-only agent activity ledger entries using local JSONL daily files under META_LEDGER_ROOT (default ~/.llm/ag-ledger). Use when agents should log session start, notable changes, or session end, and when reviewing activity by session, workspace, or time range.
dev.loop
by kevinslin
Drive a development task end-to-end from a user-stated goal through planning, context gathering, execution, verification. Use when the user asks to run a devloop, drive a task to completion, or wants a plan-gather-execute-verify workflow with phased commits and CI verification. Also use if user asks to invoke any individual phase of the devloop
dev.do
by kevinslin
End-to-end development task intake and execution. Use when the user gives a dev task (feature/bug/refactor) as a file path, pasted description, or git issue and wants it completed; this skill gathers context, asks clarifying questions if needed, then runs the dev.loop workflow to deliver the change.
land
by kevinslin
Finalize a task by syncing status to the originating GitHub issue and, when in an AG directory, updating durable project docs (progress.md, memory.md, and related task tracking files).
dev.codex
by kevinslin
“Codex runtime/config management (MCP servers, config.toml, session setup) plus session analysis/summaries. Use only for Codex self‑configuration. Do not use for creating or updating skills or SKILL.md content; use $sc for that.”
dev.review
by kevinslin
Multi-type review skill for code, design docs/specs, architecture, UX,
agent-browser
by kevinslin
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.
gen-notifier
by kevinslin
Generic desktop notification skill for agents. Send exactly one desktop notification per job at the final terminal state, immediately before the final user-facing report, unless the user says otherwise.
dev.research
by kevinslin
Create structured research documentation for codebase exploration and feature investigation. Enables agents to produce docs that capture findings, methodologies, and recommendations. Covers architecture docs, research briefs, flow docs, state docs, service design docs, feature design docs, feature specs (execution plans), investigation specs, validation specs, recipes, vendor docs, frequently asked questions (FAQ), and FAQ specs that append Q&A to an existing research document.
ag-dir
by kevinslin
Define and maintain an Agent Project Directory (AGD) with clear durable
sc
by kevinslin
Guide for creating or updating skills and SKILL.md content, including
imagekit-upload
by kevinslin
Upload images to ImageKit from file paths or clipboard, returning the CDN URL for easy sharing and embedding
meta.skill-optimizer
by kevinslin
Optimize existing skills and their associated files (SKILL.md, scripts, references, assets) for clarity, concision, and ease of use. Use when asked to optimize, streamline, simplify, or clean up a skill; consolidate duplicated or conflicting instructions; add small, clarifying examples; or run an evidence-based skill review using past runs/sessions and learnings.
fast-mode
by kevinslin
Operate Codex in fast-mode by skipping skill loading and going directly to task execution, while allowing only explicitly whitelisted skills from a local allow-list file. Use when a user requests fast-mode, minimal overhead, or "no skills unless allowed."
meta.summarize
by kevinslin
Summarize Codex activity from ag-ledger using optional scope, lookup,
create-task
by kevinslin
Create tasks across target platforms. Use when a user asks to create an issue/ticket/task. Currently supports GitHub Issues and always appends a required Context footer with the LLM session to the task body.
sudocode
by kevinslin
Write consistent sudocode from real code. Use whenever sudocode needs to be written, including flow docs, specs, architecture docs, or code-to-sudocode transformations.
tech-doc-writer
by kevinslin
This skill should be used when writing or reviewing technical documentation such as READMEs, API documentation, quickstart guides, or any user-facing documentation. Apply editorial principles focused on leading with value, cutting redundancy, and creating scannable, actionable content. Use when the user requests help writing docs, improving existing documentation, or creating user guides.
dev.worktrees
by kevinslin
Standardize git worktree creation and management with all worktrees stored under ~/.worktrees/[repo]/[branch-name]. Use whenever running or planning git worktree commands (add/list/remove/prune), creating parallel checkouts, or setting up isolated branch workspaces.
dev.can-make-public
by kevinslin
Scan a repository and its git history for secrets, credentials, private keys, internal URLs, PII, and other sensitive artifacts before making it public. Use when a user asks if a repo is safe to open-source, requests a pre-publication audit, or wants to sanitize a repo for public release.
xlsx
by kevinslin
"Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify existing spreadsheets while preserving formulas, (4) Data analysis and visualization in spreadsheets, or (5) Recalculating formulas"
dev.bootstrap.typescript
by kevinslin
Bootstrap or augment TypeScript projects. Use when asked to scaffold a new TypeScript project using the Copier template at /Users/kevinlin/code/copier-typescript-codex, or when asked to add a pre-commit hook that runs formatting and linting in an existing project.
dev.llm-session
by kevinslin
Derive Codex CLI session IDs and resume interactive sessions. Use when asked to resume Codex sessions, find or map session IDs, inspect ~/.codex/history.jsonl or ~/.codex/sessions, or troubleshoot Codex resume behavior.
dev.add-license
by kevinslin
This skill should be used when the user wants to add a LICENSE file to their repository. Currently supports Apache License 2.0 with automatic copyright information detection from git configuration. Also updates package.json license field if the file exists.
dev.code
by kevinslin
This skill should be used when performing any coding task including implementing features, fixing bugs, refactoring code, or making any modifications to source code. Provides best practices, security considerations, testing guidelines, and a structured workflow for development tasks.
dev.mermaid
by kevinslin
Generate Mermaid diagrams with proper syntax. Use when creating flowcharts, sequence diagrams, class diagrams, or any other Mermaid visualizations. Ensures correct label quoting to prevent parsing errors.
dev.conventional-commits
by kevinslin
Explain and apply the Conventional Commits specification for commit messages, including required format, types/scopes, breaking change notation, and examples. Use when asked to draft, validate, or review commit messages or when a repo wants Conventional Commits adoption.
hn-title
by kevinslin
This skill should be used when the user wants to create, analyze, or improve blog titles for Hacker News submissions. Invoke when the user mentions "HN title", "Hacker News title", wants to optimize their post title, or wants to increase their chances of reaching the HN front page.
find-links
by kevinslin
This skill should be used when the user wants to fill in TODO links, placeholder links, or missing links in markdown files. Invoke when the user mentions "fill links", "TODO links", "find links", or asks to add appropriate links to concepts in a document.
dendron
by kevinslin
do not use this skill
dev.code
by kevinslin
This skill should be used when performing any coding task including implementing features, fixing bugs, refactoring code, or making any modifications to source code. Provides best practices, security considerations, testing guidelines, and a structured workflow for development tasks.
dev.document
by kevinslin
document changes made
dev.add-license
by kevinslin
This skill should be used when the user wants to add a LICENSE file to their repository. Currently supports Apache License 2.0 with automatic copyright information detection from git configuration. Also updates package.json license field if the file exists.
dev.exec-plan
by kevinslin
This skill should be used for development tasks that require detailed technical planning with persistent documentation. Use when the task involves architectural decisions, multi-phase implementation, external dependencies, or when the user explicitly requests an execution plan.
dev.gh
by kevinslin
GitHub CLI operations
dev.lint
by kevinslin
lint project
dev.mermaid
by kevinslin
Generate Mermaid diagrams with proper syntax. Use when creating flowcharts, sequence diagrams, class diagrams, or any other Mermaid visualizations. Ensures correct label quoting to prevent parsing errors.
dev.speculate
by kevinslin
Always use this skill to provide context on the codebase. Automatically initializes and references the Speculate documentation framework (coding rules, shortcuts, templates, and project specs) to ensure agents understand project structure, development workflows, and coding standards. Use for every task to maintain context and code quality.
gen-notifier
by kevinslin
Generic desktop notification skill for agents. Send desktop notifications when tasks are complete (or when user input/errors block progress). By default, assume that all jobs will require a notification unless the user says otherwise.
dev.code-extension
by kevinslin
Install VS Code/Cursor extensions from a local .vsix via CLI (code, code-insiders, cursor, cursor-nightly). Use whenever asked to install an extension programmatically.
find-links
by kevinslin
This skill should be used when the user wants to fill in TODO links, placeholder links, or missing links in markdown files. Invoke when the user mentions "fill links", "TODO links", "find links", or asks to add appropriate links to concepts in a document.
hn-title
by kevinslin
This skill should be used when the user wants to create, analyze, or improve blog titles for Hacker News submissions. Invoke when the user mentions "HN title", "Hacker News title", wants to optimize their post title, or wants to increase their chances of reaching the HN front page.
learn
by kevinslin
learn from the current session
imagekit-upload
by kevinslin
Upload images to ImageKit from file paths or clipboard, returning the CDN URL for easy sharing and embedding
tech-doc-writer
by kevinslin
This skill should be used when writing or reviewing technical documentation such as READMEs, API documentation, quickstart guides, or any user-facing documentation. Apply editorial principles focused on leading with value, cutting redundancy, and creating scannable, actionable content. Use when the user requests help writing docs, improving existing documentation, or creating user guides.
learning-capture
by kevinslin
Extract and consolidate key learnings, insights, and actionable takeaways from the current conversation session. Use when the user wants to capture, summarize, or document what was learned during the chat, create study materials from discussions, or save important discoveries and decisions for future reference. Triggers include requests like "capture learnings," "summarize what we discussed," "create notes from this conversation," "what did I learn today," or "document our key findings."