stbenjam
- 45 skills
- 0 followers
- 70 repo stars
- last month last updated
- ▌ Skillsaw Review Panel · stbenjam bundleUse when reviewing a skillsaw PR. Dispatches 7 specialist reviewers (Architecture, Python Expert, Security & Supply Chain, QA Engineer, Technical Writer, Ecosystem, Slopinator) as parallel sub-agents by default, then synthesizes a single verdict. Use --serial for cheaper inline execution.
- ▌ Skillsaw Release Ready · stbenjam bundleAudit skillsaw for release readiness — test new rules against real repositories, audit core architectural dimensions, independently verify proposed fixes, and ship improvements in clean, focused batches. Use before cutting a release.
- ▌ Skillsaw Ecosystem Scout · stbenjamSurvey the AI coding assistant and agentic tool ecosystem, assess skillsaw's competitive position, identify emerging patterns and missing capabilities, and produce a prioritized strategic report as a GitHub issue. Use when evaluating ecosystem trends and product gaps.
- ▌ Skill Id · stbenjam bundleGuides the {{SKILL_ID}} workflow. Use when the user needs {{SKILL_ID}} task support; customize this description with concrete triggers and outcomes.
- ▌ Skillsaw Fix · stbenjamFix skillsaw lint violations — apply deterministic autofixes, then resolve the remaining violations with targeted edits guided by `skillsaw explain`. Use when skillsaw reports violations, when asked to clean up lint findings, or after `skillsaw fix` leaves violations behind.
- ▌ Skillsaw Lint · stbenjamUse when modifying agentic contextual building blocks like skills (SKILL.md), slash commands, agents, hooks, plugins, marketplaces, and instruction files (CLAUDE.md, AGENTS.md, GEMINI.md, QWEN.md, Cursor, Copilot, Cline, or Kiro rules), tool configuration such as an OpenCode `opencode.json`, Muse Code hooks (`.muse/hooks.json`), a Grok Build `.grok/` project layer or a Google Antigravity customization root (`.agents/`, `.agent/`, `_agents/`, `_agent/` — hooks, MCP config, rules, registries and plugins), and committed project memory (`.agents/memory/`). Run skillsaw on the files you touched, apply autofixes, resolve remaining violations with `skillsaw explain` guidance, and re-lint until clean before considering the work complete.
- ▌ Skillsaw Issue · stbenjamUse when skillsaw reports a likely false positive, misses an edge case, behaves incorrectly, or needs an RFE. Gather a safe report and, only with explicit user permission, create a feedback bundle or open a GitHub issue.
- ▌ Skillsaw Update · stbenjam bundleUpdate a repository to the newest skillsaw — upgrade the install, report new rules and their findings in your repo, and bump version pins (GitHub Action SHAs, Makefile targets, pre-commit hooks). Use when a new skillsaw release is out and you want its latest checks.
- ▌ Skillsaw Onboard · stbenjam bundleOnboard a repository to skillsaw — run the linter, triage the findings by rule, apply autofixes, manually fix what remains, set up CI, and create a baseline. Use when adopting skillsaw on a new or existing project.
- ▌ Skillsaw Release · stbenjamBump the version, generate release notes, and publish a new skillsaw release to PyPI. Use when cutting a new release.
- ▌ Skillsaw Create Plugin · stbenjam bundleCreate a skillsaw rule plugin — a pip-installable Python package that adds custom lint rules to skillsaw. Walks through scaffolding the package, writing rules against the lint tree, testing, and publishing to PyPI. Use when a user wants to share skillsaw rules across repositories or publish them for others.
- ▌ Skillsaw Maintenance · stbenjam bundleAnalyze upstream specs (agentskills.io, Claude Code plugin/marketplace format, OpenAI Codex plugins/marketplace, OpenClaw, MCP and MCP Registry, CodeRabbit, APM) for changes, identify gaps in skillsaw's rule coverage, and create or update PRs to close those gaps. Use when performing periodic maintenance on the skillsaw linter.
- ▌ Skillsaw Pr Followup · stbenjamFollow up on open PRs in skillsaw — fix failing CI, address reviewer feedback, push updates, and validate backward compatibility. Use when an open PR needs maintenance.
- ▌ Skillsaw Issue Solver · stbenjamPick up open GitHub issues from collaborators and create PRs to solve them. Use when triaging and resolving reported bugs or feature requests.
- ▌ Skillsaw Issue Triage · stbenjam bundleTriage a GitHub issue filed against skillsaw — classify it (bug, feature, docs, question, other), verify its claims against the codebase, enrich it with missing details, and post one structured triage comment. Use when triaging and labeling incoming issues, not to fix them.
- ▌ Ask · stbenjam bundlePause implementation and ask only the questions needed to produce a high-quality solution.
- ▌ Cut · stbenjam bundleMake the response terser while preserving important reasoning, decisions, and next steps.
- ▌ Dig · stbenjam bundleRevisit superficial or under-verified agent work by investigating its claims, assumptions, evidence, and missing edge cases.
- ▌ Dyj · stbenjam bundleStop punting and complete the user's requested task. Use after the model evades, defers, or stops before doing work it can perform.
- ▌ Lfg · stbenjam bundleImplement the requested direction immediately using reasonable defaults and no unnecessary follow-up questions.
- ▌ Lmk · stbenjam bundleSpawn a subagent to perform the research task, then report back with the answer.
- ▌ Map · stbenjam bundleExplain the shape of an implementation, its key architectural decisions, and how its main pieces fit together.
- ▌ Nah · stbenjam bundleAbandon the current direction, propose three genuinely different approaches, and recommend the strongest one.
- ▌ Qna · stbenjam bundleAnswer genuine questions directly without treating them as implied instructions to take action.
- ▌ Rip · stbenjam bundleRIP — Rethink, Improve, Prune. Use when asked to rethink existing code and improve its architecture for lasting maintainability.
- ▌ Wow · stbenjam bundleRework a frontend with award-winning visual hierarchy, interaction design, polish, originality, and Webby-worthy quality.
- ▌ Wtf · stbenjam bundleExplain the reasoning, evidence, assumptions, and tradeoffs behind the immediately preceding action or result.
- ▌ Books Next · stbenjam bundleAnalyze reading patterns and recommend what to read next from a Calibre library or Goodreads export. Use when asked what to read next.
- ▌ Books Stats · stbenjam bundleShow reading statistics from a Calibre library or Goodreads export, including pace, pages, ratings, authors, series, and TBR. Use when asked for reading statistics or habits.
- ▌ Books Vibes · stbenjam bundleFind books with similar authors, series, themes, shelves, length, or ratings in a Calibre library or Goodreads export. Use when asked for similar-book recommendations.
- ▌ Books Random · stbenjam bundlePick a random book from a Calibre library or Goodreads export, honoring the user's requested pool and filters. Use when asked to choose a random book.
- ▌ Books Series · stbenjam bundleList unfinished book series and the next unread book from a Calibre library or Goodreads export. Use when asked about unfinished series or the next unread book.
- ▌ Pr Loop · stbenjam bundleShepherd a PR: merge base branch, fix CI, address review comments, resolve threads, and monitor until merged. Use when asked to drive a pull request through to merge.
- ▌ Git Rules · stbenjam bundleUse this skill for critical Git rules whenever working with Git, especially before pushing, rebasing, or comparing branches.
- ▌ Books Calibre · stbenjam bundleSupporting Calibre backend for the books-library skill. Use when the books-library skill selects Calibre as the data source.
- ▌ Books Library · stbenjam bundleSearch, analyze, and recommend books from either a Calibre library or a Goodreads CSV export. Use when asked about books in either library.
- ▌ Deep Review · stbenjam bundleUse when a deeper level of code review is requested. Multi-agent panel code review with specialist reviewers and forced runtime reproducers for all BLOCKING bug findings. Optionally posts to GitHub/GitLab as a PENDING review.
- ▌ Test Failures · stbenjam bundleUse this skill whenever any test fails. Follow the required investigation process before deciding whether a failure is pre-existing or what to fix.
- ▌ Books Acquirer · stbenjam bundleAcquire named books via library borrow/hold/download first, then explicit retailer purchase. Use when asked to get, hold, borrow, buy, or download an EPUB book.
- ▌ Make A Movie · stbenjam bundleCreate dynamic, narrated, music-backed, friend-shareable reels with polished motion and audio mixing. Use when asked to make a short narrated video or social reel from structured content.
- ▌ Pollen Counts · stbenjam bundleGet current and forecast pollen counts for a US ZIP code. Use when asked about pollen, allergens, or allergy/pollen forecasts for a US location.
- ▌ Books Release Scout · stbenjam bundleRead-only new-release book recommendations from Calibre ratings with current library availability and retailer pricing. Use when asked to scout for new books to read or buy.
- ▌ Orangetheory Workout · stbenjam bundleLook up Orangetheory Fitness daily workout summaries. Use when asked about today's or tomorrow's Orangetheory, OTF, or orange theory workout.
- ▌ Books Find Incomplete Series · stbenjam bundleFind incomplete series in a Calibre library and identify the next book to read in each series. Use when asked which book series are incomplete.
- ▌ Books Analyze Goodreads Export · stbenjam bundleLoad and query a Goodreads CSV export as the Goodreads backend for the books-library skill. Use when the books-library skill selects a Goodreads export as its data source.