bgutschke-skills

Plugin bgutschke-skills from marketplace bgutschke in bgutschke/skills. Commands read from the repo's manifest — 8 days ago.

Skills (12)

• audit-skills

  Checks one or more SKILL.md files against this repo's Skill compliance bar — docs/skill-writing-best-practices.md's externally-sourced structure, naming, and description-design guidance, plus CODING_STANDARDS.md's house rules (self-containment, no emojis, no marketing language) — read live from both

• skill-writing-standards

  Invoked via /skill-writing-standards to research external, authoritative sources on Agent Skills authorship (Anthropic's own docs plus other maintained skill collections) and reconcile the findings into docs/skill-writing-best-practices.md as proposed, human-reviewed edits.

• blast-radius

  Finds what a change can break outside its own diff. Names the one fact the change is safe because of, rates each risk on a five-step evidence ladder, and tests that fact with a throwaway script that runs the real code. Reads a pull request by number or URL, or a ref range such as main..feature. With

• draft-commit-message

  Drafts a Conventional Commits message for the currently staged changes, matched to the target repo's own discovered commit-message convention (commitlint config, written doc, or git-log pattern) where one exists, falling back to a generic standards-based convention otherwise. Reads the diff and bran

• repo-catchup

  Reads the commits in the current repository for a date range. Replies with a one-line executive summary and a Date, Owner, Ref, and Description table. Drops bot-authored and merge commits. Groups rows by team, with a CODEOWNERS file present, otherwise by individual contributor. --from and --to each

• sweep-comments

  Deletes disallowed comments from the lines that the current branch added, compared with the repository's default branch, including the working tree. --base names another base branch. --widen sweeps the full content of each touched file. A list of files replaces the diff. A bundled classifier sorts e

• to-pr

  Invoked by a human typing /to-pr, or by an in-session subagent whose own given task already implies landing its work as a PR. Open a new PR from the current branch (draft by default for a human, always draft when subagent-invoked; title and body derived from its commits and diff), or fill in an alre

• why

  Answers why a piece of code has its shape, from evidence in every source the session reaches: commits and pull requests, tickets, design documents, team chat, monitoring, error reports, and the repository's own decision records, with every claim cited and tiered by confidence. Takes a file path with

• audit-rules

  Reads every active rule file and installed skill/agent description, and reports contradictions and unresolved overlaps between them, proposing edits only to files the user can edit directly. Use when the user asks to audit, review, or check their rules, CLAUDE.md files, or installed skills/agents fo

• curate-memory

  Runs one curation pass over the current project's memory store — reads the newest session transcripts, filters them to real user and assistant prose, and writes a complete candidate store beside the input plus one report listing every merge, drop, rewrite, and addition with its justification and a c

• refactor-rule-tree

  Runs one placement-and-pointer pass over a rule tree — the personal global rule file by default, or a given root path, plus every file reached by import or mention edge. A rule in an auto-loaded file gets a verdict: stay, move to a topic file, become a model-invoked skill or hook, or delete. A file

• renovate-triage

  Reads each open Renovate dependency-bump PR's changelog, release notes, and CI status, computes a Risk verdict — safe, needs-review, or blocked — from a fixed hard-stop rule list, and posts (or updates) one PR comment stating the verdict and reason; blocked PRs also get an Agent brief naming call si

Similar plugins