All authors
Claude Skills by bostonaholic
github.com/bostonaholic62 skills0 installs32 views
- Create Team SkillUse for creating or revising Team skills. Defines structure, catalog, and validation.Votes: 0GitHub stars: 11
- Version BumpUse for version bumps on explicit request or as the pre-merge step of a PR land. Never infer from finished, reviewed, green, or draft-ready work. Assigns SemVer.Votes: 0GitHub stars: 11
- Principle Fix Root CausesUse for root-cause repair only on explicit request. Requires fixing causes instead of symptoms.Votes: 0GitHub stars: 11
- Team DesignUse for drafting technical designs with independent review.Votes: 0GitHub stars: 11
- Team FixUse for the full bug-fix pipeline only on explicit request. Never infer from an ordinary bug fix. Runs the compressed pipeline.Votes: 0GitHub stars: 11
- Team ImplementUse for executing implementation plans only on explicit request. Never infer from a ready plan. Implements and verifies slices.Votes: 0GitHub stars: 11
- Team PlanUse for producing tactical implementation plans.Votes: 0GitHub stars: 11
- Team PrUse for opening PRs only on explicit request. Never infer from passed verification. Includes project terms, evidence, and risk.Votes: 0GitHub stars: 11
- Team QuestionUse for decomposing features into tasks and research questions. Produces task and question artifacts.Votes: 0GitHub stars: 11
- Team ResearchUse for focused codebase research before changes.Votes: 0GitHub stars: 11
- Team StructureUse for breaking reviewed designs into verified implementation slices.Votes: 0GitHub stars: 11
- Team WorktreeUse for isolated worktrees only on explicit request. Never infer from work needing isolation. Applies project conventions.Votes: 0GitHub stars: 11
- TeamUse for the Team pipeline only on explicit request. Never infer from ordinary coding work. Runs QRSPI or a leading route.Votes: 0GitHub stars: 11
- Team MigrateUse for migrating a pre-0.147 Team setup only on explicit request. Moves every harness to the Team and bostonaholic/skills plugins.Votes: 0GitHub stars: 11
- Version BumpUse on explicit version-bump or land intent, or as this repository's declared pre-merge step. Prepares and checks the release immediately before merging.Votes: 0GitHub stars: 2
- Addressing Pr CommentsTriages open PR feedback, verifying each review thread, review summary, and comment against the code, auto-applying fixes above 90% verified confidence, and recommending one option for the rest. Use when the user explicitly asks to address or fix PR comments. Never infer from unresolved comments.Votes: 0GitHub stars: 2
- Attaching Pr ScreenshotsUploads local images through GitHub's attachment pipeline and writes one verified Screenshots section into a PR body. Use when the user explicitly asks to add or attach screenshots to a PR. Never infer from local images. Not for capturing screenshots; use capturing-screenshots.Votes: 0GitHub stars: 2
- Auditing Agent Token UsageAudits recent Claude Code and Codex session logs for token and context cost: model routing, inherited subagent models, long sessions, compactions, oversized tool results, and unused MCP servers. Use when asked about agent token usage, context costs, session length, model routing, or cost efficiency.Votes: 0GitHub stars: 2
- Auditing ComplexityRanks where code complexity concentrates in a git repository (cyclomatic complexity, nesting, fan-out, mutable state) and scores CRAP change risk from a coverage file. Read-only. Use when asked for complexity hotspots or change risk. Not for test value; use auditing-tests.Votes: 0GitHub stars: 2
- Auditing Rails Tech DebtAudits a Rails app for tech debt, citing each finding to PoEAA, SOLID, or the Rails guides with file:line evidence and before/after code. Use when auditing Rails for anti-patterns, fat models or controllers, callback abuse, or N+1 queries. Not for over-engineering; use simplifying-ruby-code.Votes: 0GitHub stars: 2
- Auditing Repo SecurityAudits a third-party or freshly cloned repo before install or run for install hooks, auto-run files, CVEs, typosquats, and malicious code, graded A-F with a safe-to-run verdict. Use when asked whether a clone is safe to run, or to audit or scan a third-party repo. Not for security review of the user's own code; use reviewing-code.Votes: 0GitHub stars: 2
- Auditing TestsAudits a test suite, or a named part, for low-value tests and marks each retain, fix, consolidate, or delete with verified removal evidence. Read-only. Use when asked to audit tests for redundant, junk, or low-value tests. Not for code complexity; use auditing-complexity.Votes: 0GitHub stars: 2
- Capturing ScreenshotsCaptures deterministic, visually verified screenshots of a running web or native app (named screens, states, viewports, dark mode) with a manifest. Use when asked for screenshots of an app or its screens. Not for attaching images to a PR; use attaching-pr-screenshots.Votes: 0GitHub stars: 2
- Choosing DeterminismMoves each step of an agent skill whose correct result is fixed by its inputs into a script the skill runs, leaving the model only judgment. Use when creating a skill, or adding or changing its steps, commands, or parsing. Not for trimming a skill; use cutting-skills.Votes: 0GitHub stars: 2
- Configuring ZshChooses the zsh startup file (.zshenv, .zprofile, .zshrc, .zlogin, or a custom plugin under ZSH_CUSTOM) for a configuration change and edits the dotfiles repo source behind the symlink. Use when adding or moving environment variables, PATH entries, aliases, functions, setopt or zstyle options, or completions in zsh config.Votes: 0GitHub stars: 2
- Diagnosing React CodeRuns the react-doctor scanner on a React package, fixes its error diagnostics, and re-runs until none remain. Use when React components or hooks changed, when finishing a React feature or bug fix, or when asked to health-check React code.Votes: 0GitHub stars: 2
- Drawing Mermaid DiagramsWrites, edits, and debugs Mermaid diagrams (flowchart, sequence, class, state, ER, Gantt, pie, mindmap, timeline, quadrant, git graph, XY, Sankey, architecture, journey, kanban, block). Use when the user asks for a diagram, flowchart, ERD, or Mermaid code, or when a Mermaid diagram fails to parse or render.Votes: 0GitHub stars: 2
- Explaining ArchitectureExplains how a subsystem, feature flow, or runtime path works (architecture, data flow, file map, gotchas), with an optional critique by fresh-context critics. Read-only. Use when asked how a subsystem or flow works or where logic belongs. Not for why code is shaped as it is; use investigating-design-rationale. Not for explaining a PR or diff; use explaining-code.Votes: 0GitHub stars: 2
- Explaining CodeExplains code or code changes in plain language, briefly by default or in full for a reviewer. Use when asked to explain, ELIE, summarize, or break down a PR, diff, branch, file, function, or concept for someone new to the code. Not for how a whole subsystem works; use explaining-architecture.Votes: 0GitHub stars: 2
- Fixing Root CausesTraces a bug or failure to its root cause and fixes it there instead of patching the symptom. Use when debugging a crash, failing test, regression, or "fails after restart" bug, or when a fix would add a guard, retry, or workaround to silence an error.Votes: 0GitHub stars: 2
- Freeing Disk SpaceFinds what fills a developer machine's disk and frees space by clearing caches, build outputs, and other regenerable files, running each deletion only after approval and never emptying the Trash. Use when a disk is full or nearly full, the user is running out of disk space, builds or containers fail for lack of space, or the user asks for a disk cleanup plan, to free a target amount of space, or to clean up, reclaim space, or delete caches, build outputs, or the Trash to make room.Votes: 0GitHub stars: 2
- Grooming BacklogsGrooms a GitHub Projects backlog: verifies issues against the code, ranks and clusters them, and plans milestone, link, and closure changes, or promotes issues to Ready. Proposes tracker changes; each requires approval. Use when asked to groom, triage, or prioritize a backlog, or to promote issues to Ready.Votes: 0GitHub stars: 2
- HillclimbingIterates toward a goal one measured change at a time, keeping what raises the score and reverting what does not, until a fresh run of the check proves the completion criteria met. Use when the user gives a goal and completion criteria and asks to hillclimb, iterate, or keep going until they pass.Votes: 0GitHub stars: 2
- Investigating Design RationaleAnswers why code is shaped as it is with an evidence-rated report, tagging each claim [Direct], [Supported], [Inferred], or [Speculative] and closing with a Sources Consulted list that covers git, PRs, tickets, docs, chat, and observability, naming the sources left unchecked. Read-only. Use when asked why code is shaped as it is, why a value or limit was chosen, what alternatives were rejected, or what forces shaped a decision, including when the asker offers a guess at the reason. Use it eve...Votes: 0GitHub stars: 2
- Landing PrsLands a reviewed pull request by rebasing onto the base when the branch is behind and resolving any conflicts, running the project's declared pre-merge steps, pushing, waiting for green CI, and squash-merging. Use when the user explicitly asks to land, ship, or merge a reviewed PR. Never infer from approval, green CI, or completion. Not for a watch that should merge on approval; use watching-authored-prs. Not for rebasing without landing; use rebasing-branches.Votes: 0GitHub stars: 2
- Merging Dependabot PrsAnalyzes open Dependabot PRs for semver level, CI, breaking changes, and security fixes, then squash-merges approved patch and minor updates one at a time, or only comments @dependabot rebase; supports a dry run. Use when the user explicitly asks to merge, process, or rebase Dependabot PRs. Never infer from green CI, an approved Dependabot PR, or stale or conflicting Dependabot PRs.Votes: 0GitHub stars: 2
- Proving ClaimsProves or disproves claims, or the test plan of a PR, by trying to falsify each and rating the strongest evidence reached (PROVEN, PARTIAL, DISPROVEN, UNPROVEN). Changes nothing. Use when asked to prove, verify, or fact-check claims or a PR test plan with evidence.Votes: 0GitHub stars: 2
- Rebasing BranchesRebases the current branch onto its PR or default base, resolves conflicts by intent, re-runs the project's checks, and force-pushes with an explicit lease. Use when the user explicitly asks to rebase the current branch, or when landing-prs calls it on a rebase conflict. Never infer from a behind branch alone. Not for rebasing every open PR; use rebasing-open-prs.Votes: 0GitHub stars: 2
- Rebasing Open PrsRebases every open PR onto its own base in parallel worktrees, one subagent per PR, and force-pushes with an explicit lease after confirmation. Use when the user explicitly asks to rebase, update, or sync all open PRs. Never infer from one stale PR or a merge conflict. Not for the current branch alone; use rebasing-branches.Votes: 0GitHub stars: 2
- Redoing ImplementationsRebuilds the current implementation from scratch as the simplest design that satisfies what was learned, after the user approves the design. Use when the user explicitly asks to redo the work, start over, scrap the approach, or rewrite it more simply. Never infer from a failing or complex implementation.Votes: 0GitHub stars: 2
- Removing CommentsRemoves low-value source comments flagged by a fresh-context reviewer and, with approval, encodes enforceable constraints in types, tests, or lint. Use when the user explicitly asks to remove or clean up code comments. Never infer from a diff containing comments.Votes: 0GitHub stars: 2
- Reviewing CodeReviews a code diff (PR, branch, commit range, working tree, or a diff already in the conversation) in a fresh-context read-only subagent, because a session holding the conversation is a biased reviewer, and returns Conventional Comments findings with an APPROVE, REQUEST CHANGES, or COMMENT verdict. Use when asked to review code, a diff, or a PR, including a pasted diff, a .diff or .patch file, or a diff shown earlier; never review it inline. Not for design docs; use reviewing-design-docs.Votes: 0GitHub stars: 2
- Reviewing Design DocsReviews a technical design document or RFC adversarially in a fresh-context read-only subagent (coverage, decisions, edge cases, consistency, risks, citations, scope) and returns findings with a verdict. Use when asked to review a design doc, RFC, or technical design. Not for code diffs; use reviewing-code.Votes: 0GitHub stars: 2
- Simplifying Ruby CodeRewrites over-engineered Ruby and Rails classes (stateless service objects, behaviorless value objects, class-method-only classes, deep inheritance, needless metaprogramming) as Data, Struct, Hash, modules, or pure functions, after finding every caller and getting a green test baseline, or reports findings when asked to review. Use when asked to refactor, simplify, review, or cut boilerplate from a Ruby or Rails class, value object, service object, gem, or branch diff (hand-written initialize...Votes: 0GitHub stars: 2
- Summarizing Friction LogsAggregates frog friction logs across every repository in a workspace plus the global log into one prioritized dashboard. Use when asked for the friction dashboard, all known friction or papercuts across repos, to list friction logs, or to decide which friction to fix first.Votes: 0GitHub stars: 2
- Using Gh CliRuns GitHub work through the gh CLI and verifies each result. Use when opening a PR, checking CI or failed logs, or handling GitHub issues from a terminal. Merges, closes, reviews, comments, and force operations need an explicit request. Not for landing a PR; use landing-prs.Votes: 0GitHub stars: 2
- Verifying Production ChangesVerifies a merged change took effect in production by revision ancestry and cohort sampling, and reports a bound over sampled requests rather than "fully deployed". Use when asked to confirm or report whether a merged change is live or deployed in production, before answering, even when the build-info, status, or deploy output is already in hand; also when gating on a deploy reaching the fleet, sequencing deploys, or verifying a one-time migration, backfill, or cleanup. Not for CI or build st...Votes: 0GitHub stars: 2
- Watching Authored PrsWatches the user's own PR in a bounded loop, triaging new review feedback and reporting failing CI, or fixing it when granted, until approval, then hands off to landing-prs without merging, even when asked to merge once approved. Use when the user explicitly asks to watch their PR for feedback or CI, including a watch that should merge on approval. Never infer from an open PR. Not for a PR the user reviewed; use watching-reviewed-prs.Votes: 0GitHub stars: 2
- Watching Reviewed PrsWatches a PR the user reviewed in a bounded loop, re-reviews each settlement of their feedback against the branch, resolves or rebuts, and approves once every item settles. Use when the user explicitly asks to watch and approve a PR they reviewed. Not for the user's own PR; use watching-authored-prs.Votes: 0GitHub stars: 2
- Writing No TestsDares the agent to write no tests. Use when the user asks to write, skip, or fix tests. Always infer from a request to write, skip, or fix tests.Votes: 0GitHub stars: 2