
Claude Skills by bostonaholic
github.com/bostonaholicWorktree-Question-Research-Design-Structure-Plan-Implement-PR phase discipline with gate enforcement — loaded by orchestrator to govern pipeline phase transitions, artifact conventions, and anti-patterns
Fowler's refactoring methodology — loaded by the implementer agent when working with existing code to recognize code smells and apply proven transformations
Mine the session you are in for learnings that outlive it, and propose each one as a concrete change. It resolves this session's own transcript by a marker the run planted, normalizes it into a bounded record stream, sends three read-only lenses over it (judgment, tooling, divergent), synthesizes one Accepted / Rejected / Backlog list with the evidence behind every item, writes a plan file into a printed run cache, and waits: nothing outside that cache changes before you answer. Invoke ONLY o...
Codebase research contract for the researcher agent — the evidence constraints on findings and the compressed research-report output format. Loaded when neutral research questions need factual, file-referenced answers.
The authoritative severity-tier map for aggregating reviewer verdicts — gate types by reviewer, the Blocking/Major/Minor tiers with the auto-fix boundary, the no-consult rule, and the exit condition of zero Blocking and zero Major findings. Load when aggregating review findings, deciding a pipeline gate, or sorting a finding into a severity tier.
Documentation-gap review methodology — applying prose-quality principles to reviews, the diff-to-docs review process (inventory, impact analysis, cross-reference), and the REQUIRED/RECOMMENDED doc-change classification. Load when reviewing a diff for documentation gaps, assessing existing docs against changed code, or classifying a documentation finding.
Security review methodology — attack-surface identification, OWASP Top 10 checks, additional vulnerability checks, and the CRITICAL/HIGH/MEDIUM/LOW severity classification ladder. Load when reviewing a diff for security vulnerabilities, auditing code for injection/XSS/secrets, or classifying a security finding's severity.
Mechanical verification procedure for the verifier agent — detect available checks from project configuration, run them fastest-first in speed order, capture evidence, and derive a PASS/FAIL verdict. Loaded when pre-completion quality checks need to run.
Land a reviewed pull request: discover the open PR for the current branch, push any unpushed commits, wait for CI to go green, then squash-merge it so the PR title (which may carry a version) lands as the commit subject. Handles a PR that has fallen behind its base (rebase + force-with-lease) and surfaces branch-protection rejections verbatim. Project-agnostic — it knows nothing about how any project versions itself. Invoke ONLY on explicit ship intent — the user says "ship it", "land the PR"...
Vertical-slice breakdown methodology for the structure-planner agent — the rationale for vertical slices, the structure.md document format, the slicing rules, and the slicing heuristics. Loaded when a reviewed design is broken into independently testable slices.
SOLID object-oriented design principles methodology — loaded by implementer agent when writing code and by code-reviewer agent when checking for design violations
Machine-local teardown procedure for finished work — remove the state a merged pull request, a closed pull request, or a completed review leaves on the machine that git teardown never reaches: provisioned databases, containers, queues, buckets, caches, and temp-directory scratch. Driven by a repo-declared `.teamteardown` command list read from the default branch, never from the branch being cleaned up. Loaded by pr-cleanup and by any caller finishing with a PR or a review.
Root cause investigation methodology — loaded by agents when debugging failures to enforce evidence-first diagnosis over guess-and-fix approaches
System-fit reasoning lens — loaded by researcher, structure-planner, and planner, and read inline by implementer, code-reviewer, and ux-reviewer to weigh a change's blast radius (callers, siblings, conventions) rather than only the diff in front of it
Decide the approach before any code is written. The design-author drafts the ~200-line design document, resolving its own open questions autonomously as recorded assumptions, then an adversarial design review gates advancement. Trigger on "design this", "let's align on the approach", or "/team-design".
Compressed bug-fix pipeline — reproduce, write failing test, minimal fix, verify, and open a draft PR. Skips Question/Research/Design/Structure/Plan phases. Invoke ONLY on explicit pipeline intent — the user says "run the bug-fix pipeline", "team-fix this bug", or runs "/team-fix". The pipeline moves the tracker ticket, commits, pushes a branch, and opens a draft PR without stopping to ask: never infer pipeline intent from a plain request to fix a bug — that asks for an inline fix, not this p...
Execute the implementation phase. Includes test-first sub-step (writing failing tests, mechanical confirmation gate) and adversarial verification (5 parallel reviewers with hard-gate retry loop). Trigger on "implement this", "execute the plan", or "/team-implement".
Produce the tactical implementation plan from the structure. The plan is an autonomous artifact for the implementer — no approval gate at this phase (the design was already gated by the adversarial design review). Trigger on "plan the implementation", "spell out the steps", or "/team-plan".
Open the pull request after verification passes. Updates the changelog, optionally surfaces the tracking ticket, and closes out the topic. Trigger on "open the PR", "open a draft PR", or "/team-pr". To land/merge a reviewed PR (wait for CI, then squash-merge) use the separate /shipit skill — "ship it", "land the PR", and "land this" trigger /shipit, not this skill.
Decompose a feature description, ticket, or issue link into the QRSPI Question artifacts (task.md, questions.md). Trigger on "shape this idea", "decompose this task", or "/team-question".
Research a codebase area before making changes. Dispatches parallel read-only agents (file-finder + researcher) that read questions.md only — never task.md. Trigger on "research this", "explore the codebase for", or "/team-research".
Break the reviewed design into vertical slices with verification checkpoints. Runs autonomously and advances to PLAN — no approval gate. Trigger on "slice this up", "break the design into steps", or "/team-structure".
Prepare one or more isolated git worktrees — one per repository the topic touches. Router action — no agent. Trigger on "set up the worktree", "isolate this work", or "/team-worktree".
Full 8-phase autonomous feature implementation pipeline (QRSPI). Trigger on "hey team", "build a feature", "implement end to end", "autonomous implementation", or "/team".
Technical design document structure — problem statement, goals and non-goals, trade-off analysis, edge cases, and rollout planning. Load when writing or evaluating a design doc, TDD, or architecture proposal.
Test-driven bug-fix methodology — reproduce the defect first, write a failing test that captures it, then fix red-to-green. Load when fixing a bug, defect, or regression report.
Acceptance tests as immutable scope fence — loaded by test-architect and orchestrator to enforce test-before-implementation discipline and completion contracts
Test style rules and the flaky-test red-flag catalog — behavior-not-implementation, DAMP setup, narrow assertions, deterministic-input rules (clock, randomness, ordering, hermetic boundaries), the fidelity ladder, and the audit checklist. Load when writing tests, auditing test quality, or reviewing changed test files for flaky patterns.
Ticket-lifecycle discipline for tracker-linked pipeline runs — when a ticket moves to in-progress and in-review, how the PR links to the ticket with a conditional closing footer (including the multi-repo home-only rule), and why tickets are never closed by hand. Load when picking up a ticketed task, opening a PR for a ticketed topic, or deciding a ticket's tracker-state transition.
Live application verification procedure for the ux-reviewer agent — detect the project type (UI, API-only, or library), boot the application, exercise it with real requests, and evaluate the experience. Loaded when an implementation needs live smoke verification.
Investigate the design rationale behind code: what forces led to its shape, what alternatives were rejected, what edge cases or incidents motivated it. Builds a code anchor from git history, fans out parallel read-only investigators across every available evidence source, and synthesizes a confidence-tiered, citation-backed answer that separates what the record states from what is merely inferred. Read-only — it writes nothing. Use `how` for runtime behavior. Trigger on "why does X work this ...
Worktree isolation methodology — loaded by the router to run the entire Team pipeline in one or more isolated git worktrees, enabling parallel /team runs and features that span multiple repositories
Prose quality methodology for writing and assessing documentation. Grounded in plain language and ASD-STE100 Simplified Technical English in two modes — strict for instruction text, STE-flavored for descriptive prose.