skill-craft

Plugin skill-craft in whichguy/skill-craft. Commands read from the repo's manifest — 2 days ago.

Skills (26)

• adversarial-review

  Have an independent model try to break a proposed change and return its findings as testable hypotheses, each with the smallest experiment that would refute it. Use before shipping any prompt, review-focus, card or harness change decided from experiments; for "adversarial review", "red-team this cha

• architect

  Design system architecture and make technology decisions. Uses a structured inline design or an available independent reviewer for comprehensive work. AUTOMATICALLY INVOKE when: - "design architecture", "what tech stack", "system design" - "how should I structure", "architecture for", "design system

• ask-agent

  A delegation skill, not an agent type. Ask native agents to work in the background, continue useful work in the main conversation, and incorporate their results when they return. Use for "ask an agent", named agent roles, parallel delegation, or launch-and-notify work.

• backchain

  Use when an implementation task needs a dependency-aware plan before coding: backward planner / backchain / precondition-first planning, dependency DAGs, elaborating incomplete plans, or scheduler-ready step graphs. Turns a natural-language coding request into a forward draft then backward-chaining

• c-plan

  Resolve ambiguous user prompts by choosing whether to answer now, answer with assumptions, ask 1–2 high-value clarification questions, replan, or stop. Use when the best response depends on hidden intent, audience, scope, constraints, risk, output format, or desired depth. - linux - macos skill_craf

• compare-prompts

  Compare two prompt versions (A vs B) by running both against a directory of test input files, then evaluating results on three dimensions in priority order: quality > tokens > time. **AUTOMATICALLY INVOKE** when user mentions: - "compare prompts", "which prompt is better", "prompt efficiency" - "A/B

• improve-agent

  Use when Improve should run in a fresh native agent instead of this conversation: start one agent that runs /improve in its own context, keep useful parent work going, then verify and relay its result. For Improve in this conversation, use improve. - linux - macos short-description: Run Improve in a

• improve-system-prompt

  Benchmark and compare system prompt variants (V2/V2a/V2b/V2c) for Sheets Chat by running test scenarios through the real GAS-side ClaudeConversation pipeline. Tests both system-placement and user-placement, then evaluates with heuristic scoring (ABTestHarness) and LLM-as-judge. Product-specific: req

• improve

  Use when a repository candidate needs a deliberate review-and-improvement loop: use recent Git history, make warranted changes, run meaningful checks, and repeat until a pass finds only trivial changes or none. Supports a read-only interpretation preview; not a one-off code review. - linux - macos s

• in-parallel

  Use for "in parallel" or when one goal should be divided among independent native agents and returned as one verified aggregate. One coordinator owns decomposition, progress, acceptance, and optional Git delivery. - linux - macos skill_craft: kind: mixed

• plan-dispatcher

  Use when executing or resuming an agreed dependency graph with one main dispatcher and parallel native workers: claim ready steps, preserve launch state, collect result evidence, verify outcomes, and identify successors. Planning belongs to Backchain or the caller; this skill executes the plan. - li

• plan-test

  Generate comprehensive tests for code. Uses an inline strategy or an available independent test specialist for complex components. AUTOMATICALLY INVOKE when: - "write tests", "test this", "generate tests", "add test coverage" - "test plan", "what should I test" - After feature implementation is comp

• prompt-align

  Compare an agent or skill prompt against its test harness skill for phase-model, skip-condition, and wiring consistency. Reports mismatches and identifies which file is authoritative.

• prompt-audit

  Audit an agent or skill prompt file for internal inconsistencies (phase numbering, behavioral contracts, terminology, stale references). Produces a Q&A with info-gain scores, a learnings section, and a remediation list. Use before any prompt migration.

• prompt-migrate

  TDD-based prompt migration — given a target agent/skill prompt and a remediation list, writes failing tests first, then updates the prompt to make them pass. Commits remain user-controlled.

• prompt-refine

  Full prompt-improvement workflow — runs prompt-audit to find inconsistencies, presents a remediation plan, then runs prompt-migrate to apply fixes and prompt-align to verify harness consistency. Use for any agent or skill prompt that needs structural repair.

• pushpress

  Sign in to and navigate PushPress Core, the gym-management system, through the owner's signed-in browser: members and leads, memberships and plans with recurring billing, invoices and payments, class schedule and check-ins, digital waivers, reports, settings, and the PushPress API/MCP tools. Use whe

• review-coverage

  Add a post-ship improve-to-exhaustion directive to a plan, or run that directive after implementation. Invoke like any skill: /review-coverage, "review-coverage on this plan", residual×2 after ship, or ensure the plan has a /goal-ready ## Review Coverage section. Not for pre-exit plan quality (use r

• review-fix-bench

  Compare two code-review prompt versions against supplied fixture ground truth using an explicitly configured external benchmark runner. Reports an F1-based verdict only when the runner completes both evaluations and comparison. - linux - macos skill_craft: kind: prompt-only

• rubric-eval

  Evaluate a prompt change against a rubric over a scenario catalog: run arms on a subject model (Grok by default), grade blind with one evidence-first judge, and decide by quality, then tokens, then time, with paired standard tests. Use when deciding whether to ship a change to a packet block, review

• shiploop-e2e-audit

  Run the ShipLoop test harness and audit its retained graph, review, test, product and incremental-change evidence. Use for ShipLoop mock checks, live one-shot E2E smoke/full campaigns, or review of existing trial output. Full Google Apps Script and Salesforce game cases require an authorized test de

• shiploop-run-review

  Review a ShipLoop E2E run on the owner's Run Review page: export the run's measured numbers, write findings, advice and options for the owner to tick, check that review file, and publish both to the page. Use after a ShipLoop E2E run or iteration, or when asked for the Run Review page, a run export

• shiploop

  Markdown-authoritative delivery harness. Start or resume once, follow the script's current action packet, and submit its exact callback until the script reports completion with an HTML achievement report. Use when the user says shiploop, ship the project, or requests a durable delivery loop. - linux

• skill-interop

  Use when authoring or reviewing a portable multi-host agent skill (Grok, Claude Code, Codex, Hermes): scaffold a prompt-only skill, make a skill host-agnostic, create skill layout, review skill for interop, or install across hosts. Covers prompt-first design, host matrix, anti-patterns (divergent co

• sport80

  Use for the USA Weightlifting Sport80 portal (usaweightlifting.sport80.com): the owner's personal member account (memberships, certifications, entries, results, orders) and club account (members, events, sanctioning, finance, affiliations, and the meets and results of the club's athletes), plus publ

• test-harness

  Run a repository's test suite and audit what the run did beyond its exit code: unintended writes to tracked files, leftover artifacts, live service calls, secret-shaped or traceback output. Optionally fix the product or the tests in a disposable worktree and rerun until clean, and always emit a mach

Subagents (4)

• backchain

  Use when an implementation task needs a dependency-aware plan before coding: backward planner / backchain / precondition-first planning, dependency DAGs, elaborating incomplete plans, or scheduler-ready step graphs.

• in-parallel

  Coordinate independent native workers, verify their returns, and report progress and optional Git delivery.

• shiploop

  Markdown-authoritative SDLC session harness with action-bound evidence.

• skill-interop

  Use when authoring or reviewing a portable multi-host agent skill (Grok, Claude Code, Codex, Hermes): scaffold a prompt-only skill, make a skill host-agnostic, create skill layout, review skill for interop, or install across hosts.

Hooks (5)

• PostToolUse

  ${CLAUDE_PLUGIN_ROOT}/skills/shiploop/scripts/shiploop-status-hook

• PostToolUse

  ${CLAUDE_PLUGIN_ROOT}/skills/shiploop/scripts/shiploop-keepalive-observe

• PostToolUse

  ${CLAUDE_PLUGIN_ROOT}/skills/shiploop/scripts/shiploop-skill-call

• Stop

  ${CLAUDE_PLUGIN_ROOT}/skills/shiploop/scripts/shiploop-keepalive-stop

• SessionEnd

  ${CLAUDE_PLUGIN_ROOT}/skills/shiploop/scripts/shiploop-keepalive-session-end

Similar plugins