All authors
Claude Skills by rhawk117
github.com/rhawk11739 skills0 installs0 views
- Agent DebuggingUse when you are an engineer and a task's verification fails after your edit, to debug it alone, record each failed fix, and stop blocked at the third.Votes: 0GitHub stars: 2
- Agents AssembleUse when starting, resuming, or continuing the mightymodels per-task work loop for a staged ticket (after game-plan or one-shot): engineer dispatch per task, contract commands run before judgment checks, the `task` tool gating each task on receipts, citations and ownership, architect once on failure, whats-broken after that.Votes: 0GitHub stars: 2
- Ask An AdultEscalate a stuck decision to the wingman advisor and act on what comes back. Builds the escalation packet, dispatches wingman, then puts wingman's questions to the user through `AskUserQuestion` before any work resumes. Not for retrieving facts (send a scout), not for work you can simply do, and not for confirming a plan you have already committed to.Votes: 0GitHub stars: 2
- Baton PassHand the current session to the next one without losing what this session learned. Works from an active ticket (mid-sprint, or after stick-the-landing went green and review is next) or from a session with no ticket at all. Writes an objective snapshot from the recorded state first (the snapshot tool: tasks, checks at HEAD, ledger decisions, failed attempts, review state), runs what-we-know in interactive mode, asks in one AskUserQuestion call what the next session should focus on and what to ...Votes: 0GitHub stars: 2
- Becoming Merge VaderThe merge-vader reviewer's doctrine: judge whether a branch or a codebase is safe to merge by reading the whole diff, sending code-scout, web-scout and qualitylens for the facts the diff cannot show, grading findings on a four-step severity ladder across security, SDLC regressions, quality, documentation drift and plan conformance, and issuing a deterministic BLOCK, MERGE WITH CONDITIONS or CLEAR verdict. Not a way to start a review; review-circus does that.Votes: 0GitHub stars: 2
- Becoming Uncle BobThe uncle-bob reviewer's doctrine: grade a branch or a codebase against Robert C. Martin's SOLID principles, Clean Code smells catalog and Clean Architecture component metrics, with findings tied to named principles, evidence divided between the reviewer's own read and code-scout and qualitylens, and a letter grade whose arithmetic can be checked. Not a way to start a review; review-circus does that.Votes: 0GitHub stars: 2
- Break It DownSplit one mightymodels task that is too large into tasks of one reviewable unit of work each, and put the split to the user before anything changes. Use when the `task` tool's `start` refuses a task for more than four acceptance criteria or more than ten owned files, when an engineer or architect returns `too-large` with its cuts, or when a plan task is plainly several changes. Ends in one AskUserQuestion dialog showing every piece (id, intent, acceptance, owned files); only after the user an...Votes: 0GitHub stars: 2
- CrashoutUse when the user explicitly invokes crashout to record dissatisfaction, diagnose the failure, and await approval before resuming work.Votes: 0GitHub stars: 2
- Cross ExamineInterview the user about a plan, design, or decision until a shared understanding exists, at a depth the user picks first (Skim, Standard, or Relentless). Works the design tree in rounds: each round asks every decision whose prerequisites are settled, via AskUserQuestion only, two to four concrete options each, one recommended, pitched at a senior engineer with no rationale for asking. Facts go to scouts, decisions to the user, nothing assumed silently. Restates a decisions record after every...Votes: 0GitHub stars: 2
- Game PlanLarge-scope ramp for a mightymodels ticket: read ticket.yml and the issue, verify the ticket's claims with scouts, run cross-examine so the user decides the design before drafting, interview the user (AskUserQuestion) on how each risk is handled, then write the ticket's plan.md as a compaction-safe ledger: intent, approach, invariants that must hold throughout, dependency-ordered tasks each with deterministic acceptance criteria and the commands that verify them, non-goals, and risks with the...Votes: 0GitHub stars: 2
- Lets InvestigateRun a chat-first investigation as a gated loop: frame one target, dispatch scouts for repository facts and documentation facts, fold every report into a restated in-chat ledger (knowns, open questions, decisions, resources), then stop at an AskUserQuestion gate where the user chooses to dig further, redirect, or consolidate. Persists its ledger as rows in the state database and changes nothing else. Not for reviewing a branch or grading a codebase (review-circus), debugging with a known repro...Votes: 0GitHub stars: 2
- One ShotFast ramp into the mightymodels work loop from whatever context exists: an active ticket, a pasted issue, or a task described in chat. One AskUserQuestion dialog covers the questions open-ticket would have asked and that the context has not already answered (slug, scope, branch, progress view), then two or three scouts confirm the claims at HEAD, the task list is written with a checkable acceptance criterion per task, its commands are approved into the verification contract, and agents-assemb...Votes: 0GitHub stars: 2
- Open TicketTurn an understood problem into a staged unit of work: one AskUserQuestion interview (slug, tracker GitHub / Jira / both / none), then the ticket directory, a Findings rollup from the lets-investigate ledger or what-we-know, the GitHub issue and/or Jira ticket (a draft file when the CLI is absent) with a checked tracker body, the branch, ticket.yml with derived model routing, and a validated ticket row in the state database. Ends by asking whether to plan now (game-plan), go straight to one-s...Votes: 0GitHub stars: 2
- Prompting SubagentsBuild, review, or repair the dispatch packet for a mightymodels worker: choose the right worker (code-scout, web-scout, qualitylens, fact-checker, engineer, architect, intern, merge-vader, uncle-bob, gitty-up, wingman, terry-toolchain), fill its role template, resolve its model from ticket.yml, and read the report it returns; also the opening prompt for the next mightymodels session. Not for writing a prompt a human will paste into Claude Code or Copilot; that is ai-engineer's promptlint.Votes: 0GitHub stars: 2
- Prune TicketClose out a finished mightymodels unit of work: the close tool refuses while live work remains (unverified tasks, a live whats-broken.md, undecided or unfixed review findings, unpushed commits), compacts the ticket's recorded state into a 30-line archive at .mightymodels/archives/<slug>.md with a JSON sidecar (contracts and results, decisions, review outcomes), marks the ticket closed, proposes cascading documentation updates as diffs for the user's approval, then, on explicit confirmation th...Votes: 0GitHub stars: 2
- Review CircusReview a diff, branch, ticket, or whole codebase with the mightymodels persona reviewers. One AskUserQuestion gate sets depth (quick runs its reviewers on sonnet, standard and deep on opus), persona emphasis, and scope; the `review` tool records the run, mightymodels review-metrics and review-signals measure, merge-vader and uncle-bob report, and the tool reads their reports and merges overlapping findings, presented by id through AskUserQuestion. Only the findings the user picks go to remedi...Votes: 0GitHub stars: 2
- Stick The LandingClose an mightymodels sprint: gate the push on the task tool's ready action, push, open the PR with a checked body, have gitty-up watch CI, and route each failing check as a recorded C task (mechanical fixes to an engineer residual, then architect once; non-obvious causes to whats-broken), re-proving the whole verification contract at every new HEAD before re-pushing. On green, ask through AskUserQuestion whether to review now (review-circus) or hand off (baton-pass). Not for Jira sprint oper...Votes: 0GitHub stars: 2
- What We KnowConsolidate what is established about a problem, claim, behavior, or dependency into a knowns table with file:line or URL citations, an uncertainties list, and an analysis shaped by the question (causal chain for a behavior, verdict for a claim, fit for a dependency, SWOT for a proposed change), closing with a readiness read for the next stage. Reads the persisted lets-investigate ledger, treats entries from an older HEAD as leads to re-verify, and writes current verdicts back; assembles from...Votes: 0GitHub stars: 2
- Whats BrokenUse when CI has a non-obvious failure, a test resists repair, or behavior contradicts expectations after repeated verification.Votes: 0GitHub stars: 2
- Automate TaskTurns one automation request into one runnable Python script with inline dependencies, a command line, logging, a dry run and exit codes. Confirms the domain with the user, presents package and design options with a recommendation, maps a parallelism level to worker counts, keeps every technical choice the user stated, and checks the script before handing it to tactical-slop-review.Votes: 0GitHub stars: 2
- Build Web ServiceLeads the design of a Python HTTP service from a requirements interview to one vertical-slice handoff packet: classifies the service, brings in the contract, persistence and test design skills, and settles identity, deferred work, rate limits, caching and deployment lifecycle. The primary recipe is FastAPI, Pydantic v2 and async SQLAlchemy. Writes no project files.Votes: 0GitHub stars: 2
- Data AnalysisAnswers a question from data with a result that can be defended: fixes the question, the observation grain, the denominator and the baseline before choosing a method, validates along the deployment boundary without leakage, and reports effect size with uncertainty and what the evidence does not show. Hands back a rerunnable analysis script and a filled report.Votes: 0GitHub stars: 2
- Data EngineeringMakes data code correct first and cheap second: pins down the output, estimates sizes before running, checks schema and join contracts, chooses the engine, reads the query plan before tuning, and has results returned or published as artifacts instead of printed. Covers synthetic data and tests for data code. Hands back the changed code with the measurement behind every speed or memory claim.Votes: 0GitHub stars: 2
- Design PersistenceDesigns how a Python system stores durable records: record meaning and access patterns, invariants and state transitions, where each constraint is enforced, transaction and concurrency ownership, repository boundaries and a migration plan. Chooses the database from the requirements, writes no project files, and hands the persistence packet to design-tests.Votes: 0GitHub stars: 2
- Design TestsDesigns the tests that give evidence for a Python contract: scenarios chosen by ranked risk, each aimed at public behavior and able to fail for a plausible broken implementation. Writes no files: it briefs the test-engineer agent to write and run the tests, strict XFAIL where the implementation is missing, and hands the scenario-test packet and test files to tactical-slop-review.Votes: 0GitHub stars: 2
- Enterprise DesignTurns business intent into a caller-facing Python contract before implementation: outcomes, a rule table, the architecture boundary, and the exact public types, signatures and error classes, shown to the user as declarations. Keeps partial success, duplicates, expected rejection and dependency failure distinct. Writes no project files and hands the contract packet to design-persistence.Votes: 0GitHub stars: 2
- Tactical Slop ReviewReviews a Python pull request, branch or codebase against the expert's engineering guide and writes one file: PYTHON-REVIEW.md with findings or REFACTOR-PLAN.md with an ordered refactor plan. Facts come from the plugin's MCP tools and pylens subagents, every citation is checked by a tool before it supports a finding, and the review never edits code.Votes: 0GitHub stars: 2
- GradersNo description providedVotes: 0GitHub stars: 2
- Build A LoopDesign a reliable agent loop from a plain description of the work. Picks the loop shape, defines what one iteration may touch, sets the evidence each success criterion needs, writes a stop condition that measures progress instead of counting turns, and emits a LOOP.md contract plus the Claude Code configuration and verification hook that enforce it. Use this whenever someone wants an agent to keep working on its own - a loop, a harness, an autonomous or long-running or overnight run, a self-v...Votes: 0GitHub stars: 2
- Create Agents MdGenerate an evidence-based AGENTS.md for the current repository by dispatching two explorer subagents (toolchain and verification, conventions and structure), and optionally a CLAUDE.md that imports it with @AGENTS.md. Use it to create, regenerate, audit or merge repository instruction files: AGENTS.md, CLAUDE.md, CLAUDE.local.md and cursor, windsurf or cline rules.Votes: 0GitHub stars: 2
- Create HooksInteractive builder for Claude Code hooks. Use it to create, add or set up a hook, or to ask what hooks would suit a repository. It asks how the hook ships (project, project-local, personal, plugin), when it runs and what it is for (failure mode, context injection, tracking), takes one or several plain descriptions or infers candidates from the repository's CI, formatter and runner, routes to permissions, a skill, a subagent, instructions or a git hook when that mechanism fits better and says...Votes: 0GitHub stars: 2
- Create McpInterview-driven builder for MCP servers in Python (uv project, official `mcp` SDK, src layout with one package per tool). Use it to create, scaffold, design or add an MCP server for Claude Code. It asks where the server is installed (plugin, project, local or user scope), whether it is local only or a network service, what it does and what problem it solves, then one round per tool (inputs, outputs, side effects, whether it pauses to ask the person), infers resources and prompts, records the...Votes: 0GitHub stars: 2
- Create RulesInteractive builder for Claude Code rule files (Markdown files under .claude/rules/ with optional paths frontmatter and an XML-sectioned body). Use it to create, add, write or scaffold a rule, a set of coding conventions or a style guide for Claude, or to ask how paths scoping works, even when the user only describes the behavior ("make Claude always do X in these files"). It asks where the rule lives (project or personal), which files it governs, takes the conventions from chat or a file, ro...Votes: 0GitHub stars: 2
- Create SkillInteractive Claude Code skill creator, scenario-first. Use it to create, write, scaffold, improve, test or evaluate a skill (SKILL.md plus optional scripts, references and assets). It asks where the skill ships (personal, project, plugin), sets invocation and tool pre-approvals by checkbox, takes a plain description of what the skill does and what problem it solves, proposes a name and use-case scenarios the user accepts or rejects, records them as claude plugin eval cases with graders before...Votes: 0GitHub stars: 2
- Create SubagentInteractive builder for Claude Code subagents (agent files with YAML frontmatter and an XML-sectioned Markdown body). Use it to create, scaffold, design or add a subagent, specialist agent, reviewer agent or persona, or to ask how to write an agent file, even when the user only describes the job ("I want an agent that triages CI failures"). It asks where the agent ships (plugin, project, personal), scans what already exists, checks that a subagent is the right mechanism, drives the tool, mode...Votes: 0GitHub stars: 2
- HumanizerRewrite or review prose to remove signs of AI-generated writing (puffery, AI vocabulary, em dashes, chatbot artifacts, stacked hedging, formulaic structure) while keeping every fact and the author's voice. Use when editing, reviewing, or humanizing text, Markdown files, docs, READMEs, PR descriptions, or commit messages, and when another task wants natural human-sounding prose as its final step.Votes: 0GitHub stars: 2
- Plan PluginPlanning interview for a Claude Code plugin; ends in a phased plan and an empty plugin shell, never a build. Use whenever the user wants to create, design, plan, scope or extend a Claude Code plugin, says "I want a plugin that...", "bundle our X conventions", "package this for the team", "what should go in the plugin", or describes several customisations at once for one purpose, even without the word "plugin". Asks what problem the plugin solves and for whom, classifies it, settles name, keyw...Votes: 0GitHub stars: 2
- PromptlintUse when writing, improving, or reviewing a coding-agent prompt for Claude Code.Votes: 0GitHub stars: 2
- Tune Skill DescriptionsTunes Claude Code skill descriptions so the right skill loads for the right request. It runs the vibe-code tune loop over a labeled trigger set: real headless Claude Code routing (or fresh subagents) judges which skills each request loads, Claude proposes one rewrite at a time, the loop keeps a rewrite only when held-out validation requests improve, and the winners are written back into the SKILL.md files.Votes: 0GitHub stars: 2