Skip to content

Claude Skills by jgwill

github.com/jgwill

79 skillsA× 77B× 1C× 10 installs0 views

Fidelity AuditATwo-stage audit — spec compliance first, code quality second. Required after every implementer task before a wave can close. Independent of self-claim. Includes a cheap post-wave audit pattern using a free model.ai-agentsbashVotes: 0GitHub stars: 4
Screen ImplementerAReimplement ONE screen from a design bundle as production code in the target codebase''s stack. Visual fidelity to the prototype, but native to the target. Designed for delegated waves where each screen is a subordinate lane handled by a fresh task agent.ai-agentsshellreactVotes: 0GitHub stars: 4
Hermes Copilot Launch PreparationAPrepare a Miadi Copilot wave as a machine-readable payload with exact plugin roster, lane contracts, validation scripts, transcript audit hooks, recovery prompt, and closure gate.ai-agentsgoshellVotes: 0GitHub stars: 4
Hermes Copilot Wave ClosureAClose a completed Miadi Copilot/Hermes wave by auditing transcript evidence, changed files, validation, commit partitioning, Chronicle impact, and follow-up trigger decisions.ai-agentsgitVotes: 0GitHub stars: 4
Context Layer PromotionAEvaluate reviewed Miadi material for promotion by separating provenance, spec, wiki, and context-layer concerns before drafting durable outputs.ai-agentsgitVotes: 0GitHub stars: 4
Promotion Decision RecordAWrite an artefact-friendly markdown record of Miadi promotion decisions so later RISE and wiki waves can resume from explicit layer choices and blockers.ai-agentsVotes: 0GitHub stars: 4
Skills DirectorySkills Directory Look up any of 103,619 scanned skills — grade, score, and every finding. Free.Check a skill
Wiki Promotion DraftADraft Miadi wiki updates from already-reviewed material while preserving provenance, spec, and context-layer boundaries.ai-agentsrailsgitVotes: 0GitHub stars: 4
Storyweaver Voice Episode PacketAPrepare voice episode files: script.md, narration.txt, revision-notes.md, episode.yaml, source context, index-update guidance, and split/recovery notes.ai-agentsVotes: 0GitHub stars: 4
Forge Wave ScriptATakes a WavePlan (from scan-and-plan or from user) and invokes Wave Script Forge to write a complete executable orchestration bash script, then verifies and reports it.ai-agentsbashVotes: 0GitHub stars: 4
Resume Wave PrepAResumes an interrupted wave-forge preparation from prior artefacts. Reads existing WavePlan, review result, and generated script to determine where to continue: at review, replan, or reforge.ai-agentsbashVotes: 0GitHub stars: 4
Review Wave PlanAAdversarial review of a WavePlan before forging. Checks agent validity, path existence, desire alignment, and structural completeness. Returns ADVANCE or REVISE with specifics.ai-agentstypescriptpythonVotes: 0GitHub stars: 4
Scan And PlanAOrchestrates the full scan → plan flow: invokes Orchestration Context Scanner on all target directories and plugin sources, then invokes Orchestration Wave Planner to produce a WavePlan.ai-agentsgoVotes: 0GitHub stars: 4
Model Routing Policy SimulatorAGenerate an OpenClaw model-routing matrix from task, risk, context, tool, cost, latency, memory, confidence, and review inputs.ai-agentsVotes: 0GitHub stars: 4
Openclaw Model Routing BootstrapABootstrap the OpenClaw model-routing study by reading fixed-order context, validating or creating the launch manifest, enforcing write scopes, token caps, issue links, and stop conditions.ai-agentsVotes: 0GitHub stars: 4
Openclaw Plugin Gap ContractsAReconcile OpenClaw study plugin gap names and contracts while keeping live connector implementation out of read-only research phases.ai-agentsgitVotes: 0GitHub stars: 4
Openclaw Rise Rispec ScaffoldAScaffold OpenClaw model-routing rispecs using Reverse-engineer -> Intent-extract -> Specify -> Export and the standard 5-file rispec shape.ai-agentsgorailsVotes: 0GitHub stars: 4
Openclaw Source LedgerAMaintain OpenClaw study source ledgers with evidence types, evidence quality, contradiction handling, and strict claim-to-source rules.ai-agentsdocumentationVotes: 0GitHub stars: 4
Stckin Artefact ReportAWrite replayable findings and next-wave notes into the active Miadi deep-search artefact folder after an orchestration or STCKin work session.ai-agentsgitVotes: 0GitHub stars: 4
Stckin Orchestration ScaffoldAScaffold or refine a Miadi-native Copilot orchestration kit by adapting source plugin patterns to STCKin, deep-search, and artefacted session work.ai-agentsgitVotes: 0GitHub stars: 4
Stckin Wave BootstrapABootstrap Miadi STCKin and orchestration-kit work by studying mia-awesome-copilot, Miadi STC hooks, and prior deep-search artefacts before editing.ai-agentsgitVotes: 0GitHub stars: 4
Miadi Gemini Session PrepAPrepare a reliable Miadi Gemini CLI orchestration session with charter, source ledger, extension recommendations, replayable launch script, and compact attention-only reporting.ai-agentsbashgitVotes: 0GitHub stars: 4
Chart PathAT4 · Chart path's practice. How a structural tension chart an agent writes reaches Asterion, who may see it, the words the teams use for repository, checkout, chart memory, project, seat and workspace, what Miadi's /stc-config holds that Asterion must keep when it moves into Miadi, and how a chart is steered without Asterion writing its file. Use when registering or syncing a coaia-narrative memory in Asterion, when a chart does not show on Asterion, before registering anything from a private...ai-agentsgoshellVotes: 0GitHub stars: 4
Chronicle EpisodeAThe one entry point for Miadi Chronicle episode work on any host and from any agent. Mint a vessel with mkepisode or the episode API, prove the five stages (created, committed, pushed, registered, receipt-verified), register on the chronicle medicine wheel, relate and sync an inquiry with inquiry-weave, author lineage, raise and answer Attention items, open a ceremony (a talking circle by default) held in a circle of people and bound to an episode, add a Miadi review to an episode (which open...ai-agentspythonrustVotes: 0GitHub stars: 4
Deep SearchAThis skill should be used when the user asks for "deep research", "thorough research", "research everything about", "cover every angle", "comprehensive research on", "spawn research agents", "/deep-research", or wants multi-agent parallel research on any topic. Also triggers when user says "research this for me", "find everything about", "I need a research doc on", or describes needing exhaustive coverage of a subject. NOT for quick lookups or single questions — this is for producing comprehe...ai-agentsgobashVotes: 0GitHub stars: 4
Mcp Remote QmdCConfigure a companion agent (Claude Desktop, Claude Code, or any MCP client) to consume a remote QMD index over SSH via the mia-qmd `qmd mcp-remote` proxy. Triggers on: "set up remote qmd", "configure qmd over ssh", "connect to eury qmd", "install mcp-remote-qmd", "/mcp-remote-qmd", or when the user wants an agent to search Guillaume's curated knowledge ground (wikis-md, GUILLAUME-md, iaip-artefacts-md, miadi-md, llms-txt, mia-code-rispecs-md) without bash-shelling whispering_inquiry.sh. NOT ...ai-agentsshellbashVotes: 0GitHub stars: 4
Miadi Mightyeagle Issue 263AUse this skill for jgwill/Miadi#263 security-remediation orchestration work: resume from the live issue workspace, revise the issue-263-derived rispecs, and run explicit implementer/review/promotion handoffs without creating a new plugin.ai-agentsrustgoVotes: 0GitHub stars: 4
Miadi ReactARead the emoji reactions people leave on GitHub issues and comments, as Miadi stores them, and know the open choices for letting a reaction hand work to an agent's tmux lane. GitHub sends no webhook for reactions; Miadi polls the Reactions API and keeps each reaction under owner/repo/issue and comment in Redis. Use the `miadi-react` CLI as it is (scan, show, events, watch, poll), or plan the next step with the human. Triggers on "reaction", "who reacted", "emoji on the issue", "thumbs up on t...ai-agentsgobashVotes: 0GitHub stars: 4
Proposal VisualizationAPresent a proposal, plan, migration or architecture as one HTML page that a human can read, comment on and approve at a glance. The page has a before/after figure that draws only what changes, figures coloured by who owns each part, a clickable wireframe with an ownership overlay, and every decision, question, risk and step as a coded card that comments can anchor to. Host-neutral: any agent that writes HTML can follow it. Triggers on "visualize the proposal", "make an artifact so we can comm...ai-agentsgonodeVotes: 0GitHub stars: 4
Use Design Bundle Integration KitAUse this skill when Claude Code needs to integrate a Claude Design bundle (claude.ai/design) into a target codebase via Copilot CLI orchestration. Triggers on: "implement the design bundle", "integrate the claude design", "wire up the bundle into <repo>", "run the design integration waves", or any task that already has a PDE folder with `bundle/` extracted and an `orchestration/` subfolder pending. Tells Claude Code (the main-session orchestrator) how to dispatch waves to the `miadi-design-bu...ai-agentsrustbashVotes: 0GitHub stars: 4