All authors
Claude Skills by sunholo-data
github.com/sunholo-data73 skills0 installs280 views
- Test Coverage GuardianAnalyze test coverage, identify gaps, detect dead code, and improve test quality. Use when user asks to check coverage, review tests, find untested code, or improve test robustness.Votes: 0GitHub stars: 34
- Trace DebuggerDebug performance issues and understand code flow using AILANG telemetry traces. Use when user asks to debug slow compilation, analyze benchmarks, find bottlenecks, investigate hangs, or understand system behavior.Votes: 0GitHub stars: 34
- Use AilangWrite and run AILANG code with correct syntax. Use when user asks to write AILANG programs, fix AILANG syntax errors, run AILANG code, or needs help with AILANG syntax. Includes version checking, syntax validation, and common patterns.Votes: 0GitHub stars: 34
- Wasm DebuggerDiagnose AILANG WASM browser failures — frozen pages, silent loadModule hangs, type-checker stack overflows, missing effect handler bridges, version drift between wasm/ailang.wasm and the .ail source. Use when a browser demo using AILANG WASM behaves differently than the CLI, or when the page freezes without a console error.Votes: 0GitHub stars: 34
- Ailang PackagesCreate, validate, and publish AILANG packages with correct conventions. Use when user asks to create a new package, fix package errors, add dependencies, publish to registry, or import packages. Also use when encountering `IMP010`, `LDR001`, `MOD010`, or `export type` errors during package development.Votes: 0GitHub stars: 34
- Benchmark RunnerRun ai-coding-lang-bench benchmark trials against AILANG, monitor active sessions, analyze results (cost/tokens/time/pass-rate), compare prompt strategies, and identify language gaps. Use when user says "run benchmark", "benchmark AILANG", "run trials", "analyze results", "find gaps", "monitor benchmark", or "compare prompt strategies".Votes: 0GitHub stars: 34
- Cli Doc MaintainerKeep the AILANG CLI and its docs true to the dispatch table. Use when adding or renaming a command, adding a flag or env var, auditing CLI docs, fixing a doc that cites a command the binary rejects, or when `ailang --help` and a page disagree.Votes: 0GitHub stars: 34
- Cloud Cascade DebugInvestigate why an `ailang publish` cascade didn't fire (or fired and silently failed) on multivac. Inspects gcloud logs across the registry validator, the Pub/Sub `ailang-cascade` topic, and the coordinator's task queue. Use when the user says "auto-cascade didn't work", "why didn't multivac pick this up", "check cloud logs for cascade", or "the dependents didn't get bumped".Votes: 0GitHub stars: 34
- Cloud SetupSet up Claude Code cloud/mobile environments for AILANG development. Use when starting a new cloud session, when tools are missing (Go, make, gh), or when user says "setup cloud", "setup environment", or mentions mobile Claude Code.Votes: 0GitHub stars: 34
- Coordinator HelperManage coordinator daemon tasks, approve/reject work, monitor autonomous agents. Use when user asks to delegate tasks, check task status, review agent work, manage the coordinator, or use GitHub-driven approval workflow.Votes: 0GitHub stars: 34
- Eval Gap FinderFind AILANG vs Python eval gaps and improve prompts/language. Use when user says 'find eval gaps', 'analyze benchmark failures', 'close Python-AILANG gap', or after running evals.Votes: 0GitHub stars: 34
- Gemini Cli HelperRun Gemini CLI commands from Claude with correct Node version. Use when user asks to run Gemini CLI, test Gemini traces, or debug Gemini telemetry.Votes: 0GitHub stars: 34
- Github Issue TriageTriage open GitHub issues on sunholo-data/ailang by verifying each one against the current code on origin/dev, then closing (with evidence), labelling, transferring or escalating it. Use when the user asks to "check issues", "triage issues", "sync issues", "what issues are open", "clean up the issue tracker", or after a release to find what shipped.Votes: 0GitHub stars: 34
- Local Model OnboardingOnboard a new on-device model to the Mac Studio eval rig end-to-end — hardware size/shape feasibility gate, OpenRouter quality pre-screen, ollama pull, opencode+pi cross-harness registration in models.yml, and continuous-rotation wiring. Use when the user wants to add/test/try a new local (Ollama) model on the rig, asks whether a model is the right size/shape for the hardware, or wants to evaluate a candidate before committing rig time.Votes: 0GitHub stars: 34
- Local Ollama EvalRun AILANG agent-mode evaluations against local Ollama models on a dedicated Mac Studio rig. Use when user mentions "local ollama", "gemma4", "run eval locally", "smoke tier on the rig", "ollama benchmark", or wants to start/monitor a local-model eval rotation. Covers the M-EVAL-LOCAL-OLLAMA + M-EVAL-LOCAL-OBSERVABILITY workflow.Votes: 0GitHub stars: 34
- Mission BriefRead-only steering brief for attended mission sessions — dashboard + directive channel + live loop health + inbox, then hand the wheel to Mark. Use when the user says "mission brief", "catch me up on the mission", "steering session", or opens a fresh thread for in-person steering or meta-loop updates. NOT for running iterations — that is mission-control.Votes: 0GitHub stars: 34
- Motoko AnalyzerRun ONE motoko-mission diagnostic and improvement cycle through five non-skippable ordered gates — observe (failure-mode segmentation), diff (capture the exact wire bytes), cheap-confirm, build, validate + record. Use when investigating why motoko disengages or grinds wrong on benchmarks, when analyzing the motoko↔pi harness gap, when the user says "run a motoko cycle", "analyze motoko", "why is motoko failing", or when fired unattended by the motoko-mission launchd job.Votes: 0GitHub stars: 34
- Pr MonitorRobustly observe, audit, and respond to GitHub PRs we author (or have changes-requested on). Use when waiting on review feedback, when the user says "any new comments?", when reviewing CR/maintainer asks, or when replying to inline review threads. Codifies lessons from missing the `/pulls/N/reviews` endpoint and from `since=` cursor resets.Votes: 0GitHub stars: 34
- Trace DebuggerDebug performance issues and understand code flow using AILANG telemetry traces. Use when user asks to debug slow compilation, analyze benchmarks, find bottlenecks, investigate hangs, or understand system behavior.Votes: 0GitHub stars: 34
- Ailang Core TriageTriage an incoming AILANG core report — bug, feature request or observation — into a backlog row with a recommendation, cross-referenced against existing design docs. Use when a message arrives on the ailang-core inbox. Does NOT write design docs; it decides whether one is warranted.Votes: 0GitHub stars: 34
- Mission Loop ChangeChange or add a mission loop safely — routing/lanes, schedule and cadence, driver code, plists, and adding a whole new mission. Use when editing tools/launchd/mission-control.sh, any dev.ailang.mission-* plist or mission-*.env, changing a mission's models/fallbacks/interval, porting a fix to the world fork, bootstrapping a new mission loop (e.g. for ailang-parse), or when asked why a mission-loop change "didn't take". Covers reach, live-edit hazards, drought simulation and reload.Votes: 0GitHub stars: 34
- Perf SweepMonthly AILANG runtime performance and memory sweep — re-measures workload p95 latency, peak RSS of five memory-shaped programs (live-data recursion, effect results, log lines, string building, deep-trace ratio) and allocation-per-op of the evaluator and builtins, diffs against the last banked snapshot in .ailang/state/perf/, names what got slower or fatter with the command that produced each number, and exits 2 on a regression. Use when the user says "perf sweep", "monthly sweep", "is ailang...Votes: 0GitHub stars: 34
- Simplicity AuditWeekly codebase-complexity audit — re-measures the v1.0.0 simplicity gates (language-core closure, command and flag counts, os.Getenv routes, duplicate symbol names across packages, packages without a doc comment, skill trees, instruction-surface bytes, tracked files, root clutter), diffs against the last banked snapshot, and names what got more complex. Use when the user says "simplicity audit", "weekly audit", "is the codebase getting more complex", "find duplicate implementations", "codeba...Votes: 0GitHub stars: 34