All authors
Claude Skills by 1225Sakura
github.com/1225Sakura42 skills0 installs66 views
- Agent Doc DisciplineWriting-time discipline for documents agents consume (agent-facing docs, specs, tickets, .dsh/skills/) — every rule checkable and carrying a why, steps before reference, one meaning in one home, no restating what the environment already saysVotes: 0GitHub stars: 8
- Ai Slop CleanerClean AI-generated code slop with a regression-safe, deletion-first workflow and an optional reviewer-only modeVotes: 0GitHub stars: 8
- AnalyzeRun read-only deep repository analysis and return a ranked synthesis with explicit confidence, concrete file references, and clear evidence-vs-inference boundariesVotes: 0GitHub stars: 8
- Ask NavigatorNavigator lane — chart a foggy effort (destination unclear, questions not yet stateable) into a map of decision tickets, work the frontier one ticket per session, then hand the collapsed decisions off as a mission brief. Wayfinding, not building — it produces decisions, never deliverables.Votes: 0GitHub stars: 8
- AskSecond-opinion advisor lane — route a question to an independent subagent (optionally with a different role card) and persist the answer as an ask artifactVotes: 0GitHub stars: 8
- AutopilotAutonomous end-to-end pipeline from a brief idea to verified working code, driven by the native dsh goal mechanismVotes: 0GitHub stars: 8
- AutoresearchStateful single-mission improvement loop with strict evaluator contract, markdown decision logs, and max-runtime stop behaviorVotes: 0GitHub stars: 8
- Best Practice ResearchBounded best-practice research wrapper using official/upstream evidence first, with a cited recommendation and explicit handoffVotes: 0GitHub stars: 8
- CancelCancel any active omd execution mode (autopilot, ralph, team, ralplan, deep-interview) and clean up mode stateVotes: 0GitHub stars: 8
- DebugDiagnose the current omd session or repo state using mode state, notepad, logs, and focused reproductionVotes: 0GitHub stars: 8
- Deep InterviewSocratic deep interview with mathematical ambiguity gating before explicit execution approvalVotes: 0GitHub stars: 8
- DeepinitDeep codebase initialization with hierarchical AGENTS.md documentationVotes: 0GitHub stars: 8
- DesignCanonical repo-local DESIGN.md workflow for product, UI/UX, and frontend decision source of truthVotes: 0GitHub stars: 8
- DrydockLay the keel of the shipyard harness in any repo — the 4-pillar shared environment (Context, Rules, Tools, Standards) across its surfaces (CLAUDE.md, project skills, design-system, scripts, shared context) so that every human and agent inherits the same design language and anyone can ship. Run once per repo; re-run with --check to audit drift.Votes: 0GitHub stars: 8
- ExecuteCarry an approved task through to working, verified codeVotes: 0GitHub stars: 8
- External ContextSpawn parallel document-specialist subagents for external web searches and documentation lookupVotes: 0GitHub stars: 8
- GraphDeclarative DAG pipeline contract — deterministic graph semantics and journal-based crash recovery, executed model-driven in omd until the phase-2 runtime landsVotes: 0GitHub stars: 8
- HarborHarbor intake for external work — the captain only handles unresolved decisions. Sweeps incoming issues and PRs, verifies every claim before disposition, reuses every decision already made, and hands the maintainer a docket whose pending items each carry one question with options, recommendation, impact and evidence. Agent-autonomous for facts and for actions covered by standing authorization; signed for every new judgment. Never merges.Votes: 0GitHub stars: 8
- HudStatus visibility for omd sessions — the five-element HUD contract (mode, round, story, agents, todos) and its three shipped surfaces: MCP hud_render/hud_summary, the web GUI right-sidebar HUD panel (client half), and the /oh-my-dsh/hud.json data routeVotes: 0GitHub stars: 8
- LaunchShipyard's governed delivery pipeline — converge the mission, synthesize a durable spec, decompose vertical-slice tickets with blocking edges, run the frontier in parallel via team, close with verification, and report with a full decision log. Two entry gates — the yard gate (drydock audit) and the fog gate (an effort whose destination is unclear is routed to ask-navigator (preferred) / deep-interview/plan (fallback) before this pipeline starts). Humans own the checkpoints where there is no u...Votes: 0GitHub stars: 8
- LoftLoft the shape before cutting steel — answer a design question that prose cannot settle by building a throwaway artifact — a pure logic module in a clickable shell, or structurally different UI variants behind one route. The captain reacts to the artifact; the answer folds into the decision; the artifact never docks. Use when a design question stalls in words or a spec discussion reaches "we would have to see it".Votes: 0GitHub stars: 8
- Minimal Code DisciplineYAGNI-ladder coding discipline for writing changes — existence-first, reuse before writing, dependency ladder, shortest correct diff, with non-negotiables that must never be minimized awayVotes: 0GitHub stars: 8
- Omd DoctorDiagnose an oh-my-dsh installation — host version, registration counts, Config model resolvability, MCP smoke, .omd/ writability, probe matrix — as a checklist table with fix suggestionsVotes: 0GitHub stars: 8
- Omd SetupInstall and configure oh-my-dsh — dsh plugin add (npm or local path), Config keys explained, verify with /omd-doctor, update and uninstall flowsVotes: 0GitHub stars: 8
- Performance GoalEvaluator-gated performance optimization workflow — baseline measurement, bottleneck analysis, small reversible optimizations, re-measurement loop, gated completionVotes: 0GitHub stars: 8
- PlanStrategic planning with optional interview workflow and consensus modeVotes: 0GitHub stars: 8
- Project Session ManagerWorktree-first isolated dev environments for issues, PRs, and features — git worktree + provider CLI (gh/jira) methodology adapted to dsh sessionsVotes: 0GitHub stars: 8
- RalphPRD-driven fresh-agent persistence loop — iterates until every story passes with command evidence and an independent verifier signs offVotes: 0GitHub stars: 8
- RalplanConsensus planning entrypoint that auto-gates vague ralph/autopilot/team requests before executionVotes: 0GitHub stars: 8
- ReleaseRepo-aware release assistant — derives release rules from repo/CI inspection, caches them in .omd/RELEASE_RULE.md, then guides version bump, notes, tag, and publishVotes: 0GitHub stars: 8
- RememberReview reusable project knowledge and decide what belongs in project memory, notepad, or durable docsVotes: 0GitHub stars: 8
- ResearchInvestigate an open question and return grounded, sourced findingsVotes: 0GitHub stars: 8
- ReviewEvaluate finished work for defects, risk, and simplification before it shipsVotes: 0GitHub stars: 8
- Self ImproveAutonomous evolutionary code improvement engine with tournament selectionVotes: 0GitHub stars: 8
- SkillManage local dsh skills — list, add, remove, edit, search, info, sync, setup wizardVotes: 0GitHub stars: 8
- SkillifyTurn a repeatable workflow from the current session into a reusable dsh skill draftVotes: 0GitHub stars: 8
- TeamExplicit-invocation multi-agent pipeline — the lead orchestrates role-carded subagents through a five-stage pipeline with mandatory stage handoffsVotes: 0GitHub stars: 8
- TraceEvidence-driven tracing lane that orchestrates competing tracer hypotheses as parallel subagentsVotes: 0GitHub stars: 8
- UltragoalDurable multi-goal initiative — ordered stories with attempt counts and per-story evidence persisted under .omd/ultragoal, driven by dsh's native goal mechanism (create_goal/update_goal) with a final review gateVotes: 0GitHub stars: 8
- VerifyVerify that a change really works before you claim completionVotes: 0GitHub stars: 8
- Visual VerdictStructured visual QA verdict — compare a generated UI screenshot against reference images and return a strict JSON verdict (score, pass/revise/fail, differences, suggestions) that drives the next edit iterationVotes: 0GitHub stars: 8
- WikiLLM Wiki — persistent markdown knowledge base under .omd/wiki that compounds across sessions (Karpathy model), maintained with plain file toolsVotes: 0GitHub stars: 8