dstack-core
claudecodexCross-project workflows for planning, implementation, review, verification, and delivery.
86 skills
DStack workflows for documentation, editorial prose, and copy.
Plugin dstack-writing from marketplace dstack in gosuda/dalcom-skills. Commands read from the repo's manifest — 3 days ago.
articulateUse when the user knows what they mean but cannot express it completely or clearly. Not for discovery, ideation, or style-only editing: use unslop for style.
copywritingUse when asked to write or fix product/marketing copy, landing pages, UI strings, brand voice, AI tells, an end-of-article CTA, or a hook/lede. Not for whole articles.
docs-updateUse when documentation has drifted from code changes and the user asks to synchronize it. Delivers the fixes as local commits or as a reviewable PR after preview approval. Not for ADRs, architectural rationale, or writing an isolated document (use docs-writing).
docs-writingUse when asked to write, restructure, or audit documentation with Diataxis types, or to draft a feature docs page or diagram source. Not for ADRs or architectural rationale.
good-readmeUse when the user asks to create, rewrite, review, or polish an open-source README. Produces one evidence-backed README.md in a fixed section order and checks it with five gates. Not for remote, credential, publish, deploy, or irreversible changes.
humaniseur-frUse when the user supplies French text that reads like AI output and asks to naturalize it. Rewrites hollow formulas, stacked connectors, systematic hedging, heavy nominalization, and unintegrated anglicisms while keeping register and meaning. French only; not for English (use humanizer-plain-englis
humanizer-korean-plainUse when Korean prose reads as machine-generated (기계 문체), machine-translated (번역투), or bureaucratic (행정 문체) and must be rewritten as plain, natural Korean without changing its meaning. Covers rewriting, drafting from notes, and reviewing notices, emails, READMEs, and explanatory text. Not for contro
humanizer-korean-steUse when Korean technical documents such as runbooks, procedures, manuals, or operating guides (절차서, 운영 지침, 매뉴얼, 장애 대응 문서) need controlled wording: one action per step, conditions before actions, unified terms, and warnings placed before risky steps. Unofficial Korean profile inspired by ASD-STE100.
humanizer-plain-englishUse when asked to make English plain, clear, natural, and readable while keeping its meaning and voice. Not for ASD-STE100 controlled-language work: use humanizer-simple-english-asd-ste100. Not for stripping AI tells from otherwise clear prose: use unslop. Not for Korean or French: use humanizer-kor
humanizer-simple-english-asd-ste100Use when asked to rewrite technical English toward ASD-STE100 Simplified Technical English: short, unambiguous sentences, one instruction per step, consistent terms, and AI-style padding removed. An STE-inspired pass, not certification. English only; not for general readability (use humanizer-plain-
proofUse when asked to publish, read, comment on, suggest to, or pull a Proof collaborative markdown document. Not for proofreading, math proofs, or test evidence.
reorderUse when asked to reorder a drifted listing under one stated principle, moving items only and rewording nothing. Not for deliberately ranked listings.
rewrite-clean-v0Use when a document or file has been edited piecemeal and reads as sediment. Not for re-deriving a code subsystem contract: use breaking-driven.
rhythmic-tasteUse when the user says "give this rhythm", "vary the structure", or "the sections all read the same". Not for judging an artifact''s overall taste: use taste.
Cross-project workflows for planning, implementation, review, verification, and delivery.
86 skills
DStack workflows for marketing and viral growth, from audience research to opportunity scouting.
28 skills
DStack workflows for executing plans, orchestrating subagents, and bounded autonomous loops.
20 skills
DStack workflows for shaping intent into approved plans, specs, and task lists.
19 skills
DStack workflows for native systems, toolchains, and performance.
18 skills
DStack workflows for security review, vulnerability triage, and defensive implementation.
16 skills
AgentDB (external: maintained in ruvnet/agentdb, pinned to commit 27678c3, plugin 3.6.0): agentdb's own standalone MCP server pinned to [email protected] (vector memory with get/list/update/delete for records, patterns and skills, hybrid keyword + vector episode search and an opt-in local cross-encoder, an opt-in aidefence injection guard on memory writes, reflexion, skills, outcome feedback, capabilities report), a memory-specialist agent, 3 skills, /agentdb-status, and the agentdb mod guard that keeps secrets out of memory and refuses delete/reset unless allowed. Complements ruflo-agentdb, which reaches AgentDB through ruflo's server
3 skills · 1 command · 1 agent · 1 MCP server
Rewrite AI-sounding text so it reads like the writer without changing what it says.
1 skill
5 skills + 35 modes + Material Passport pipeline. Includes v3.6.7 cross-model audit gate and v3.6.8 generator-evaluator contract.
5 skills · 16 commands · 4 agents · hooks
OpenAPI specification generation, Mermaid diagram creation, tutorial writing, API reference documentation
3 skills · 1 command · 5 agents
Provision direct cloud access (Vertex AI, Bedrock, or LLM gateway) for the Claude Microsoft 365 add-in. Generates the customized manifest, walks through Azure admin consent, and writes per-user config via Graph extension attributes.
1 skill · 9 commands
Build, launch, grade, and schedule Claude Managed Agents (CMA) in your own Anthropic account — a plugin re-implementation of Anthropic's launch-your-agent reference skill (Apache-2.0; independent, not a fork). Every session starts with a goal (./my-agent/goal.json, opt-in SessionStart hook, driven by /cs-goal); loop_compiler.py compiles it into a bounded grade->iterate loop (max_iterations 1..20), a recurring cron scheduled-deployment loop, or a single-pass interview->stage->launch workflow. 6 skills: orchestrator (context: fork goal router) + interview + stage-launch + grade-iterate + run-without-you + wrap-up. 18 stdlib-only deterministic scaffolders (no network/API calls; live launches emitted as BYOK curl that never prints the key), 4 agents, 8 commands, hooks, 5 references, 4 assets. Validators enforce CMA limits. Distinct from engineering/agent-harness (generic domain loop) and write-a-skill (authors Claude Code skills, not CMAs).
6 skills · 8 commands · 4 agents · hooks
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.