aspire
claude.NET Aspire tooling for app host development and deployment.
1 skill
Engineering skills for issue backlog burn-down with runbook-driven validation, bug reports, one-issue wakes that resume from the issue tracker, and workspace setup, product mapping, build-failure diagnosis, complexity, consistency and conformance analysis, test design, scenario analysis, technical debt reviews, parallel change, yak-shave planning, whole-codebase untangling, capturing an unowned practice as a skill built from a catalog of primitives, one-step rabbit-hole teaching, and controlled technical writing.
Plugin engineering-workflow from marketplace sliekens in sliekens/agentic. Commands read from the repo's manifest — 4 days ago.
analyze-complexityAnalyze a code path, system, workflow, or architecture to separate inherent complexity imposed by requirements and external constraints from accidental complexity introduced by the current implementation, then define the invariants a simplification must preserve. Use when the user asks what complexi
backlogFront door to the workspace backlog. Walk the blocked issues with the user one at a time, or add a new item by routing it to the skill that owns that kind of item. A walk re-investigates each fork first. A fork with one good option, or a two-way door, is decided and unblocked without a question. Onl
blind-spot-coverageUse this skill when deciding whether a behavior deserves a test, or when the user wants test coverage for blind spots in a specific method. A qualifying behavior gets one integration test for its longest happy path and smaller unit tests for durable edge cases and blind spots. Leave it untested when
bug-reportFile one reported defect as an issue in the workspace issue tracker, with expected behavior, actual behavior, a repro or an explicit `none`, and evidence as identifiers rather than log or trace payloads. Use when the user reports a bug, says something is broken, or asks to file or write a bug report
capture-skillCapture a practice the user is introducing as one new skill built from the primitive catalog, after testing that none of the skills they name already own it. Use when the user says they have skills for some jobs but something is missing, says a practice is not captured or is not covered, says nothin
cause-effect-graphingBuild a directed graph connecting causes (inputs, preconditions) to effects (outputs, actions) through AND/OR/NOT logic nodes, then mechanically derive a decision table from it — for when conditional logic is too tangled to see clearly in prose or needs to be communicated visually to non-technical s
combinatorial-testingShrink an exponential combination space (feature flags, config options, API parameters) down to a minimal test matrix that still guarantees every pair of values is covered — pairwise/all-pairs testing, escalating to orthogonal arrays when 3-way interaction coverage is needed. Use eagerly whenever th
compoundEnd-of-session hill climb on the instruction surface. Encodes this session's friction into AGENTS.md, skills, or project docs so the next session does not pay the same tax. Do not use when the user is introducing a practice the current skills do not own (`capture-skill`).
cross-checkCompare two representations of one subject — design and implementation, specification and analysis, reference architecture and code, API documentation and handlers, threat model and deployed controls — on a grid of subject units against comparison facets, classify every cell as agreement, refinement
decision-tablesBuild a decision table that maps every meaningful combination of conditions to a specific outcome, and flags the combinations nobody has specified. Use eagerly whenever behavior is governed by combinations of independent yes/no conditions — authorization rules ("if role is admin AND resource is acti
design-space-explorationMap the dimensions along which an architectural or design decision can vary, place known options in that space, and surface the unexplored regions and implicit assumptions before a decision gets locked in. Use eagerly when the user is deciding *how* to build something and multiple valid approaches e
equivalence-partitioning-bvaTurn a parameter's valid/invalid ranges into a systematic set of test cases by partitioning the input space into equivalence classes and probing the boundaries between them, where bugs disproportionately cluster. Use eagerly whenever the user needs test cases for numeric ranges (age, quantity, price
expand-and-contractReplace a system with Parallel Change, also called Expand and Contract. Build the new structure beside the old one, migrate existing usages, then delete the old structure. A later slice waits until production has reached its checkpoint. An additive migration must be in production before code that us
fix-loopHarden a sound architecture one issue at a time — fix one issue, validate every phase against a repository validation runbook, file every out-of-scope problem found along the way as a new issue, then take the next issue — until only blocked issues remain or a release is needed to verify more. A simp
flaky-build-investigationDiagnose intermittent build, test, packaging, or CI pipeline outcomes by comparing equivalent runs and correlating logs, configuration, code, environment, ordering, and timing. Use when a build or test sometimes fails, a rerun passes, behavior depends on runner or execution order, or the user asks w
fmeaSystematically enumerate failure modes for a system or process, score each by severity, likelihood, and detectability, and produce a prioritized risk register (Risk Priority Number = S × O × D). Use eagerly whenever the user asks "what could go wrong", wants a pre-launch risk review of a critical fe
holeTeaches a person one step at a time, down a rabbit hole, and follows their signals. Use when they say teach me, explain this, go slowly, one thing at a time, /hole, or hole. Once a Hole lesson is already active, also use when they send clear, unclear, fuzzy, muddy, down, dig, surface, up, out, skip,
operator-setupCreate or update a personal operator profile under ~/.agents/projects/ — who the operator is, skill calibration, and collaboration preferences for this project. Only invoke when the user explicitly runs /operator-setup. Do not auto-trigger based on context.
product-mapCreate or update a product map, feature map, or capability map from an existing implementation. Use when no map exists, when documenting what a program does, or after code changes add, alter, or remove capabilities that an existing map must reflect. Produces current-state documentation that planning
realignAudit a codebase for divergent solutions to one recurring problem — several error-handling styles, competing HTTP clients, three ways to assemble the same query — by searching out every instance, clustering them by approach, electing a canonical form from what already exists, and proposing a migrati
scenario-analysisBuild a set of named, narrative scenarios — each a coherent story of who does what under what conditions and what should happen — to find requirements gaps and give stakeholders a shared vocabulary to validate against. Use eagerly for requirements analysis, checking whether user stories or acceptanc
scenario-designDiagnose the shape of a scenario-enumeration problem (multiple variables, states, conditions, or failure modes) and route to the right systematic technique — decision-tables, equivalence-partitioning-bva, combinatorial-testing, state-transition-testing, fmea, design-space-exploration, scenario-analy
state-transition-testingModel a system as states connected by event-triggered transitions, and find the (state, event) combinations nobody has defined — missing transitions, unreachable states, trap states, and undefined invalid-transition handling. Use eagerly whenever the user describes an entity with a status field that
ste-writingASD-STE100 Simplified Technical English, and the reply shape a reader with ADHD can act on. A standing style rule, not an on-request tool. Layer 1 governs the words of every text a human reads — chat replies, docs, READMEs, commit messages, PR text, code comments, error messages, release notes, tool
technical-debt-auditIdentify structural problems in a codebase and file each as a technical debt issue in the project's issue tracker, grouped under one project, milestone, or label (or, when the workspace tracks issues as committed files, as one file per issue plus an index). Use this skill when the user asks about st
untangle-codebaseUntangle a whole codebase in one pass, so agents working in it read less per change, break less without noticing, and debug faster. Lists every place the code gets "should these pieces change together?" wrong, redesigns from first principles, and carries the refactor through until subagents find not
work-onceRun one skill for one issue, write the returned next skill onto that issue, and exit. Use when a schedule wakes an agent, when the user runs /work-once, or when one tick should resume from the issue tracker. Prefer an open issue that already has next_skill and is not waiting on a person; a person un
workspace-setupInstall the workspace files that engineering-workflow skills depend on — the validation runbook (VALIDATION.md) that fix-loop reads, including whether changes land through pull requests or by direct push, and the issue-tracker record (ISSUE_TRACKER.md) that says where issues and work artifacts live
yak-shavePlan a replacement before Parallel Change. Sniff out a bad system or a feature the current architecture cannot hold, inventory what that system does, decide which capabilities to retain, retire, or introduce, and design the interface for that set. Then enter `expand-and-contract`. Use when the user
.NET Aspire tooling for app host development and deployment.
1 skill
Create, update, validate, operate, and troubleshoot Dev Container setups, including `devcontainer.json`, local or published Dev Container Features, and `devcontainer` CLI workflows.
1 skill
Market research for technology purchases: survey current products, compare independent evidence, and recommend only when asked.
1 skill
Synology utilities for managing local users and groups with synouser and synogroup.
1 skill
UGREEN NAS ACL utility for editing file and directory permissions with ugacltool.
1 skill
Deprecated. The STE Writing skill moved to the engineering-workflow plugin; install that instead. This package is now empty and will be removed in a future release.
Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Backend API design, GraphQL architecture, workflow orchestration with Temporal, and test-driven backend development
9 skills · 1 command · 8 agents
Long-term semantic memory for Claude Code, powered by OpenViking
5 skills · 1 command · 1 MCP server · hooks
AI-supervised issue tracker for coding workflows
1 skill · 1 agent · hooks
Create, inspect, validate, and assess furniture layouts with bounded next actions in Pascal through MCP.
3 skills · 2 MCP servers
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.