Explore skills
Showing 40981–41010 of 71536 skills
Sorts a cost-cutting list against an issued design into accept, accept with an alternate, and block, with the reasoning written out per item across design intent, performance, lifecycle cost, schedule, risk transfer, and reversibility. Trigger on "VE review", "value engineering", "review this VE list", "where can we cut", "cost reduction options", "VE round 2", or a pasted contractor proposal with substitutions and savings figures. Works with any contract and any specification format. Performance requirements come from the user's own specification and contract; the skill supplies the sorting method and never a code threshold or a performance value from memory. Produces a recommendation memo, not a directive.
DavidCho1999/archaiflow-skills
Stars: 1Claude CodeCodexAssembles the site environmental criteria block a project needs before any structural or envelope design starts: wind, snow, seismic, ice, rain, and flood parameters, each recorded with the source it came from. Trigger on "wind speed for this site", "ground snow load", "site hazard parameters", "design criteria block", "seismic parameters", "rainfall intensity", "wind-snow-lookup", or a pasted site location with a request for design values. Works in any jurisdiction. The skill knows which parameters a design needs and what each one feeds; the values come from the user's own code maps, official hazard tool, or authority, supplied by typing, pasting, or naming a file. It never supplies a hazard value from memory or from web search, and reports every parameter it could not source as a gap. Returns mapped parameters only, never design pressures or loads.
DavidCho1999/archaiflow-skills
Stars: 1Claude CodeCodexThis skill should be used when the user provides a site address, parcel info, or zoning lookup text and needs a structured zoning summary for early design. Trigger on 'zoning summary', 'zoning lookup', 'site zoning for [address]', or pasted zoning portal output. Targets North American projects (US + Canada). Generates a worksheet markdown in `docs/zoning/` and updates the project zoning index.
DavidCho1999/archaiflow-skills
Stars: 1Claude CodeCodexCreate branded architecture, IT current-state, flowchart, sequence, state machine, ER/data model, timeline, swimlane, quadrant, radar/spider, polar chart (polar/radial lollipop), loop/flywheel, nested, tree, org chart, layer stack, Venn, pyramid/funnel, treemap, bar, line, Gantt and scatter charts, high-level, process, medallion, data flow, DP integration, DP security matrix, Sankey, fishbone, Wardley map, kanban, user journey, deployment, dependency graph, UML class, story map, or database schema diagrams as standalone HTML/SVG/PNG. Redraw .drawio/.drawio.png/.drawio.svg or Mermaid .mmd sources at a chosen size/detail; onboard brand tokens from a website; add semantic patterns, callouts, accessible motion, or sketchy/hand-drawn styling.
drafael/coding-harness
Stars: 1Claude CodeCodexAuto-activate when the user mentions NGLess, ngless, NGS processing, metagenomics pipelines with NGLess, writing .ngl scripts, or is working in the ngless repository (Rust source at src/). Also activate when the user asks about preprocessing FASTQ reads, mapping reads to references, counting features, or parallel sample processing in the context of NGLess scripting or development.
ngless-toolkit/ngless
Stars: 152Claude CodeCodexDynamic multi-agent workflows for Zed Agent and zcode. Use when the user says "ultracode", "workflow:", "/deep-research", or wants broad multi-file work with planning, parallel execution, verification, or crash-resume.
Suraj1235/open-dynamic-workflows
Stars: 50Claude CodeCodexUltracode-style dynamic workflows for Zed Agent and zcode. Use when the user says "ultracode", "workflow:", "/deep-research", or wants broad multi-file work with planning, parallel execution, verification, or crash-resume.
Suraj1235/open-dynamic-workflows
Stars: 50Claude CodeCodexFetch a GitHub issue, branch, implement with TDD, open a PR
phel-lang/phel-pdo
Stars: 6Claude CodeCodexBackground context for the Electronic Bookkeeping Act (電子帳簿保存法) in the shinkoku tax filing plugin. Contains requirements for electronic bookkeeping, scanner storage, mandatory electronic transaction data storage, and shinkoku's compliance status. This skill is not user-invocable — Claude loads it automatically when responding to electronic bookkeeping compliance questions.
kazukinagata/shinkoku
Stars: 372Claude CodeCodexBackground context for housing loan tax credit (住宅ローン控除) in the shinkoku tax filing plugin. Contains eligibility requirements, credit limits, calculation rules, and interaction with furusato-nozei for the current tax year. This skill is not user-invocable — Claude loads it automatically when responding to housing loan tax credit questions or calculations.
kazukinagata/shinkoku
Stars: 372Claude CodeCodexBackground context for invoice-system input tax credit rules (仕入税額控除) in the shinkoku tax filing plugin. Contains eligibility requirements, the 6 permanent exceptions (帳簿のみ保存の恒久特例), transitional measures for purchases from tax-exempt businesses, and storage requirements. This skill is not user-invocable — Claude loads it automatically when responding to input tax credit questions under the invoice system.
kazukinagata/shinkoku
Stars: 372Claude CodeCodexBackground legal and regulatory context for the shinkoku tax filing plugin. Contains the standard disclaimer about the scope of tax information provided, the relationship to the Tax Accountant Act (税理士法), and tool limitations. This skill is not user-invocable — Claude loads it automatically when generating tax-related responses that require a disclaimer.
kazukinagata/shinkoku
Stars: 372Claude CodeCodexTerse output mode — strips filler/articles/hedging, ~75% token reduction. Activate whenever: context is filling up, user says be brief/terse/caveman/less tokens, or CAVEMAN_TRIGGERED appears in context. Persists every response until CAVEMAN_RELEASED or user says stop/normal mode.
DangQuangSE/team-development-skills
Stars: 19Claude CodeCodexSuggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
DangQuangSE/team-development-skills
Stars: 19Claude CodeCodexTerse output mode — strips filler/articles/hedging, ~75% token reduction. Activate whenever: context is filling up, user says be brief/terse/caveman/less tokens, or CAVEMAN_TRIGGERED appears in context. Persists every response until CAVEMAN_RELEASED or user says stop/normal mode.
DangQuangSE/team-development-skills
Stars: 19Claude CodeCodexSuggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
DangQuangSE/team-development-skills
Stars: 19Claude CodeCodexTerse output mode — strips filler/articles/hedging, ~75% token reduction. Activate whenever: context is filling up, user says be brief/terse/caveman/less tokens, or CAVEMAN_TRIGGERED appears in context. Persists every response until CAVEMAN_RELEASED or user says stop/normal mode.
DangQuangSE/team-development-skills
Stars: 19Claude CodeCodexSuggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
DangQuangSE/team-development-skills
Stars: 19Claude CodeCodexTerse output mode — strips filler/articles/hedging, ~75% token reduction. Activate whenever: context is filling up, user says be brief/terse/caveman/less tokens, or CAVEMAN_TRIGGERED appears in context. Persists every response until CAVEMAN_RELEASED or user says stop/normal mode.
DangQuangSE/team-development-skills
Stars: 19Claude CodeCodexSuggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
DangQuangSE/team-development-skills
Stars: 19Claude CodeCodexSecrets architecture reference for node-template — when to use OpenBao+ESO vs GitHub env secrets, which operation pattern fits which write/rotate/add flow, the load-bearing invariants from the spec, the YAML catalog + Zod-loader the script consumes, and where to find the canonical implementation. Use when adding/rotating a secret, designing a service that consumes secrets, debugging an ExternalSecret or writer-role login, deciding between substrate and Compose-infra routing, touching `pnpm secrets:set` / `scripts/secrets/` / `scripts/lib/secrets-catalog-loader.ts` / `nodes/<node>/.cogni/secrets-catalog.yaml` / `infra/secrets-catalog.yaml` / `infra/k8s/argocd/{openbao,external-secrets}/` / per-node ExternalSecret manifests, or evaluating any new workflow that touches secret values. Triggers: 'add a secret', 'add a node secret', 'rotate a key', 'OpenBao', 'ESO', 'ExternalSecret', 'secrets-catalog', 'catalog tier', 'A1', 'A2', 'B-tier', 'writer role', 'bao login', 'vault-action', 'vault-config-operator', 'secrets-manage', 'secret in GH env vs OpenBao', 'where do I put this credential', 'per-node catalog'.
cogni-dao/cogni
Stars: 4Claude CodeCodexStandard for building Cogni research views — dashboard slices, wallet/market analytics, trader comparisons, P/L curves, bet histograms, anything that aggregates over `poly_trader_fills`, `poly_trader_position_snapshots`, `poly_market_outcomes`, or any other large operational table. Use this skill any time you are about to write a new database query that supports a research, dashboard, comparison, or analytics view — whether the user calls it a "research view", "comparison panel", "P/L tab", "histogram", "metric", "slice", "research tab", "dashboard chart", "scorecard", or anything similar. ALSO use this skill when migrating existing JavaScript-side aggregations to SQL, when investigating an OOM in any wallet/market/research read path, when reviewing PRs that add new SELECT queries against fills / snapshots / outcomes, when adding new entries to `/api/v1/poly/research/*`, when designing what goes on the Research tab, or when anyone proposes a `LIMIT N` band-aid on a fill-scanning query. Strongly prefer this skill — naively writing `db.select().from(polyTraderFills).where(...)` is the failure mode that produced bug.5012; this skill exists specifically to prevent that class of incident from recurring.
cogni-dao/cogni
Stars: 4Claude CodeCodexEnd-to-end OpenRouter key + spend + outage playbook for Cogni. Use when investigating unexplained OpenRouter spend ('who used opus/model X?', 'why is my bill high'), a suspected leaked/compromised API key, a prod AI outage that surfaces as `provider_unavailable` / `402` / LiteLLM `Insufficient credits`, or when you must rotate/cap/kill an OpenRouter key across the fleet. Encodes the diagnostic decision tree (provider_unavailable = upstream, truth in `service=litellm` Loki; 402 = account balance dry; a model NOT in the deployed LiteLLM catalog can't come from Cogni infra), the attribution method that needs a MANAGEMENT key (/api/v1/{keys,activity,credits,key}), the rule-out-local sweep, the LiteLLM-is-Compose-on-VM + OpenBao-SSOT converge facts, the full break-glass rotation runbook (mint capped → OpenBao fleet-wide → deploy-infra converge → BEHAVIOR-verify → delete), and the CARDINAL rule: never leave a compromised key alive/uncapped — cap-or-disable on suspicion, delete the moment prod is verified on the replacement. Triggers: 'openrouter', 'who used opus', 'opus-4.8 spend', 'unexplained openrouter charges', 'leaked api key', 'compromised key', 'rotate openrouter key', 'provider_unavailable', '402 insufficient credits', 'prod AI down', 'litellm out of credits', 'openrouter activity', 'management key', 'cap the key', 'kill the leaked key', 'openrouter attribution', 'which key does prod use'.
cogni-dao/cogni
Stars: 4Claude CodeCodexAuthoritative reference for the cogni-template test pyramid and production-like e2e test topology — enforcement vs test layers, vitest configs, infra prereqs, GitHub/DoltHub test org boundaries, the cogni-operator-test app, what agents can/can't run locally, coverage tracking, and the non-obvious gotchas that bite every time. Use this skill whenever the user is writing a new test, asking "which layer does this belong in", debugging a flaky test, hitting CWD/env-loading issues, deciding between unit/component/stack/external, running any `pnpm test:*` or `pnpm arch:check` / `pnpm lint` command, working with testcontainers, touching fake adapters or `APP_ENV=test`, troubleshooting skip-gates, seeing errors from `.env.test` not loading, wondering about coverage or whether a test will run in CI, or trying to decide whether to run stack/e2e locally vs defer to CI. Also trigger when the user mentions mocking the database, Privy/GitHub App construction errors in tests, the smee proxy, `pnpm test:smee`, validating the agent API, the candidate/test GitHub App, `cogni-test-org`, `cogni-test-nodes`, node-formation flight testing, or anything that smells like test-environment setup. Short-circuits the usual "spelunk through docs + configs" lookup.
cogni-dao/cogni
Stars: 4Claude CodeCodexAd-Hoc Raw Upload to Databricks
rbutinar/ade-ops
Stars: 0Claude CodeCodexDatabricks Job & Notebook Lineage (Lite)
rbutinar/ade-ops
Stars: 0Claude CodeCodexExecute SQL on a Databricks SQL Warehouse
rbutinar/ade-ops
Stars: 0Claude CodeCodexExecute Databricks Notebooks / Jobs
rbutinar/ade-ops
Stars: 0Claude CodeCodexDatabricks Workspace Status
rbutinar/ade-ops
Stars: 0Claude CodeCodexList Available Fabric Capacities
rbutinar/ade-ops
Stars: 0Claude CodeCodex