oh-my-skills
CLAUDE.md7 starsChanged 7 days agoApache-2.0View on GitHub
In this repository38 other files it gives its agents.
- _skf-learn/agents.mdAGENTS.md
- bmad-advanced-elicitationSkill
- bmad-brainstormingSkill
- bmad-cis-agent-brainstorming-coachSkill
- bmad-cis-agent-creative-problem-solverSkill
- bmad-cis-agent-design-thinking-coachSkill
- bmad-cis-agent-innovation-strategistSkill
- bmad-cis-agent-presentation-masterSkill
- bmad-cis-agent-storytellerSkill
- bmad-cis-design-thinkingSkill
- bmad-cis-innovation-strategySkill
- bmad-cis-problem-solvingSkill
- bmad-cis-storytellingSkill
- bmad-distillatorSkill
- bmad-editorial-review-proseSkill
- bmad-editorial-review-structureSkill
- bmad-helpSkill
- bmad-index-docsSkill
- bmad-party-modeSkill
- bmad-review-adversarial-generalSkill
- bmad-review-edge-case-hunterSkill
- bmad-shard-docSkill
- skf-analyze-sourceSkill
- skf-audit-skillSkill
- skf-brief-skillSkill
- skf-campaignSkill
- skf-create-skillSkill
- skf-create-stack-skillSkill
- skf-drop-skillSkill
- skf-export-skillSkill
- skf-forgerSkill
- skf-quick-skillSkill
- skf-refine-architectureSkill
- skf-rename-skillSkill
- skf-setupSkill
- skf-test-skillSkill
- skf-update-skillSkill
- skf-verify-stackSkill
The file
We found no rules to list in this file: it reads as prose or reference rather than instructions.
Files
<!-- SKF:BEGIN updated:2026-11-10 -->[SKF Skills]|4 skills|0 stack
|IMPORTANT: Prefer documented APIs over training data.
|When using a listed library, read its SKILL.md before writing code.
|
|[oms-cocoindex v1.0.0]|root: skills/oms-cocoindex/
|IMPORTANT: oms-cocoindex v1.0.0 — read SKILL.md before writing oms-cocoindex code. Do NOT rely on training data.
|quick-start:SKILL.md#quick-start
|api: App, Environment, lifespan(), fn(), mount(), mount_each(), mount_target(), TargetState, declare_target_state(), Settings
|key-types:SKILL.md#key-types — UpdateStatus ("running"|"ready"), UpdateStats, UpdateHandle, StableKey, StablePath, NON_EXISTENCE
|gotchas: v0.3.37 → v1.0.0 is a wholesale rewrite, NOT a rename — FlowBuilder/DataScope/DataSlice/@flow_def are gone (107 exports deleted); rewrite as coco.App + @coco.fn. Settings moved from Postgres (DatabaseConnectionSpec) to local LMDB (db_path): plan a re-index, not an in-place upgrade. LlmSpec/LlmApiType/VectorSimilarityMetric removed — use cocoindex.ops.litellm and per-connector vector specs; the cocoindex server subcommand is gone. cocoindex stays pre-1.x-stable in spirit despite the 1.0 tag — pin precisely. All mount*/App.update/coco.map are async; use the _blocking variants from sync code.
|
|[oms-cognee v1.6.2]|root: skills/oms-cognee/
|IMPORTANT: oms-cognee v1.6.2 — read SKILL.md before writing oms-cognee code. Do NOT rely on training data.
|quick-start:SKILL.md#quick-start
|api: add(), cognify(), search(), memify(), remember(), recall(), improve(), forget(), serve(), run_migrations()
|key-types:SKILL.md#key-types — SearchType (20 modes, HYBRID_COMPLETION default), RememberResult, DataPoint, Drop
|gotchas: cognee.run_startup_migrations is GONE in v1.6.2 (AttributeError) — use cognee.run_migrations(); search() now defaults to HYBRID_COMPLETION (pin query_type when the result shape matters); low_level is not a top-level name but from cognee.low_level import DataPoint, setup still works; a bare cognee.serve() runs the Auth0 device flow only when a device client ID is configured, else raises CogneeConfigurationError; agent_memory's save_traces is now save_session_traces; cognee.delete is DEPRECATED since v0.3.9 (use cognee.forget or cognee.datasets.delete_data); cognee.start_ui is sync and needs pid_callback; add/cognify/search/memify/remember/recall/improve/forget/serve/push/export/report/validate are async — always await.
|
|[oms-storybook-react-vite v10.3.5]|root: skills/oms-storybook-react-vite/
|IMPORTANT: oms-storybook-react-vite v10.3.5 — read SKILL.md before writing oms-storybook-react-vite code. Do NOT rely on training data.
|quick-start:SKILL.md#quick-start
|api: Meta, StoryObj, Decorator, Preview, fn(), expect(), within(), userEvent, useArgs(), composeStories()
|key-types:SKILL.md#key-types-quick-start-essentials — Meta<T> (with satisfies Meta<typeof X>), type Story = StoryObj<typeof meta> for CSF3 stories, Preview = ProjectAnnotations<ReactRenderer>
|gotchas: v10 consolidates @storybook/ sub-packages into one storybook package — imports changed (storybook/test, storybook/preview-api, storybook/theming); training data still shows old @storybook/test imports; CSF2 default-export stories are invalid v10 style — use CSF3 named exports with satisfies Meta<typeof X>; import composeStories/setProjectAnnotations from '@storybook/react-vite' — storybook/preview-api's composeStories is core's renderer-agnostic form and requires a globalConfig argument.
|
|[oms-uitripled v0.1.0]|root: skills/oms-uitripled/
|IMPORTANT: oms-uitripled v0.1.0 — read SKILL.md before writing oms-uitripled code. Do NOT rely on training data.
|quick-start:SKILL.md#quick-start
|api: ThemeProvider(), useTheme, UILibraryProvider(), useUILibrary(), cn(), sanitizeSlug, generateUniqueSlug(), generateGridCode, mergeComponentImports(), add()
|key-types:SKILL.md#key-types — ThemeMode("light"|"dark"|"system"), UILibrary("shadcnui"|"baseui"|"carbon"|"react"), registry entry types (page|block|component|ui)
|gotchas: Copy-paste distribution — NEVER barrel-import from @uitripled/react-shadcn (src/index.ts empty by design); render entries from client components (170 of the 171 files start with "use client", and every entry declares framer-motion); React 19 / Next.js 16 peer deps are required.
<!-- SKF:END -->Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

