В каталоге 183 730 навыков в 14 категориях.
Ollama proxy — one endpoint that routes to multiple Ollama instances. Drop-in Ollama proxy replacement for localhost:114...
Build RAG systems with Ollama local + cloud models. Latest cloud models include DeepSeek-V3.2 (GPT-5 level), Qwen3-Coder...
Review an Ollama deployment for unauthenticated API exposure, model pull from untrusted registries, CORS misconfiguratio...
Create, update, and validate a persistent Windows service for Ollama (auto-start on boot), including setting OLLAMA_MODE...
Auto-configure Ollama when user needs local LLM deployment, free AI alternatives,or wants to eliminate hosted API costs....
Configure auto-configure Ollama when user needs local LLM deployment, free AI alternatives, or wants to eliminate hosted...
Beginner-friendly reverse-engineering workflow for Ollvm Deobfuscation. Use it to collect evidence, choose static or dyn...
OlmoEarth MLX: Spatio-Temporal Earth Intelligence
Build ontology logs (ologs) from problem descriptions using categorical foundations. Use when designing problem taxonomi...
Econometrics skill for OLS regression and linear models. Activates when the user asks about: "run OLS", "linear regressi...
Get Project Olympia status update and M&A due diligence progress
Olympus Kernel architecture, OHM minting, treasury, roles, Cooler loans and Crane integration.
Use this skill when the user wants to pivotal operations manager command line tool.
Drafts Operations and Maintenance agreements for energy facilities covering scope, performance standards, compensation,...
Write and review a business-level App Spec — domain model, workflows with ROI, stories with failure paths, platform gap...
Apply the skills collection's UPGRADE_NOTES.md after an upgrade. Re-syncs installed tracker and browser-provider descrip...
Repo-local extension of om-approve-merge-pr - the develop → main promotion pull request merges with a merge commit, neve...
Approve (submit an approving review) and squash-merge a PR given only its number, refusing when the QA gate or a blockin...
Repo-local extension of om-auto-continue-pr - the PR state is re-read before every push, because a human may merge or cl...
Resume any open PR — started by `om-auto-create-pr` or opened outside the pipeline. Claims it, resumes in an isolated wo...
Repo-local extension of om-auto-continue-pr-loop - the PR state is re-read before every push, because a human may merge...
Advanced om-auto-continue-pr for PRs started by om-auto-create-pr-loop — claims the PR, resumes from the first non-done...
Repo-local extension of om-auto-create-pr - per-phase test, copy and generated-file discipline, commit style and the dep...
Run an arbitrary autonomous task end-to-end and ship it as a PR against the configured base branch. Drafts a Progress-tr...
Advanced om-auto-create-pr for long, multi-step spec implementations needing resumability and strict step tracking — run...
Repo-local extension of om-auto-fix-issue - how an issue reference is recognised in a Cezar task prompt, this repository...
Fix or implement a tracker issue end to end from a single command — takes an issue id or a plain problem description (fi...
Repo-local extension of om-auto-fix-pr - the open-thread exit criterion the stabilization loop gets.
Drive an open PR to merge-ready from its number — merges the latest base, then loops review-autofix (om-auto-review-pr),...
money-tracker.online extension of the installed om-auto-implement-spec skill. Spec lifecycle bookkeeping - the metadata...
Implement an existing spec and ship a verified, reviewed, ready PR. Resolves the spec by path, name, issue, or spec-PR n...
money-tracker.online extension of the installed om-auto-manage-issues skill. Human-hold labels, category mapping, the re...
Bring existing tracker issues up to standard without implementing anything — applies missing SDLC labels, clarifies laco...
Repo-local extension of om-auto-qa-pr - the viewports, themes, hydration wait and console policy that decide PASS/FAIL i...
QA a PR's UI change in a real browser through the configured browser-provider descriptor — first ensuring the PR has bee...
Turn a window of merged PRs (date, PR-number floor, or last 7 days) into a manual QA scenarios report for human testers...
Repo-local extension of om-auto-review-pr - QA routing for user-facing changes and the human-only visual judgement this...
Review or re-review a PR by number in an isolated worktree. Runs the `om-code-review` skill — or, for spec-only design P...
Security report over a window — merged PRs since a date or PR number (default last 7 days), or one branch or spec. Runs...
Paranoid OWASP-style security analysis of ONE unit (a PR, spec, or branch diff) — severity-ranked findings, non-obvious...
Draft a CHANGELOG.md release entry in an emoji-driven format for every PR merged since the last release, then delegate t...
money-tracker.online extension of the installed om-auto-write-spec skill. Repo-specific spec sections and the spec PR's...
Autonomously turn a brief or FR issue into a spec landed on a ready PR — runs om-spec-writing --autonomous (defaults pos...
Turns a product brief (its Scope and Key flows) or a spec's Phasing into a tracker backlog — epics, stories with accepta...
Divergent conversation before any artifact exists — open questions one at a time, alternatives including building nothin...
Verify that the current branch is ready to publish by running every configured validation command in order, fix straight...
Close the tracker issues that recently merged PRs authoritatively fixed — via `fixes`/`closes`/`resolves` keywords or `c...
Repo-local extension of om-code-review for money-tracker.online - the context sources, the severity map and the suppress...
Repo-local extension of om-code-review for aitl-starter. Adds project rules from docs/ENGINEERING_STANDARDS.md (layering...
Review a diff, branch, or PR against correctness, security, breaking-change, and quality standards — runs the validation...
Write, rewrite, or refresh an AGENTS.md (repo root or one package/module) from the actual codebase — Always / Ask First...
Author a new OM skill from a brief, or split an oversized SKILL.md into layered references/ files — conservatively, behi...
Guide a product discovery conversation and write product-brief.md with the problem, evidence, scope, decisions, and the...
Take one part of an installed dependency into the repo for customization via the eject recipe the dependency ships — dec...
Turn a real agent failure into one reproducible eval-harness case plus the smallest knowledge change — failing case firs...
Design in a design tool (Figma or similar) on the repository's design system — write a brief for a new screen using only...
Repo-local extension of om-fix - test-first at the seam, catalogue copy, generated files and the suppression ban.
Implements the minimal code change identified by the om-root-cause step, adds regression tests, and runs the configured...
Turn a PR into tracked follow-up work — paste a PR or PR-comment link to extract the actionable ask and open a follow-up...
Read knowledge shipped inside installed dependencies — detect the ecosystem and exact installed version, locate AGENTS.m...
Grounded gap analysis of requirements against the platform an app builds on — client docs become an Epic/Story tree whos...
Read-only router for "which skill should I use?", "what do I do next?", "how do I do X here?". Builds the answer at run...
Run and create integration/E2E tests by exploring the live app with the configured browser provider, preserving reposito...
LLM-as-judge for a coding-agent session or an eval-harness result — checks controller attestations first, then project g...
Scan open pull requests via the configured tracker, classify merge readiness from labels, reviews, CI, and mergeability,...
Build a neutral clickable low-fi prototype from a product brief during discovery, after the first synthetic panel and be...
Shared PR opener for the auto pipeline — commits the worktree, pushes, reuses an existing PR or opens a ready (non-draft...
Parse CRE Offering Memorandums. Extract NOI, cap rate, occupancy, rent roll, property details, financial projections fro...
Classify finished pipeline runs from the configured tracker — clean single pass, hard recovery, loop checkpoints, or cau...
Repo-local extension of om-pr-autopilot - the PR state is re-read before every push, because a human may merge or close...
Diagnose what state one open PR is actually in — unfinished plan steps, missing review, unresolved conversations, red CI...
Audit a spec before implementation — readiness gate, backward-compatibility check against BACKWARD_COMPATIBILITY.md, com...
Repo-local extension of om-prepare-issue - the tenant, money and visual sections every issue here carries, the plan-stag...
Create one well-formed tracker issue from a brief without implementing it — dedupes against existing issues and PRs, lin...
Repo-local extension of om-prepare-test-env - how this app boots for QA (local D1, throwaway .dev.vars, the seed, the 30...
Prepare a reusable, technology-agnostic environment for local tests and QA. Compiles discovery into cross-platform launc...
Runs a manual QA session for a PR, issue, or branch — publishes an interactive runbook the tester works through in paral...
Review all currently unreviewed open pull requests, newest first, using the om-auto-review-pr skill and respecting in-pr...
Read-only root-cause analysis for a tracker issue. Identifies the bug's location and the minimal change surface so the n...
One-time pipeline configurator. Inspects the repo (default branch, validation scripts, labels), asks a few questions, wr...
Adds the product layer to a repository that om-setup-agent-pipeline already configured — one yes per product role, a dis...
Publicly share a sanitized coding-agent session plus a ZIP of the files it generated, then file a harness-feedback issue...
Run only the tests a change can affect — diffs the branch against its base, maps changed files to affected units via the...
Repo-local extension of om-spec-writing - what a spec here cites, the clean-room rule and how phases are sized.
Write and review feature specifications to staff-engineer standards. Skeleton-first drafting with a hard Open Questions...
Builds a panel of personas from real material, interviews them under decision pressure (never stated preference), and wa...
Diagnose a failure from its symptom — reproduce, classify the broken invariant, route via the repo AGENTS.md Task Router...
Evidence-first design review of a PR's UI. Walks the changed screens in a real browser, performs the user's tasks, and p...
Extract the repository's design contract (tokens, component registry, screen archetypes, conventions) into .uxproof/ so...
Turn a vague product, UI/UX, or AI feature idea into a decided direction. Use when shaping a feature, simplifying an ove...
Read-only triage gate for an autofix chain. Decides whether a tracker issue is a real, still-unfixed defect on the curre...
Draft and revise academic prose against a rubric, evidence, and citation requirements. Use for essays, reports, literatu...
Inspect or set OmA approval posture (suggest, auto, full-auto) for autonomous workflow control.
Evaluate system boundaries and architectural tradeoffs. Use for architecture decisions, design reviews, and ADRs.
Run autonomous staged execution loops until acceptance passes or a blocker is reached.
Implement server APIs, authentication, and application data access. Schema modeling and query tuning use oma-db.
Define a product/UI blueprint with durable decisions, interaction states, constraints, and verification hooks.
Install or verify the oma CLI and its runtimes (bun, uv, serena) before any oma-* skill, agent, or workflow runs an `oma...
Explore goals, constraints, and alternative approaches before choosing a design. Use when the user requests ideation or...