Menu
SkillsMP a collecté 24 skills depuis geehexx/library-ops. Ouvrez un skill pour examiner sa source et ses détails.
Affichage de 24 skills collectés sur 24.
Use when a task is ambiguous, needs Codex Plan mode, native user-question tooling, /goal setup, MCP elicitation handling, or when a subagent reports blocked, partial, low-confidence, or needs-user status.
Langue du texte source : anglais
Use when a task mentions RTK, code graph, code-review-graph, Serena, ast-grep, Repomix, MCP tooling, context optimization, token pressure, fan-out, blast radius, symbol retrieval, repo maps, or agent meta-system configuration.
Langue du texte source : anglais
Deploy applications to Render by analyzing codebases, generating render.yaml Blueprints, and providing Dashboard deeplinks. Use when the user wants to deploy, host, publish, or set up their application on Render's cloud platform.
Langue du texte source : anglais
Use when a session ends, checks fail, user corrections arrive, or AGENTS/skills/process instructions may need improvement.
Langue du texte source : anglais
Use when aligning Spec Kit artifacts, community presets, Task Master PRD content, and generated task graph.
Langue du texte source : anglais
Use when designing repo-local wireframes, accessibility annotations, role-aware navigation, or UI flow design.
Langue du texte source : anglais
Use when the task requires automating a real browser from the terminal (navigation, form filling, snapshots, screenshots, data extraction, UI-flow debugging) via `playwright-cli` or the bundled wrapper script.
Langue du texte source : anglais
Persistent browser and Electron interaction through `js_repl` for fast iterative UI debugging.
Langue du texte source : anglais
Use when starting, inspecting, updating, expanding, validating, or completing Task Master tasks for the project.
Langue du texte source : anglais
Use when designing exact search, PostgreSQL full-text search, lexical ranking, or search tests.
Langue du texte source : anglais
Use when configuring GitHub repo, branch protections, PR template, CI, commitlint, CODEOWNERS, or release controls.
Langue du texte source : anglais
Use when preparing SemVer, changelog, release PRs, protected branches, deployment, or production readiness evidence.
Langue du texte source : anglais
Help the user define a concrete, measurable goal before starting work, especially when they ask to use the goal tool, create a goal, set an objective, clarify success criteria, or turn a fuzzy intention into a quantitative outcome. Use this skill for goal…
Langue du texte source : anglais
Use when implementing Django models, managers, selectors, forms, views, APIs, migrations, or tests for one feature, with Pyright-first Python checks.
Langue du texte source : anglais
Use when creating or revising the canonical PRD, capability tree, dependencies, acceptance criteria, or task decomposition.
Langue du texte source : anglais
Use when conducting PR review, pre-merge review, security review, architecture review, or task-done validation.
Langue du texte source : anglais
Use when auditing and improving skill definitions, triggers, references, naming, and progressive-disclosure hygiene.
Langue du texte source : anglais
Use when evaluating Spec Kit community presets before install, adaptation, or rejection.
Langue du texte source : anglais
Help address review/issue comments on the open GitHub PR for the current branch using gh CLI; verify gh auth first and prompt the user to authenticate if not logged in.
Langue du texte source : anglais
Use when authoring, expanding, validating, running, or triaging Promptfoo eval suites, deterministic assertions, provider-backed semantic tests, red-team plans, or agent/control-plane prompt regression coverage.
Langue du texte source : anglais
Use when the user explicitly asks for a desktop or system screenshot (full screen, specific app or window, or a pixel region), or when tool-specific capture capabilities are unavailable and an OS-level capture is needed.
Langue du texte source : anglais
Security-oriented ownership and bus-factor analysis grounded in git history. Use when the user explicitly wants orphaned sensitive code, CODEOWNERS reality checks, sensitive hotspots, security maintainers, or ownership-cluster analysis. Do not trigger for…
Langue du texte source : anglais
Use when the user explicitly asks to threat model a codebase or path, enumerate abuse paths, or perform AppSec threat modeling. This skill builds a repository-grounded threat model covering trust boundaries, assets, attacker capabilities, abuse paths, and…
Langue du texte source : anglais
Use when implementing demo users, public-domain corpus import, metadata provenance, image handling, or seed refresh commands.
Langue du texte source : anglais