RADAR SKILL · GITHUB

Agent Skills utili, ordinati per utilizzo reale.

Confronta Skills verificati per funzione, contenuto del pacchetto, installazioni e affidabilità della fonte.

AMBITO CATALOGO
VERIFICATO
Skills
5771
repository
824
ultimo aggiornamento
8 set 2026
5771 Skills
jssblck
Community

parallel-agents

Use when agents work concurrently in a codebase, shared files have recurring merge conflicts, or AGENTS.md or CLAUDE.md needs maintenance.

installazioni
1
GitHub Stars
0
Aggiornato
8 set
jssblck
Community

project-bootstrap

Use when the user requests repository setup, tooling infrastructure, or Jess's full project template. Skip coding, prototypes, and hardening requests that do not include repository setup.

installazioni
1
GitHub Stars
0
Aggiornato
8 set
jssblck
Community

resolve-pr-conflicts

Use when a PR has merge conflicts with its base branch, including conflicts found during babysitting or merging.

installazioni
1
GitHub Stars
0
Aggiornato
8 set
jssblck
Community

ship-it

Use when asked to ship a completed change, commit and open a PR, or push changes and watch CI. Use babysit for monitoring an existing PR.

installazioni
1
GitHub Stars
0
Aggiornato
8 set
jssblck
Community

stop-slop

Use when drafting or editing durable prose, including docs, UI copy, comments, commit messages, and PR or issue text. Skip ordinary chat replies.

installazioni
1
GitHub Stars
0
Aggiornato
8 set
jssblck
Community

tag-release

Use when asked to tag or cut a patch, minor, or major release.

installazioni
1
GitHub Stars
0
Aggiornato
8 set
jssblck
Community

testing-craft

Use when writing, reviewing, or refactoring tests, or choosing verification for a code change.

installazioni
1
GitHub Stars
0
Aggiornato
8 set
kmalakoff
Community

sense

Query a markdown tree with the sense CLI: filter notes by frontmatter, full-text search the prose, follow wikilinks/backlinks, trace how notes connect (link path, similar-but-unlinked), and read note outlines. Use when the user wants to query, filter, count, search, or report on a folder of markdown notes, when you need to find which notes discuss a topic before reading them, when you want a note's backlinks or structure, when you want to know how two notes connect, when a directory has a sense.config.json, or when asked to add a saved entry to one.

installazioni
1
GitHub Stars
0
Aggiornato
8 set
kmalakoff
Community

sense-setup

Set up the sense CLI on a markdown tree and make the tree-design decisions that shape it: sense init, presets (which files, which settings, whether the scope searches by meaning), the embed block that names the model, and the trade-offs of frontmatter conventions, summaries, folder layout, and note size. Use when creating or restructuring a markdown knowledge base, running sense init, editing sense.config.json, choosing the backing store (sqlite, duckdb or turso), configuring search scope or vectors, or deciding how notes should be written for an agent to query later.

installazioni
1
GitHub Stars
0
Aggiornato
8 set
sebastianelvis
Community

pr-review

Use this skill for a systematic review of another person's GitHub Pull Request. Trigger on "review PR 123", "is this safe to merge", "check this PR's design", "does this break the protocol", or "does this solve the issue". Check the problem, architecture, protocol conformance, root cause, necessity, correctness, security, and project rules. Require the human to confirm the specification, the problem, and the approach before a detailed review. Do NOT use for an uncommitted local diff, a PR description, or a lint check.

installazioni
1
GitHub Stars
0
Aggiornato
8 set
wangnan0916
Community

debug-mode

Diagnose and fix reproducible runtime bugs with temporary structured logs, root-cause evidence, verification, and cleanup. Use for explicit debug-mode or instrumented debugging requests. Continue active sessions across reproduction replies. Use trace-mode when the goal stops at code location.

installazioni
1
GitHub Stars
0
Aggiornato
1 set
wangnan0916
Community

trace-mode

Trace runtime behavior and locate responsible code paths with temporary structured logs and NDJSON evidence. Use for runtime handlers, state transitions, and async boundaries. Use debug-mode when the goal includes a product fix. Continue active traces across capture replies.

installazioni
1
GitHub Stars
0
Aggiornato
1 set
sickn33
Community

professional-proofreader

Use when a user asks to "proofread", "review and correct", "fix grammar", "improve readability while keeping my voice", and to proofread a document file and save an updated version.

installazioni
1
GitHub Stars
46,1K
Aggiornato
7 set
sickn33
Community

telegram-mini-app

Expert in building Telegram Mini Apps (TWA) - web apps that run inside Telegram with native-like experience. Covers the TON ecosystem, Telegram Web App API, payments, user authentication, and building viral mini apps that monetize.

installazioni
1
GitHub Stars
46,1K
Aggiornato
7 set
vercel-labs
Ufficiale

plan-mode

Holistic, system-aware planning before implementing non-trivial tasks. Use when the task involves new features, architectural decisions, multi-file changes, unclear requirements, or multiple valid approaches. Triggers on "/plan", "plan this", "design an approach", "let's plan first".

installazioni
1
GitHub Stars
5,8K
Aggiornato
29 ago
phaserjs
Community

geometry-and-math

Use this skill when using Phaser 4 math and geometry utilities. Covers vectors, rectangles, circles, triangles, polygons, random number generation, angles, distance, interpolation, and snapping. Triggers on: Vector2, Rectangle, Circle, math, distance, angle, random, lerp.

installazioni
1
GitHub Stars
40,3K
Aggiornato
21 ago
phaserjs
Community

graphics-and-shapes

Use this skill when drawing shapes and graphics in Phaser 4. Covers the Graphics game object, lines, rectangles, circles, arcs, polygons, gradients, fill, stroke, and generated textures. Triggers on: Graphics, draw shape, fillRect, lineStyle, polygon, arc.

installazioni
1
GitHub Stars
40,3K
Aggiornato
21 ago
openai
Ufficiale

game-studio

Route early browser-game work. Use when the user needs stack selection and workflow planning across design, implementation, assets, and playtesting before moving to a specialist skill.

installazioni
1
GitHub Stars
5,5K
Aggiornato
28 ago
wshobson
Community

checkpoint-promotion

Gate fine-tuned checkpoints with drift budgets, paired comparison, and forgetting checks before promotion. Use after a training run produces a checkpoint, when deciding whether a tuned model ships, or when a promoted model needs re-gating against updated goldens.

installazioni
1
GitHub Stars
39,5K
Aggiornato
7 set
wshobson
Community

context-driven-development

- Creates and maintains project context artifacts (product.md, tech-stack.md, workflow.md, tracks.md) in a conductor/ directory. Scaffolds new projects from scratch, extracts context from existing codebases, validates artifact consistency before implementation, and synchronizes documents as the project evolves. Use when setting up a project, creating or updating product docs, managing a tech stack file, defining development workflows, tracking work units, onboarding to an existing codebase, or running project scaffolding.

installazioni
1
GitHub Stars
39,5K
Aggiornato
7 set
wshobson
Community

data-quality-frameworks

Implement data quality validation with Great Expectations, dbt tests, and data contracts. Use when building data quality pipelines, implementing validation rules, or establishing data contracts.

installazioni
1
GitHub Stars
39,5K
Aggiornato
7 set
wshobson
Community

eval-harness-first

Build the evaluation harness that gates every fine-tuning run — golden sets, per-failure-mode graders, judge calibration, and base-model baselines. Use when starting a fine-tuning effort, when converting traces into an eval set, or when calibrating a judge against human labels.

installazioni
1
GitHub Stars
39,5K
Aggiornato
7 set
wshobson
Community

go-concurrency-patterns

Master Go concurrency with goroutines, channels, sync primitives, and context. Use when building concurrent Go applications, implementing worker pools, or debugging race conditions.

installazioni
1
GitHub Stars
39,5K
Aggiornato
7 set
wshobson
Community

grpo-rlvr-training

Train reasoning and verifiable-task behavior with GRPO and reinforcement learning from verifiable rewards (RLVR). Use when task success is algorithmically checkable (math, code, tool calls, structured output), when designing GRPO reward functions, or when a GRPO run diverges or reward-hacks.

installazioni
1
GitHub Stars
39,5K
Aggiornato
7 set