Comentaris

Comentaris i anotacions del codi

Skills: 1009–1032 de 2134
knoopx

python

knoopx

Structures Python projects, writes type-hinted code, tests with pytest, and enforces quality with ruff and mypy. Use when setting up pyproject.toml, writing tests, adding type annotations, or formatting/linting code.

Revisió de codi 85 fa 8 mesos
ailabs-393

codebase-documenter

ailabs-393

This skill should be used when writing documentation for codebases, including README files, architecture documentation, code comments, and API documentation. Use this skill when users request help documenting their code, creating getting-started guides, explaining project structure, or making codebases more accessible to new developers. The skill provides templates, best practices, and structured approaches for creating clear, beginner-friendly documentation.

Desenvolupament d’API 459 fa 11 mesos
existential-birds

pydantic-ai-tool-system

existential-birds

Register and implement PydanticAI tools with proper context handling, type annotations, and docstrings. Use when adding tool capabilities to agents, implementing function calling, or creating agent actions.

Agents 84 fa 8 mesos
existential-birds

review-ai-writing

existential-birds

Detect AI-generated writing patterns in developer text — docs, docstrings, commit messages, PR descriptions, and code comments. Use when reviewing any text artifact for authenticity and clarity.

Revisió de codi 84 fa 8 mesos
TMHSDigital

custom-properties

TMHSDigital

Define and bind Blender custom properties via bpy.props using the type annotation form, with PropertyGroup for grouping, PointerProperty for binding, and the four storage location options for Scene/Object/WindowManager/AddonPreferences. Targets 5.2 LTS.

Comentaris 17 fa 1 mes
TMHSDigital

operators

TMHSDigital

Author Blender operators with bpy.types.Operator, bl_idname conventions, the poll/invoke/execute/modal lifecycle, REGISTER and UNDO options, and defensive context handling. Targets 5.2 LTS with 4.5 LTS compatibility.

Comentaris 17 fa 1 mes
alexander-danilenko

code-documenter

alexander-danilenko

Use when adding docstrings, creating API documentation, or building documentation sites. Invoke for OpenAPI/Swagger specs, JSDoc, doc portals, tutorials, user guides.

Desenvolupament d’API 17 fa 8 mesos
corygabrielsen

review-pr

corygabrielsen

Thorough, educational PR review process. Gathers context, explains changes, identifies issues systematically, and drafts constructive feedback collaboratively before submitting.

Revisió de codi 1 fa 8 mesos
dhruvbaldawa

interviewing

dhruvbaldawa

Systematic questioning to clarify requirements, goals, and constraints. Use when there's ambiguity about what the user wants, hidden complexity needs uncovering, or you need to understand before proceeding. Triggers on unclear requirements, vague goals, or when other skills encounter fundamental ambiguity.

Generació de codi 31 fa 9 mesos
b1rdmania

hinge-profile-optimizer

b1rdmania

Improve a Hinge dating profile through research-backed screenshot audits, photo selection and ordering, conversational discovery, prompt and caption writing, settings review, or post-launch troubleshooting. Use for a full profile rebuild or a focused request about photos, copy, positioning, match quality, or profile performance.

Revisió de codi 75 fa 1 mes
jsboige

coordinate

jsboige

Cycle de coordination ai-01 (coordinateur UNIQUEMENT — jamais sur un worker). Lit memoire + dashboards + inbox + GitHub, merge les PRs pretes, tranche les design-gates, dispatche des grains par lane, reporte. Arguments: [--dispatch] [--focus <topic>]

Revisió de codi 16 fa 1 mes
kody-w

rappterbook

kody-w

Interact with Rappterbook — the third space of the internet for AI agents, built on GitHub

Comentaris 16 fa 1 mes
jsboige

check-cell-order

jsboige

Detect cell-ordering / enchainement problems in Jupyter notebooks (canonical-order slippage, misplaced or forgotten cells). Arguments: [target] [--severity HIGH MED LOW] [--json]

Revisió de codi 16 fa 4 mesos
OmniNode-ai

Agent Dispatch Watchdog

OmniNode-ai

Detect and recover from stalled agent dispatches in epic-team wave execution. Monitors Task() subagents for progress and triggers recovery when agents stop producing tool calls.

Eines de línia d’ordres 4 fa 3 mesos
OmniNode-ai

Comment sweep

OmniNode-ai

Recurring read-only sweep of a project tracker for comments awaiting a reply. Drafts every reply to a file and posts nothing. Thin process interface — the overlay names the tracker, the query and where drafts land.

Comentaris 4 fa 17 d
jthorare

review

jthorare

Orchestrate a multi-agent PR code review. Spawns domain-specific reviewer subagents in parallel based on changed files. Findings are saved to ~/.agentic-workflow/<repo-slug>/reviews/<pr>.json — run /postReview to publish to GitHub.

Comentaris 1 fa 27 d
jthorare

ui-evidence

jthorare

Generate Playwright-based UI evidence for a web app PR — plan with qa-runner, run headless with no model, repair broken selectors via judge, lint for sloppiness, and publish (ask-first) to Linear and to the PR as a comment with its screenshots. Local stack only, never dev/prod.

Comentaris 1 fa 4 d
constellation-works

orbit-orchestrate

constellation-works

Prepares and supervises an Orbit backlog. Deduplicates and pilots tasks (task-pilot), assigns crews, promotes ready work, dispatches with orbit run ship and orbit run auto drains, diagnoses failed or stuck jrun-* runs, and routes CI/QA sweep findings into repair tasks. Use for delivery operations across tasks, jobs, activities and workflow runs. Use orbit for one assigned task and orbit-setup for machine configuration or scheduler installation.

Comentaris 15 fa 7 d
kriscard

Interactive Teaching

kriscard

"Learning: Use for /learn sessions or when user explicitly asks to be taught step-by-step. NOT for quick answers or general help."

Generació de codi 14 fa 8 mesos
Blockether

ponytail-debt

Blockether

Harvest every ponytail: comment in the codebase into a debt ledger, so the deliberate shortcuts and deferrals ponytail leaves behind get tracked instead of rotting into "later means never". Use when the user says "ponytail debt", "/ponytail-debt", "what did ponytail defer", "list the shortcuts", "ponytail ledger", or "what did we mark to do later". One-shot report, changes nothing.

Comentaris 14 fa 1 mes
HMS091

github-code-review

HMS091

"Review PRs: diffs, inline comments via gh or REST."

Comentaris 0 fa 8 d
HMS091

autonomous-freelancing

HMS091

"Full-stack autonomous freelancing pipeline — research platforms, register accounts, monitor tasks, auto-bid, auto-deliver code. User handles accounts/wallets, agent handles ALL technical work."

Comentaris 0 fa 1 mes
GitQuuu

ado-deliver

GitQuuu

Builds one approved Azure DevOps Task end to end with the agent team - picks the next Task tagged agent-ready (or a given id), claims it, creates a branch, runs fullstack-developer, tester and reviewer, then commits, pushes, opens a linked pull request and updates the work item. Use when the user says take the next task, deliver task 456, work the backlog, or similar.

Comentaris 0 fa 2 d
HMS091

github-issue-to-pr

HMS091

"Carry a GitHub issue to a verified PR with honest CI state."

Comentaris 0 fa 8 d