Comentaris
Comentaris i anotacions del codi
code-explain
dmonteroh
"Explain complex code clearly for humans and agents. Produce a structured walkthrough (high-level intent -> data/control flow -> key invariants -> edge cases) with optional Mermaid diagrams and actionable next steps. Use for onboarding, debugging understanding, and “how it works” docs."
session-behavior
ederheisler
Core behavioral guidelines and interaction patterns for the agent. This skill provides the foundation for how the agent should communicate and behave across all interactions. Use this skill to establish consistent behavior patterns at the beginning of a session. The skill defines tone, proactivity level, and request handling strategies that should be applied throughout the session. THIS SKILL HAS HIGH PRIORITY - always load at session start and re-trigger periodically to avoid behavioral drift. During context compaction, these rules should remain at the top priority.
testgen
sequant-io
"Generate test stubs from /spec verification criteria"
e2e-task-list-completed
bostonaholic
Run the live end-to-end verification of the task-list-completed GitHub App against the bostonaholic/task-list-sandbox repo. Use when asked to "run the e2e test", "verify the app end to end", "e2e task-list-completed", or after changing the app when live verification is wanted.
ns-review
noahdgrant
REVIEW phase. Runs a local, multi-provider review of a unit's diff before push, writes review.md with Critical/Important/Suggestion findings, and loops fixes until no Critical stays open. Use after verify, before shipping, or when asked to review a branch or diff.
agent-kanban
abpai
Operate the agent-kanban board via its stdio MCP server (preferred) or the kanban CLI — supports local (SQLite), Linear, and Jira providers.
ns-principle-fix-root-causes
noahdgrant
"Apply when debugging. Trace each symptom to its root cause and fix it there; reproduce first, ask why until you reach it, resist nil-check guards that silence crashes."
shap
eyadsibai
Use when "SHAP", "Shapley values", "feature importance", "model explainability", or asking about "explain predictions", "interpretable ML", "feature attribution", "waterfall plot", "beeswarm plot", "model debugging"
SakJules-gh-issues
beer-sakthai
"Fetch GitHub issues, select candidates, spawn background fix agents, open PRs, and optionally process PR review comments. user-invocable: true"
foodie-site
elinking-111
"Build or iteratively evolve a foodie/travel review website from notes and deploy it to GitHub Pages. Use this skill both for greenfield generation from Apple Notes/pasted text/social posts and for ongoing upgrades to an existing site: visual refinement, map/filter changes, showcase pages, shared interactions, and admin editing for shared content."
qa
sequant-io
"Code review + QA vs Acceptance Criteria, including A+ status suggestions and review comment draft."
e2e-dependabot-shepherd
bostonaholic
Run the live end-to-end verification of the dependabot-shepherd GitHub App against the bostonaholic/shepherd-sandbox repo. Use when asked to "run the e2e test", "verify the app end to end", "e2e dependabot-shepherd", or after changing the app when live verification is wanted.
implement-issue
ehuerta6
Implement one approved GitHub Issue from scope discovery through a verified, review-ready change.
documentation-governance
CMSForNerd
"Enforces strict OKF standards, UK English conventions, and prevents orphaned pages in the documentation hierarchy."
test
sequant-io
"Execute structured browser-based testing for admin features"
eli5
trimcrae
Explain something in plain language, the way you would to a smart person who does not work on this project. Load when the user types /eli5, or asks for it in their own words — "explain it like a normal person", "in plain English", "I don't follow", "assume I know nothing", "what does that actually mean" — or when they push back on an answer that was dense rather than wrong. Covers the rewrite rules (lead with the point, one idea per sentence, jargon gets replaced not glossed, at most one analogy), what plain language must NOT change (a hedge, a null, an unknown or a number stays exactly as strong as it was), and the failure modes that make an eli5 worse than the original — talking down, hollowing out, and the analogy that quietly becomes the argument.
eli5
srobroek
Explain a topic at five depth levels from metaphor to frontier. Use when asked "ELI5", "explain X", "what is X", or "how does X work".
fault-localization
gittensor-model-hub
From issue or traceback to the exact faulty lines — traceback grounding, symbol search, sibling consistency, call-site audit.
github-issues
adui-studio
'Create, update, and manage GitHub issues using MCP tools. Use this skill when users want to create bug reports, feature requests, or task issues, update existing issues, add labels/assignees/milestones, set issue fields (dates, priority, custom fields), set issue types, manage issue workflows, link issues, add dependencies, or track blocked-by/blocking relationships. Triggers on requests like "create an issue", "file a bug", "request a feature", "update issue X", "set the priority", "set the start date", "link issues", "add dependency", "blocked by", "blocking", or any GitHub issue management task.'
SakJules-github
beer-sakthai
"GitHub CLI for issues, PRs, CI/check logs, comments, reviews, releases, repos, and gh api queries."
verify
sequant-io
Execution verification for CLI/script features — runs commands and captures output for human review. Use after /exec for script changes.
docstring
CMSForNerd
"Provides structured guidelines for writing PEP-257 Google-style Python docstrings and detailed JSDoc comments."
gitea-pull-review
jumi-ai
Use when implementing Gitea pull-review create/list/submit or inline comments (pending reviews, commit_id vs current head, submit vs issue comments). This forge is Gitea 1.27. Do not webfetch go-gitea/main or GitHub review docs.
SakJules-dogfood
beer-sakthai
"Exploratory QA of web apps: find bugs, evidence, reports."