注释
代码注释与标注
dogfood
niyatna
"Exploratory QA of web apps: find bugs, evidence, reports."
ticket-lifecycle
nullvoidundefined
Use to open, advance, close, or report on the external tracker ticket (Jira, Notion, or Asana) that tracks a task. Triggers at task classification, at every state change in the work, at task close, and on "what did I ship this week" or "how long does this tier take".
fizz
visionik
Fizzy.do Kanban CLI for managing boards, cards, comments, tags, and more.
ticket-reaper
surreptakos
Reap the current repo's open tickets against the speed-over-robustness rule — park belt-and-suspenders work in Maybe Someday, close what is moot, post one digest. Use when asked to reap or sweep the tracker, and as step 0 of /maintain-repo.
generar-post
josevictorgarcia
Crear un post (carrusel) de Instagram o TikTok de N slides a partir de una plantilla propia de Canva, cambiando solo los textos (y, si la plantilla lo pide, una imagen libre de derechos). Úsala cuando el usuario pida un post, una publicación, un carrusel o contenido nuevo sobre un tema concreto, o mencione una de sus plantillas. También cuando pida "otro igual pero de X".
cadence
eyecantell
Run the cadence check on this branch's PR (review evidence, squash, CI, ledger, worktree, pushed, deploy) — do the independent review and post its evidence comment if missing, then merge only when every row passes. Pass a PR number to check another PR, or "week" for every PR merged in the last 7 days.
Scholar Evaluation
unerue
Abstract: ScholarEval is a retrieval augmented evaluation framework that assesses research ideas based on two fundamental criteria: soundness (the empirical validity of proposed methods based on existing literature) and contribution (the degree of advancement made by the idea across different dimensions relative to prior research). The framework achieves significantly higher coverage of expert-annotated evaluation points and is consistently preferred over baseline systems in terms of evaluat
github-code-review
darkmatter
"Review PRs: diffs, inline comments via gh or REST."
todo-manager
Nakadie
Manage the weekly todo note. Use this skill whenever the user asks to add a ticket to their todos, move a ticket between days, mark a todo as done, or create a Jira subtask from a PR review comment. Handles Jira title lookup, PR/status checks, and subtask creation automatically.
tech-radar-blip
bcook797
Guide for writing high-quality blip submissions for the ThoughtWorks Tech Radar. This skill should be used when someone asks for help submitting a blip to the Tech Radar, writing a radar submission, or preparing a technology recommendation for the ThoughtWorks radar.
osm-rail
dacekroberts
Build a city's rail leg from OpenStreetMap instead of GTFS - when that is justified, how to derive stations without losing a line, and the traps OSM has that no transit feed has. Use when a city's agency publishes no reachable or current feed, or when a feed is stale or incomplete. Not a replacement for add-city Step 4; it is that step's OSM branch.
sharingan
zheref
Drive one open PR to CON-32 readiness at its human gate, then stop there. Use when the maintainer invokes /sharingan #<PR> to <G2 G4>, or asks to get a PR ready, unstick a PR, or take it to the merge gate; /en composes it as its second and fourth steps. It names the first blocking condition, settles review threads, requests the owed reviewer round, and decides readiness with nen pr ready. It never merges, self-reviews, or votes.
ticket-lifecycle
nullvoidundefined
Use to open, advance, close, or report on the external tracker ticket (Jira, Notion, or Asana) that tracks a task. Triggers at task classification, at every state change in the work, at task close, and on "what did I ship this week" or "how long does this tier take".
explain-code
dakotahp
Explains code with visual diagrams and analogies. Use when explaining how code works, teaching about a codebase, or when the user asks "how does this work?"
line-chart-generator
zxhfighter
Generate line charts and time-series visualizations using matplotlib. Use when users need to create line charts for price trends, stock data, performance metrics, or any time-series data. Supports annotations, reference lines, and customization of chart dimensions.
kata-intent
walternagai
Fase INTENT do ciclo Karpathy (kata). Use quando o kata estiver na fase 2.5 — verificar intenção entre código, teste e especificação antes de mudar comportamento. Triggers: INTENT, intent gate, intenção, código vs teste, spec, conflito, fable-method.
content-daily
nabilakhannn
Primary LinkedIn content creation skill. Invoke for "give me today's content", "write me a LinkedIn post", "today's post", "content for this week", "generate my weekly posts", "post idea for me", "help me write a post", "I need content for [topic]", "batch this week's content". Runs a rigid 5-phase pipeline — Research → Topic Selection → POV Questions → Writing → Log. Cannot skip phases. Uses your voice card, the 7-layer Writing SOP, hook library, posts-log memory, and your positioning. Enforces anti-AI red-flag scan before output.
excel-report-styler
Bhagirathiramesh88
"Transform plain or raw Excel reports into polished, presentation-ready workbooks with warm vivid color scales, conditional formatting, data bars, frozen panes, and annotated headers. Use this skill whenever the user uploads an .xlsx file and asks to make it 'colorful', 'impactful', 'presentation-ready', 'annotated', 'formatted', 'polished', or wants outliers to stand out. Also trigger when the user says 'add color scales', 'highlight outliers', 'make it pop', 'style this spreadsheet', 'beautify this Excel', or 'format for leadership'. Works on any multi-sheet Excel workbook. Does NOT create new analysis or change data -- only applies visual formatting on top of existing content."
SKILL: harn-gitea-connector
burin-labs
For SVN polling, add a poll trigger and run harn connector check . --provider svn --run-poll-tick.
migrate-legacy-acs-to-sdlc-v1
tigger-developer
Archive and close a brownfield project's legacy GitHub tickets while reconciling its SDLC v1 acceptance-criteria ledger and documentation before SDLC v3 initialization. Invoke only when the operator requests this migration.
ratios
The-Interdependency
Self-declaring module composition ratios on msdmd — a single comment line on a file's first and last line (never a fenced block). The canonical seal is The-Interdependency/a0's compact positional N:M C:D I:O annotation (code:comment · consumed:declared · fan-in:fan-out), computed by a0's scripts/annotate.py; the named loc_comments=… imports_exports=… calls_definitions=… line is a portable, per-file adaptation for standalone libraries, verified by the stdlib ratios_check.py (drift/misplacement failures, visible gaps). JSON/Markdown are out of scope. Load this when recording a module's composition ratios, when authoring or extending the ratio registry, or when wiring ratio verification into CI.
Trello-Task-Protocol
webdev0814
Write operations require the API proxy.
Browser Automation with playwright-cli
surreptakos
Machine-local half of a Claude Code setup: global rules, skills, hooks, plugin manifests, per-project memory. No credentials.
revkit
konradmichalik
Use revkit for GitHub/GitLab PR review operations — reading a PR, listing, filtering, replying to and resolving review comments, checking CI status, and fetching failure logs. Prefer it over raw gh/glab API calls: it returns compact, normalized JSON that costs far fewer tokens than parsing raw API responses, and it works identically on GitHub and GitLab.