Skip to main content

weselben/RooForge

SkillsMP a collecté 35 skills depuis weselben/RooForge. Ouvrez un skill pour examiner sa source et ses détails.

Dernière activité source enregistrée
Catalogue SkillsMP mis à jour
skills collectés
35
Étoiles GitHub
4
Forks GitHub
0

Skills dans ce dépôt

classification en attente

Affichage de 35 skills collectés sur 35.

métier
non classé
description

Write clear, size-gated PR descriptions with mandatory AI disclosure. Load `ste100` for prose. Triggers: "create a PR", "open a pull request", "update PR description", or pushes a branch with PR intent.

Langue du texte source : anglais

mis à jour
métier
non classé
description

Always load first — before responding to any user prompt — unless the user states otherwise in the prompt itself. Examples that trigger forge: 'let's continue on the auth refactor', 'work on the next ticket', 'open the map for the payment effort', 'what's…

Langue du texte source : anglais

mis à jour
métier
non classé
description

Set the git identity (name + email) before any commit, amend, or rebase. Apply repo-local on first commit; use `-c` for one-offs.

Langue du texte source : anglais

mis à jour
métier
non classé
description

Load when the user starts a new session on an ongoing effort — fresh chat, 'let's continue', 'pick up where we left off', or the first turn of any working session.

Langue du texte source : anglais

mis à jour
métier
non classé
description

Issue-tracker integration point for git-tracked repos. Premade with GitHub operations (gh CLI — native sub-issues for parent/child, native blocked_by dependencies for blocking, frontier queries). Load whenever a skill or workflow (e.g. wayfinder) needs to…

Langue du texte source : anglais

mis à jour
métier
non classé
description

Load when building new UI or reshaping an existing one — visual design, typography, palette, layout decisions — or when a design reads as a templated default.

Langue du texte source : anglais

mis à jour
métier
non classé
description

Coordinator-driven parallel implementation — dispatch one implementer subagent per task in its own worktree, per-task review, fix loop, integrate. Load when the plan has independent tasks ready to execute.

Langue du texte source : anglais

mis à jour
métier
non classé
description

Write human-facing text in ASD-STE100 Simplified Technical English — short sentences, approved words, one meaning per word. Governs PR bodies, docs, and issue/PR comments; chat replies and commit messages are not in scope (caveman-commit owns commits).

Langue du texte source : anglais

mis à jour
métier
non classé
description

Plan a huge chunk of work — more than one agent session can hold — as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.

Langue du texte source : anglais

mis à jour
métier
non classé
description

Review a GitHub PR or local branch inside a worktree — hard-rule validation, then a kimi -p review loop producing caveman-review findings. PR mode posts ONE review under the authenticated user's identity; local mode returns findings. Triggers: "review this…

Langue du texte source : anglais

mis à jour
métier
non classé
description

Finish a development branch — commit, verify, push, open PR. PR is the only path. Load when implementation is complete and tests pass. Triggers: "finish this branch", "wrap up", "open a PR".

Langue du texte source : anglais

mis à jour
métier
non classé
description

Breaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large to start, when you need to estimate scope, or when parallel work is possible.

Langue du texte source : anglais

mis à jour
métier
non classé
description

Resolve PR review findings — reads caveman-review findings, dispatches one resolver subagent per finding group into its own worktree, commits under user's git identity, pushes to PR head branch, replies under each review thread with the resolving commit SHA.…

Langue du texte source : anglais

mis à jour
métier
non classé
description

Drive `kimi -p` review/resolve loops via a shell framework. Dynamic prompts: callers supply their own `.md` template; loops renders it, compresses it, drives `run_loop` until `DONE:` or `BLOCKED:`. Triggers: "kimi -p loop", "review loop", "resolve loop".

Langue du texte source : anglais

mis à jour
métier
non classé
description

Load when the task involves SEO — meta tags, sitemaps, structured data, rendering strategy, Core Web Vitals, search ranking, or content optimization.

Langue du texte source : anglais

mis à jour
métier
non classé
description

Load when building or auditing digital products for the EU market — accessibility work, WCAG compliance, accessibility statements — or when the user mentions BFSG, EAA, EN 301 549, or EU accessibility law.

Langue du texte source : anglais

mis à jour
métier
non classé
description

Load when the task involves Tailwind CSS — styling components, utility classes, className work, converting custom CSS to utilities, or Tailwind build/config issues. Covers v4 (CSS-first) and flags v3 differences.

Langue du texte source : anglais

mis à jour
métier
non classé
description

Load when a design or implementation feels over-engineered, when evaluating architecture or reviewing code for simplicity, or when the user mentions KISS, over-engineering, or premature abstraction.

Langue du texte source : anglais

mis à jour
métier
non classé
description

Load when designing, building, or reviewing SaaS, cloud-native apps, microservices, containerized workloads, or serverless functions — or when the user mentions 12-factor, config in env, stateless processes, or dev/prod parity.

Langue du texte source : anglais

mis à jour
métier
non classé
description

Load before code changes, before writing docs or an ADR, when a user question exposes a missing how-to, and when closing a chunk of work; also loaded by forge after each squash-merge and by deep-research after a report.

Langue du texte source : anglais

mis à jour
métier
non classé
description

Repo bootstrap runbook — writes the local agent contract and captures repo specifics. User-invoked only.

Langue du texte source : anglais

mis à jour
métier
non classé
description

Harness adaptation runbook — clone the repo, find harness-specific references, patch them for the running harness. User-invoked only.

Langue du texte source : anglais

mis à jour
métier
non classé
description

Load when the user wants to tidy up — 'clean up', 'remove stale stuff', after a merged PR, or when worktrees and scratch files pile up.

Langue du texte source : anglais

mis à jour
métier
non classé
description

Build and sharpen a project's domain model. Use when the user wants to pin down domain terminology or a ubiquitous language, record an architectural decision, or when another skill needs to maintain the domain model.

Langue du texte source : anglais

mis à jour
métier
non classé
description

Ultra-compressed commit message generator. Cuts noise from commit messages while preserving intent and reasoning. Conventional Commits format. Subject ≤50 chars, body only when "why" isn't obvious. Use when user says "write a commit", "commit message",…

Langue du texte source : anglais

mis à jour
métier
non classé
description

Ultra-compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Each comment is one line: location, problem, fix. Use when user says "review this PR", "code review", "review the diff", "/review", or invokes…

Langue du texte source : anglais

mis à jour
métier
non classé
description

Ultra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman…

Langue du texte source : anglais

mis à jour
métier
non classé
description

Format commits per Conventional Commits v1.0.0 spec. Load when writing any commit message.

Langue du texte source : anglais

mis à jour
métier
non classé
description

Exhaustive evidence-based research — minimum 10 search iterations, recursive reflection, structured reports with markdown-native tables. As long as the research is solid; no fixed length cap. Triggers: "research this", "deep dive", "exhaustive analysis",…

Langue du texte source : anglais

mis à jour
métier
non classé
description

Dispatch up to 10 parallel subagents via AgentSwarm for 2+ independent tasks. Triggers: "swarm mode", "parallel agents", "dispatch in parallel", or 2+ independent tasks with no shared state.

Langue du texte source : anglais

mis à jour
métier
non classé
description

Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.

Langue du texte source : anglais

mis à jour
métier
non classé
description

Build a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.

Langue du texte source : anglais

mis à jour
métier
non classé
description

Use when you need to resolve an in-progress git merge/rebase conflict. Loads `subagent-driven-development` when conflicts touch integration branches and need per-task unblock work.

Langue du texte source : anglais

mis à jour
métier
non classé
description

Create an isolated git worktree for feature work. Detect existing isolation first; only create if needed. Triggers: "worktree", "isolate", "parallel implementation", "subagent dispatch".

Langue du texte source : anglais

mis à jour
métier
non classé
description

Verify completion claims with fresh evidence. Iron Law: NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE. Load when about to claim complete/fixed/passing; before commit/PR/task done.

Langue du texte source : anglais

mis à jour
Affichage de 35 skills collectés sur 35.