wakqasahmed
UserCanonical AI engineering workflow skills, aggregated by wakqasahmed/skills
Categories
Indexed Skills (24)
workflow-router
Routes a software-work request to the smallest applicable delivery workflow and records repository conventions once. Use when a user asks what engineering workflow to follow, wants help starting a change, needs a release or blocker path, or says setup workflow.
roast
Use when someone asks to roast an idea, pressure-test or stress-test an idea, validate a business idea, "convene the council", get a brutal second opinion before building something, or says "/roast". Spins up a 6-persona council that attacks the idea from every angle, then a Judge returns one GO / RESHAPE / KILL verdict with the cheapest test to de-risk it.
handover
Compact the current conversation into a handover document a fresh agent can pick up and continue seamlessly. Invoke when only 5-10% of the session limit remains, when context usage passes 40% (less than 60% of the context window remaining), when context is about to cross an agent or session boundary, when work is blocked, or on explicit user request — never haphazardly mid-task. Covers decisions, shipped changes, key files, running state, verification, deferrals, and open questions.
ai-agent-pr-metadata
Add GitHub-visible AI agent and AI code-review metadata and exact agent labels without adding AI attribution to commits, and scope Alibaba/Open Code Review's review surface to control LLM token spend. Use when configuring PR templates, issue/PR labels, PR creation commands, PR update comments, or Alibaba Code Review/open code review workflows to disclose the implementing agent, review tool, LLM model, run URL, or to add/tune a `.opencodereview/rule.json`.
changesets-release
Records release intent with Changesets and guides semver, changelog, CI, and artifact-version checks for independently distributed packages. Use when a repository has `@changesets/cli`, `.changeset/`, a version-packages PR, publishable plugins, SDKs, libraries, or monorepos.
decompose-to-issues
Break high-level work into independently executable GitHub issues using vertical slices. Use when a plan, PRD, roadmap item, or vague feature needs issue-sized execution units.
diagnose
Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression.
external-campaign-triage
Track state across many candidate issues, PRs, and repos in a multi-repo external open-source contribution campaign, using a local tracker instead of GitHub labels. Use when scouting, claiming, implementing, or following up across many third-party repos in an ongoing campaign, and always before posting any status-check comment on a stalled external PR.
external-pr-style
Write PR descriptions for third-party upstream repos in natural human prose to avoid maintainer AI-rejection patterns. Use before opening any PR against a repo we don't own.
external-pr-viability
Check whether an upstream repo actually merges outside contributors before investing implementation time in an unsolicited PR. Use right after scouting a candidate issue in a third-party repo, before writing any fix.
git-guardrails-claude-code
Set up Claude Code hooks to block dangerous git commands (force-push, direct push to protected branches, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Code.
open-code-review-setup
Set up Alibaba Open Code Review (OCR) on a repository that lacks it, or audit and update an existing setup. Use when creating a new repository, onboarding an existing repo to automated AI code review, configuring `.opencodereview/rule.json` or the OCR GitHub Actions workflows, or when OCR reviews are not running on PRs.
review-gate
Run an independent semantic review gate before merging non-trivial work, alongside CI and any configured automated code review tool.
subagent-pipeline
Run a cold-start implementer, reviewer, and fixer subagent chain for one issue, gated by CI, ending in a staging PR. Use when subagent delegation is authorized and the issue is non-trivial.
tmux-orphaned-socket
Diagnose and recover from "error connecting to /tmp/tmux-*/default (No such file or directory)" when tmux ls or attach fails but sessions were working before. Use when a tmux socket has gone missing, especially after any /tmp cleanup, disk-space sweep, or agent-run cleanup script — never assume the sessions are lost before checking.
to-prd
Synthesize the current conversation and repository context into a concise product and engineering spec, publish it to the project issue tracker, and gate agent readiness before decomposition. Use when high-level work needs product framing, implementation and testing decisions, or success criteria captured without another general interview.
wizard
Generate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover. Don't invoke this for steps the agent can perform itself.
write-prompt-guide
Produce a pack-specific PROMPT_GUIDE.md that teaches end users what to type to get a good run out of one Agent Skill pack, from that pack's own SKILL.md, README, and open issues. Use when a skill pack has agent-facing docs but nothing telling a human how to invoke it well.
writing-for-agents
Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.
clarify-work
Clarify non-trivial engineering work before implementation by resolving ambiguity, terminology, constraints, and the smallest viable path. Use when a request is broad, fuzzy, architectural, cross-cutting, or has hidden product decisions.
define-done
Define acceptance criteria, risk level, and verification before editing. Use at the start of non-trivial implementation or when an issue lacks clear proof of completion.
hitl-blocker
Convert human-only blockers into visible GitHub issues. Use when work is blocked by missing credentials, secrets, DNS, billing, account permissions, approvals, or other user-held external state.
release-gate
Check deployment, staging, rollback, and health verification before release. Use for user-facing, infrastructure, CI/CD, integration, or high-risk changes.
resolving-merge-conflicts
Use when you need to resolve an in-progress git merge/rebase conflict.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.