All authors
Claude Skills by wakqasahmed
github.com/wakqasahmed30 skills3 installs78 views
- Ai Agent Pr MetadataAdd 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`.Votes: 0GitHub stars: 2
- Changesets ReleaseRecords 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.Votes: 0GitHub stars: 2
- Clarify WorkClarify 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.Votes: 0GitHub stars: 2
- Decompose To IssuesBreak 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.Votes: 0GitHub stars: 2
- Define DoneDefine 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.Votes: 0GitHub stars: 2
- Design Composition CheckFalsify a new or unfamiliar design system by rendering its hardest UI compositions before other features build on it. Use when a freshly researched, extracted, or ingested design system or token set is about to be used by more than one feature and no prior screen has exercised it yet.Votes: 0GitHub stars: 2
- DiagnoseDisciplined 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.Votes: 0GitHub stars: 2
- Docker Volume GuardrailsSet up a Claude Code hook to unconditionally block Docker commands that permanently delete a volume (docker volume rm/prune, docker rm -v, docker system prune --volumes, docker compose down -v). Use when setting up guardrails against destructive volume deletion, or after "never delete volumes without confirmation" has been violated or nearly violated.Votes: 0GitHub stars: 2
- External Campaign TriageTrack 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.Votes: 0GitHub stars: 2
- External Pr StyleWrite PR descriptions and maintainer replies for third-party upstream repos in natural, concise human prose to avoid maintainer AI-rejection patterns. Use before opening any PR against a repo we don't own, and before replying to a maintainer's comment or question on one.Votes: 0GitHub stars: 2
- External Pr ViabilityCheck 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.Votes: 0GitHub stars: 2
- Git Guardrails Claude CodeSet 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.Votes: 0GitHub stars: 2
- Hitl BlockerConvert 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.Votes: 0GitHub stars: 2
- Open Code Review SetupSet 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.Votes: 0GitHub stars: 2
- Release GateCheck deployment, staging, rollback, and health verification before release. Use for user-facing, infrastructure, CI/CD, integration, or high-risk changes.Votes: 0GitHub stars: 2
- Resolving Merge ConflictsUse when you need to resolve an in-progress git merge/rebase conflict.Votes: 0GitHub stars: 2
- Review GateRun an independent semantic review gate before merging non-trivial work, alongside CI and any configured automated code review tool.Votes: 0GitHub stars: 2
- Subagent PipelineRun 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.Votes: 0GitHub stars: 2
- Tmux Orphaned SocketDiagnose 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.Votes: 0GitHub stars: 2
- To PrdSynthesize 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.Votes: 0GitHub stars: 2
- WizardGenerate 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.Votes: 0GitHub stars: 2
- Workflow RouterRoutes 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.Votes: 0GitHub stars: 2
- Write Prompt GuideProduce 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.Votes: 0GitHub stars: 2
- Writing For AgentsWriting documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.Votes: 0GitHub stars: 2
- RoastUse 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.Votes: 0GitHub stars: 2
- CavemanUser-invoked persistent ultra-compressed communication mode that targets 20-50% token reduction on typical replies while preserving technical accuracy.Votes: 0GitHub stars: 2
- HandoverCompact 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.Votes: 0GitHub stars: 2
- Docker Db GuardrailsSet up a Claude Code hook to block schema-wipe commands (Laravel migrate:fresh/migrate:refresh/migrate:reset/db:wipe, Rails db:drop/db:reset, prisma migrate reset, sequelize db:drop, alembic downgrade base, DROP DATABASE/TABLE/SCHEMA, TRUNCATE, dropdb, mysqladmin drop, mongo dropDatabase, redis FLUSHALL/FLUSHDB) against a Docker container unless the actually-resolved target database visibly indicates it is disposable (test/testing/demo/sandbox/scratch). Use when copying files into a container...Votes: 0GitHub stars: 2
- Git Identity GuardInstall a $PATH-level git wrapper that hard-blocks any commit or push whose author/committer identity doesn't match one configured name/email, everywhere on the machine, with no override. Use when commits keep landing under the wrong email (breaking CLA bots, GitHub's "Verified" badge, or account-linked contribution credit), when a project's own docs say "always commit as X" but agents keep overriding it anyway, or when setting up a fresh machine/session for an external-contribution campaign.Votes: 0GitHub stars: 2
- Vps CleanupReclaim disk on a shared dev/staging VPS or server in approval-gated tiers without breaking concurrent agent sessions. Use when disk usage is high or full, on "No space left on device", when asked to clean up the disk, or before a large build on a nearly full box.Votes: 0GitHub stars: 2