vibe
Skill8 starsChanged 6 months agoMITView on GitHub
Router for the vibestack skills: name the task and it picks the right skill, also where there is no / picker.
19 other projects use a version of this.
Adopted by
Most recently taken up by
- foryourhealth111-pixel/Vibe-Skillstheir own version, first seen Nov 3, 2026
- kexi/vibe-skillstheir own version, first seen Nov 1, 2026
- pmatos/skillstheir own version, first seen Nov 1, 2026
- ubmids/vibetheir own version, first seen Oct 20, 2026
- mistralai/mistral-vibetheir own version, first seen Oct 19, 2026
- pcx-wave/vibe-skilltheir own version, first seen Oct 1, 2026
Other versions19 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 19
- mistralai/mistral-vibe★ 5.3ksame name
- foryourhealth111-pixel/Vibe-Skills★ 3.8ksame name
- pcx-wave/vibe-skill★ 118same name
- geeks-accelerator/in-bed-ai★ 26same name
- kennethleungty/claude-music★ 23same name
- rizukirr/vibekit★ 20same name
- th3vib3coder/vibe-science★ 16same name
- JustineDevs/meta-architect★ 5same name
- Ally-for-Hire/Github-Vibe-Skill★ 2same name
- JustineDevs/premortem★ 2same name
9 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository62 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- address-pr-reviewSkill
- agent-evalSkill
- ai-cost-guardSkill
- autoplanSkill
- aws-costSkill
- bedrock-guardrailsSkill
- benchmarkSkill
- browseSkill
- canarySkill
- carefulSkill
- claudeSkill
- codexSkill
- connect-chromeSkill
- connect-reviewSkill
- context-restoreSkill
- context-saveSkill
- csoSkill
- design-consultationSkill
- design-htmlSkill
- design-reviewSkill
- design-shotgunSkill
- devex-reviewSkill
- diagramSkill
- document-generateSkill
- document-releaseSkill
- freezeSkill
- guardSkill
- healthSkill
- iac-reviewSkill
- improve-archSkill
- investigateSkill
- kb-reviewSkill
- land-and-deploySkill
- landing-reportSkill
- learnSkill
- make-pdfSkill
- mcp-reviewSkill
- office-hoursSkill
- open-browserSkill
- pair-agentSkill
- plan-ceo-reviewSkill
- plan-design-reviewSkill
- plan-devex-reviewSkill
- plan-eng-reviewSkill
- plan-tuneSkill
- pr-summarySkill
- qa-onlySkill
- qaSkill
- retroSkill
- reviewSkill
- scrapeSkill
- setup-browser-cookiesSkill
- setup-deploySkill
- shipSkill
- skillifySkill
- specSkill
- telegramSkill
- unfreezeSkill
- unslopSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
7 rules. 0 are common, 3 are distinctive, and 4 are very specific to this project.
0
Common
Most of the 19 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 17
If this session was compacted, the copy of this skill in context may be cut off.
- Very specific: line 18
Read ${CLAUDE_SKILL_DIR}/SKILL.md from disk and resume at the step you are on.
- Very specific: line 22
Use when the task clearly wants a vibestack workflow but the right one is not obvious, or when the host has no slash-command picker and the …
- Very specific: line 133
Failures: When the user names the cause and a narrow fix, make one read-only check of the file, test or log it rests on.
- Distinctive: line 139
Answer directly instead: when the request is a quick factual question (including "which skills are there?" — show the table), a small edit …
- Distinctive: line 143
Pick one: Don't stack skills; each carries its own full workflow, and a skill's own instructions take precedence once invoked.
- Distinctive: line 145
Only route to a skill that is installed: Don't guess a name: if the table or the index has nothing that fits, or the skill is not present …
“Common” is measured: kept by at least 6 in 10 of the 19 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
If this session was compacted, the copy of this skill in context may be cut off.
Read ${CLAUDE_SKILL_DIR}/SKILL.md from disk and resume at the step you are on.
When to invoke
Use when the task clearly wants a vibestack workflow but the right one is not
obvious, or when the host has no slash-command picker and the pack has to be
found by name. In Claude Code, Cursor, Kiro and Copilot CLI, skills are
/name. In Codex there is no / picker — reference a skill as $name inside an ordinary
message (Use $office-hours to shape this idea).
/vibe — pick the right skill
The router is named vibe, not vibestack: the pack's own checkout is
sometimes parked at ~/.claude/skills/vibestack, and a skill installing to that
path would collide with it — the installer's own integration test asserts that
checkout survives.
Route on intent. Process skills come first: brainstorm or plan before implementing, investigate before fixing, review before shipping.
| When the task is… | Use |
| Shape a rough idea into a design doc | office-hours |
| Turn intent into a precise, executable spec | spec |
| Plan a feature, refactor, or architecture change | plan-eng-review, autoplan |
| Execute an approved multi-step plan | an installed plan-execution skill if present; otherwise the plan-eng-review cold-start briefs lane by lane, then review and ship |
| Weigh product scope or the bigger problem | plan-ceo-review |
| Plan a UI change, or review a design before it is built | plan-design-review |
| Pressure-test the developer experience of a plan | plan-devex-review |
| Audit the live developer experience of a shipped product | devex-review |
| Debug an error, test failure, or odd behavior | investigate (see Failures below) |
| Review a diff before merge | review |
| Rewrite a PR description from its actual changes | pr-summary |
| Get a second opinion from a different model | codex or claude — by host, see below |
| Audit security | cso |
| QA a running web app | qa (fixes), qa-only (report) |
| Drive a browser, scrape a page, pair a remote agent | browse, scrape, open-browser, pair-agent |
| Test logged-in pages with your real browser's cookies | connect-chrome, setup-browser-cookies |
| Turn a browse or scrape flow that worked into a skill | skillify |
| Read, transcribe or send Telegram messages as yourself | telegram |
| Review a shipped UI, or explore design directions | design-review, design-shotgun, design-consultation |
| Turn an approved mockup into production HTML/CSS | design-html |
| Render a Mermaid diagram to HTML and PNG | diagram |
| Render markdown or HTML to a polished PDF | make-pdf |
| Ship: tests, version, changelog, PR | ship |
| See which VERSION slots open PRs already claim | landing-report |
| Address PR review threads and failing CI | address-pr-review |
| Merge, deploy, and confirm production health | type /land-and-deploy (typed-only), then canary (setup-deploy configures it once) |
| Measure page performance against a baseline | benchmark |
| Update docs after shipping | document-release, document-generate |
| Strip machine-sounding prose | unslop |
| Check code-quality health or find refactors | health, improve-arch |
| Make the build, lint and tests pass without editing a test | health as /health --fix |
| Review AWS spend, or price a change before it deploys | aws-cost (--estimate <plan>) |
Review a Terraform plan, cdk diff or EKS config before apply | iac-review |
| Cap paid-inference spend | ai-cost-guard |
| Audit Bedrock guardrails, region and tenant isolation | bedrock-guardrails |
| Review a knowledge base or RAG pipeline | kb-review |
| Review an Amazon Connect, Lex or voice solution | connect-review |
| Evaluate an agent or prompt | agent-eval |
| Review an MCP server | mcp-review |
| Save or restore working context across sessions | context-save, context-restore |
| Review, search or prune what the pack has learned | learn |
| Run a retrospective from git history | retro |
| Tune which questions the skills ask you | plan-tune |
| Guard a risky session | careful, freeze, guard (and unfreeze to release) |
| Update the pack itself | type /vibe-upgrade (typed-only) |
| Find and retire unused skills, hooks, permissions and caches | vibe-gc |
Anything not listed here is in the full index — read it rather than guessing at a skill name:
_found=""
for _d in "${CLAUDE_SKILL_DIR:-}" "$HOME/.agents/skills/vibe" "$HOME/.claude/skills/vibe" \
"$HOME/.cursor/skills/vibe" "$HOME/.kiro/skills/vibe" "${COPILOT_HOME:-$HOME/.copilot}/skills/vibe" \
".agents/skills/vibe" ".claude/skills/vibe" ".cursor/skills/vibe" ".kiro/skills/vibe" ".github/skills/vibe"; do
if [ -n "$_d" ] && [ -r "$_d/skills-index.md" ]; then
cat "$_d/skills-index.md"; _found=1; break
fi
done
if [ -z "$_found" ]; then
for _r in "$HOME/.agents/skills" "$HOME/.claude/skills" "$HOME/.cursor/skills" "$HOME/.kiro/skills" \
"${COPILOT_HOME:-$HOME/.copilot}/skills"; do
[ -d "$_r" ] && { echo "$_r:"; ls "$_r"; }
done
fiThe index sits next to this file, so if none of those paths resolve, read
skills-index.md from the directory this SKILL.md was loaded from.
Second opinion — route by host. The outside voice has to be a different model from the one already running:
if [ -n "${CODEX_THREAD_ID:-}" ] || [ -n "${CODEX_SANDBOX:-}" ]; then echo "HOST: codex"
elif [ -n "${CLAUDECODE:-}" ]; then echo "HOST: claude"
else echo "HOST: other"; fiHOST: claude → codex. HOST: codex → claude (codex refuses to run
nested under Codex, and would be the same model anyway).
HOST: other (Cursor, Kiro, Copilot CLI) → codex, unless the session's own
model is GPT, then claude. Copilot CLI sets no documented session variable,
so it always reports HOST: other.
Rules when routing:
- Invoke it, don't describe it. Once a skill fits, hand off: invoke it
through the Skill tool (Claude Code, Cursor, Kiro, Copilot CLI), or on Codex load that
skill's
SKILL.mdand follow it (users invoke it there asUse $<name>). Do not answer with a list of options, and do not do the skill's work freehand when the skill exists. Except: never invoke a typed-only skill (a row that says "type/name") — tell the user to type it (on Codex,Use $name) and do not do its work yourself. - Failures. When the user names the cause and a narrow fix, make
one read-only check of the file, test or log it rests on; if it holds, fix
it and run the focused test, otherwise invoke
investigate. When the cause is unknown, make one read-only triage pass, with no reproduction and no wider search, over the supplied evidence and the code it implicates; fix only if that pass alone proves the root cause, otherwise invokeinvestigate. - Answer directly instead when the request is a quick factual question (including "which skills are there?" — show the table), a small edit the user scoped themselves, or the user asked for a direct answer rather than a workflow.
- Pick one. Don't stack skills; each carries its own full workflow, and a skill's own instructions take precedence once invoked.
- Only route to a skill that is installed. Don't guess a name: if the table or the index has nothing that fits, or the skill is not present on this host, say so and proceed normally — these are workflows, not dependencies.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

