cursor/skills/vibeflow-quick/SKILL.md
Fast-tracks small tasks into a prompt pack in one command. Skips discover, generates an ephemeral spec in memory. Use for well-defined tasks that fit in ≤4 files.
npx skillsauth add pe-menezes/vibeflow vibeflow-quickInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Fast-track: generate a prompt pack for small tasks in one command. Skips discover, generates ephemeral spec, outputs ready-to-use prompt pack.
Usage: Provide the task description as input.
Detect the language of the user's input. Write ALL output in that same language. Technical terms in English are acceptable regardless of the detected language.
.vibeflow/ exist?
.vibeflow/)This is NOT a full analyze. Do NOT generate .vibeflow/. Do just enough
to understand the project:
package.json, pyproject.toml, Cargo.toml,
go.mod, build.gradle, pom.xml, or equivalent. Determine the stack..cursorrules, CLAUDE.md, .github/copilot-instructions.md, or
.cursor/rules/ exist, read them for coding conventions.Keep all findings in memory — do NOT write files.
At the end, suggest: "For deeper analysis, run the vibeflow-analyze skill."
Using .vibeflow/ (if available) or Phase 1 context, generate a spec
in memory only (do NOT save to file). The spec must contain:
.vibeflow/patterns/
apply (if .vibeflow/ exists).Do NOT include Technical Decisions or Risks sections (this is fast-track).
Using the ephemeral spec and .vibeflow/ knowledge (if available),
generate the prompt pack.
The prompt pack MUST start with:
You are only seeing this prompt; there is no context outside it.
(Write this opening line in the user's detected language.)
Then include, in this order:
From the ephemeral spec.
What NOT to do.
≤ 4 files (default for quick).
If .vibeflow/ exists: embed real code examples from pattern docs
and conventions.md, just like the vibeflow-prompt-pack skill does.
If .vibeflow/ does NOT exist: include the conventions and patterns
you observed during the Phase 1 lightweight scan.
Real file paths. Verify they exist. Include relevant code snippets.
Architectural direction. NOT step-by-step.
Detect test runner from stack. Always include test commands. If no test runner detected: "No test runner detected. Add manual tests to validate."
Save the prompt pack to: .vibeflow/prompt-packs/<feature-slug>.md
Create .vibeflow/prompt-packs/ if it doesn't exist.
After saving, suggest: "Prompt pack saved. After implementation, use the vibeflow-audit skill to verify."
testing
Implements a feature from its spec with guardrails: budget, DoD, anti-scope, and pattern compliance. Runs an 8-phase pipeline (find spec → extract guardrails → load patterns → plan → implement → test → refine → self-verify DoD). Use after gen-spec when ready to implement.
development
Audits implementation against its DoD and project patterns. Runs the test suite, compares code against the spec, and reports PASS / PARTIAL / FAIL. Also runs the Critical Gate — a safety scan of the diff for destructive or dangerous operations. Use after implementation to verify quality before shipping.
development
Implements a feature from its spec following all guardrails: budget, DoD, anti-scope, and pattern compliance. Runs an 8-phase pipeline (find spec → extract guardrails → load patterns → plan → implement → test → refine → self-verify DoD). Use after gen-spec when you're ready to code. The agent has filesystem access and acts as Coding Agent.
development
Audits recent work against its Definition of Done and project patterns. Runs the test suite, compares code against the spec, and reports PASS / PARTIAL / FAIL. Also runs the Critical Gate — a safety scan of the diff for destructive or dangerous operations. Generates an incremental prompt pack for any gaps found. Use after implementation to verify quality before shipping.