vibe-iterate

Plugin vibe-iterate in estevanhernandez-stack-ed/vibe-iterate. Commands read from the repo's manifest — 1 month ago.

Skills (18)

• bootstrap

  Internal SKILL — invoked by the bare router on first run, or directly when the user says 'set up vibe-iterate', 'init vibe-iterate', or '/vibe-iterate:bootstrap'. Identifies the app type, confirms with the user, infers framework pins from package.json, asks for competitor URLs, and writes .vibe-iter

• bug-bash

  This skill should be used when the user says `/vibe-iterate:bug-bash` and wants to fix the highest-priority user-reported bug. v1.0: reads `feedback.md` only. Triages by severity × frequency × blast-radius, reproduces, ships the fix as one PR + Atlas entry. Dormant for repos without `feedback.md` (s

• competitive

  This skill should be used when the user says `/vibe-iterate:competitive` and wants to ship a feature based on what competitors have shipped. Scans competitor changelogs/releases, diffs against your shipped features, ranks gaps by strategic relevance (not parity), picks one, ships one PR + Atlas entr

• evolve-iterate

  This skill should be used when the user says `/vibe-iterate:evolve-iterate` and wants vibe-iterate to reflect on past sessions and propose improvements to itself. Reads ~/.claude/plugins/data/vibe-iterate/ session logs + friction.jsonl, weights findings, writes proposed SKILL/trigger/rubric edits to

• feature-add

  This skill should be used when the user says `/vibe-iterate:feature-add` and wants to ship the next feature. Scans competitor URLs, Product Hunt, framework releases, and feedback.md. Clusters candidates, scores on impact/fit/effort/Atlas-history, ships one PR with an Atlas entry naming the candidate

• forecast

  This skill should be used when the user says `/vibe-iterate:forecast <bet>` and wants to score a long-range bet on the future-tuned lens. Reads the codebase + Atlas + horizon.md, scores on conviction, time-to-relevance, optionality (cost-of-waiting), and strategic fit. Outputs scores + rationale + h

• friction-logger

  Internal SKILL — not a slash command. Append-only friction capture for vibe-iterate. Invoked by every banner mode + bootstrap at the trigger points listed in skills/guide/references/friction-triggers.md. Implements Pattern #6 (Friction Log) from the Self-Evolving Plugin Framework.

• guide

  Shared behavior for vibe-iterate commands — Ptolemy persona, posture (regression-aware/user-trust-aware/small-diff-preferred), knowledge sources (context7 + scheduled refresh + web fallback), Atlas write conventions, Cart-detection pattern. Referenced by every command SKILL.

• horizon

  This skill should be used when the user says `/vibe-iterate:horizon` and wants to think long-range — what bets to make now to be ahead in months and years, not days and weeks. Ingests four forward signals (stack/platform roadmaps, ecosystem/model curves, competitor trajectory, own-product trajectory

• radar

  This skill should be used when the user says `/vibe-iterate:radar` and wants a read-only digest of what's new across their stack and competitor set since last visit. Reads the cached scheduled-refresh file (per-project, weekly). When the cache is missing, optionally runs a manual refresh on demand.

• rate

  This skill should be used when the user says `/vibe-iterate:rate <idea>` and wants to score a feature idea against their shipped product. Reads the codebase + Atlas, scores on impact, fit-with-stack, effort, regression-risk, user-trust-impact. Outputs scores + rationale + ship-now/queue/decline verd

• scan-releases

  This skill should be used when the user says `/vibe-iterate:scan-releases [package]` and wants to know what's new in a specific lib (or all libs) since they last bumped. Reads manifest pins (package.json, pyproject.toml, Cargo.toml, go.mod, *.csproj/NuGet), queries release notes via context7 + web s

• session-logger

  Internal SKILL — not a slash command. Two-phase append-only session log for vibe-iterate: a sentinel entry at command start (outcome=in_progress) and a terminal entry at command end, paired by sessionUUID. Invoked by every banner mode + bootstrap at start and end. Part of Level 2 (session memory) of

• ship

  This skill should be used when the user says `/vibe-iterate:ship <brief>` and wants to skip ingestion and ship from a hand-written brief. Takes a markdown brief (file path or inline prompt), runs the build with regression-aware/small-diff posture, ships one PR + Atlas entry. Bypasses the signal-inge

• spy

  This skill should be used when the user says `/vibe-iterate:spy <url>` and wants a one-shot competitive read on a single URL. Fetches and reads the URL (changelog, what's-new, landing page), outputs structured read of what they shipped, what they emphasize, gaps, and overlap with the user's product.

• upgrade

  This skill should be used when the user says `/vibe-iterate:upgrade <package>` and wants to surgically bump one library to its latest version with codemods if available. Reads release notes via :scan-releases, runs the codemod if one exists, runs the test suite, ships the bump as one PR with an Atla

• ux-polish

  This skill should be used when the user says `/vibe-iterate:ux-polish` and wants to fix shipped-but-rough UI surfaces. Walks routes/components/key flows, identifies rough patches (inconsistent spacing, weak hierarchy, missing empty/loading/error states, dead-end paths), scores by user-trust impact,

• vibe-iterate

  This skill should be used when the user says `/vibe-iterate` (bare, no subcommand). Reads project state (Atlas, radar cache, recent commits), recommends a mode for the moment (feature-add, competitive, ux-polish, bug-bash), and asks before launching. On first run (no .vibe-iterate/ directory), grace

Similar plugins