{"_id":"@brijeshc2049/quiver","name":"@brijeshc2049/quiver","dist-tags":{"latest":"2.0.0"},"versions":{"2.0.0":{"name":"@brijeshc2049/quiver","version":"2.0.0","description":"A curated quiver of composable skills for Claude Code: interviews, audits (security, design, UX, a11y), deep review, debugging, testing, perf, plain-language explanations, and a full anti-generic design suite. Installs skill folders into your Claude Code ","bin":{"quiver":"bin/quiver.js"},"engines":{"node":">=16.7.0"},"keywords":["claude","claude-code","skills","code-review","design","performance","readability","testing","cli"],"author":{"name":"Brijesh Chandrakar"},"license":"MIT","homepage":"https://github.com/brijeshc/quiver#readme","repository":{"type":"git","url":"git+https://github.com/brijeshc/quiver.git"},"bugs":{"url":"https://github.com/brijeshc/quiver/issues"},"gitHead":"134fe4bfa1cee2be8167f292756b76a53f42909e","_id":"@brijeshc2049/quiver@2.0.0","_nodeVersion":"26.1.0","_npmVersion":"11.13.0","dist":{"integrity":"sha512-+qA1WFczyT+Rl8jafOgJ1v+LgZ/ouIxH+fWIFU/ZSzQu9l2SFD+qQ+f2xF9BkaGUsxTTm8hiQOyghG+aj6n5bw==","shasum":"5f884d404627085969c1cb668ffc3928629c2c1d","tarball":"https://registry.npmjs.org/@brijeshc2049/quiver/-/quiver-2.0.0.tgz","fileCount":62,"unpackedSize":167505,"signatures":[{"keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U","sig":"MEUCIHOVnlZbrQyb/6uKcvcDsu0QouMEnR7scHZ44vcXgSv8AiEA8yqpwzlYTp/+Boktm7MqorYMGkwaKy8T59V5QuzUbb4="}]},"_npmUser":{"name":"brijeshc2049","email":"brijeshchandrakar@hotmail.co.uk"},"directories":{},"maintainers":[{"name":"brijeshc2049","email":"brijeshchandrakar@hotmail.co.uk"}],"_npmOperationalInternal":{"host":"s3://npm-registry-packages-npm-production","tmp":"tmp/quiver_2.0.0_1783242438500_0.09236519849032665"},"_hasShrinkwrap":false}},"time":{"created":"2026-07-05T09:07:18.306Z","2.0.0":"2026-07-05T09:07:18.621Z","modified":"2026-07-05T09:07:18.797Z"},"maintainers":[{"name":"brijeshc2049","email":"brijeshchandrakar@hotmail.co.uk"}],"description":"A curated quiver of composable skills for Claude Code: interviews, audits (security, design, UX, a11y), deep review, debugging, testing, perf, plain-language explanations, and a full anti-generic design suite. Installs skill folders into your Claude Code ","homepage":"https://github.com/brijeshc/quiver#readme","keywords":["claude","claude-code","skills","code-review","design","performance","readability","testing","cli"],"repository":{"type":"git","url":"git+https://github.com/brijeshc/quiver.git"},"author":{"name":"Brijesh Chandrakar"},"bugs":{"url":"https://github.com/brijeshc/quiver/issues"},"license":"MIT","readme":"# 🏹 Quiver\n\n**A curated quiver of skills for Claude Code. Every arrow has a purpose.**\n\nQuiver is a set of 31 sharply-scoped, composable skills that make Claude Code interview like a senior engineer, audit like a skeptic, debug like a scientist, and design like it has taste.\nVersion 2.0 rebuilds the whole collection on a strict authoring contract: shared procedure cores, thin domain wrappers, and a no-op test that deletes every sentence that doesn't change the agent's behavior.\n\n```text\nYou:    /ask-me a billing export feature\nClaude: Walk me through the moment a user needs this export.\n        What were they doing right before? …\n        → writes SPEC.md you both agree on\n\nYou:    /design-audit src/\nClaude: → scope, hunt, verify, report: the 3 structural moves\n          that unlock the most, ranked by leverage\n```\n\n## Why Quiver exists\n\nMost skills collections suffer the same three problems: skills that are **vague** (\"makes your code better\"), **overlapping** (four flavors of code review), and **bloated** (walls of prose the agent skims).\nQuiver fixes all three:\n\n- **Every skill is a contract.** Its description says exactly when it triggers; its body says exactly what procedure runs and what deliverable you get.\n- **Zero overlap by design.** Audits sweep the codebase, reviews judge the diff, and every name encodes its scope. You always know which arrow to draw.\n- **Nothing is bloated.** Wrapper bodies stay under ~150 words, cores under ~300; depth lives in reference files loaded only when needed. The rules are public in [docs/WRITING-SKILLS.md](docs/WRITING-SKILLS.md).\n\n## Install in 60 seconds\n\n**Option A - npm (one cross-platform command):**\n\n```bash\nnpx @brijeshc2049/quiver install          # all skills -> ~/.claude/skills\nnpx @brijeshc2049/quiver install --project # -> ./.claude/skills (share with your team)\nnpx @brijeshc2049/quiver install ask-me deep-review   # just a few; required cores are pulled in\n```\n\n**Option B - plugin marketplace (native, versioned, no file copying):**\n\n```text\n/plugin marketplace add brijeshc/quiver\n/plugin install quiver@quiver\n```\n\nSkills are namespaced as `/quiver:ask-me` and update with `/plugin marketplace update quiver`.\n\nStart (or restart) Claude Code, type `/`, and you'll see the skills.\nManual `git clone` + copy, subset rules, and troubleshooting: see **[docs/INSTALL.md](docs/INSTALL.md)**.\n\n## The architecture: cores + wrappers\n\nTwo **core** skills hold the procedures; thin **wrappers** point a domain lens at them.\n\n| Core | The loop | Its wrappers |\n|---|---|---|\n| [`interviewing`](skills/interviewing/SKILL.md) | one question at a time → saturation → deliverable | `ask-me`, `design-discussion` |\n| [`auditing`](skills/auditing/SKILL.md) | scope → hunt → verify → report | `security-audit`, `design-audit`, `ux-audit`, `a11y-audit` |\n\nA wrapper is ~100 words: \"run the core with this lens, produce this deliverable.\"\nIts checklist lives in a `lens.md` beside it.\nInstall a wrapper and its core together; a wrapper without its core fails visibly instead of degrading.\n\n## The quiver\n\n### Interviews - settle it before building\n\n| Skill | Draw it when… | What you get |\n|---|---|---|\n| [`/ask-me`](skills/ask-me/SKILL.md) | starting anything ambiguous | An interview (one question at a time) → a `SPEC.md` you both agree on |\n| [`/design-discussion`](skills/design-discussion/SKILL.md) | weighing architecture choices | Sparring with trade-offs and recommendations → an ADR per decision (or a session `DESIGN.md`) |\n\n### Audits - sweep the existing code\n\n| Skill | Draw it when… | What you get |\n|---|---|---|\n| [`/security-audit`](skills/security-audit/SKILL.md) | touching auth, input, or going to production | Untrusted-data walk: injection, authz, secrets - severity, source→sink, fixes |\n| [`/design-audit`](skills/design-audit/SKILL.md) | code feels hard to change | Structural findings ranked by leverage, each naming the change it makes expensive |\n| [`/ux-audit`](skills/ux-audit/SKILL.md) | users say it's hard to use | Flow walk: the moments users are confused, blocked, or misled |\n| [`/a11y-audit`](skills/a11y-audit/SKILL.md) | building or auditing any UI | WCAG 2.2 AA pass: keyboard walk, semantics, contrast computed not eyeballed |\n\n### Workflow - build, verify, ship\n\n| Skill | Draw it when… | What you get |\n|---|---|---|\n| [`/deep-review`](skills/deep-review/SKILL.md) | a diff/branch/PR needs judgment before merge | Real bugs with evidence and severity, never style nitpicks |\n| [`/root-cause`](skills/root-cause/SKILL.md) | something is broken or flaky | Reproduce → isolate → prove → fix + regression test |\n| [`/write-tests`](skills/write-tests/SKILL.md) | coverage is missing or hollow | Behavior-focused tests that survive refactoring, run and shown passing |\n| [`/perf`](skills/perf/SKILL.md) | something is slow | Profile → fix the proven bottleneck → before/after numbers |\n| [`/refactor`](skills/refactor/SKILL.md) | structure blocks the next feature | Behavior-preserving steps, tests green after every one |\n| [`/readable`](skills/readable/SKILL.md) | code works but humans struggle | Naming/structure/comment pass, behavior untouched |\n| [`/simply-explained`](skills/simply-explained/SKILL.md) | anything needs explaining | Plain words, one analogy, one mermaid diagram, exportable to markdown |\n| [`/document`](skills/document/SKILL.md) | docs are missing or stale | READMEs/API docs/docstrings/ADRs for a named reader, examples executed |\n| [`/api-design`](skills/api-design/SKILL.md) | designing any interface others call | Caller-first design: example code → contract → evolution plan |\n| [`/ship`](skills/ship/SKILL.md) | work is done, tree is messy | Atomic commits with honest messages; optional reviewable PR |\n\n### Design suite - the anti-generic system\n\nStart with the foundation, then layer a register:\n\n| Skill | The register |\n|---|---|\n| [`/design-dna`](skills/design-dna/SKILL.md) | **Foundation** - banned generic tells, identity derivation, type/color/space/motion contract |\n| [`/design-scholarly`](skills/design-scholarly/SKILL.md) | A university press monograph |\n| [`/design-minimal`](skills/design-minimal/SKILL.md) | Rams-era Braun, Swiss typography |\n| [`/design-expressive`](skills/design-expressive/SKILL.md) | A magazine cover, a concert poster |\n| [`/design-brutalist`](skills/design-brutalist/SKILL.md) | Béton brut, early-web, gig flyers |\n| [`/design-luxe`](skills/design-luxe/SKILL.md) | A flagship boutique at midnight |\n| [`/design-playful`](skills/design-playful/SKILL.md) | Great toy design |\n| [`/design-mood <emotion>`](skills/design-mood/SKILL.md) | Emotion → full system: 10 recipes in [moods.md](skills/design-mood/moods.md) |\n| [`/design-scene <scene>`](skills/design-scene/SKILL.md) | Lived moment → full system: 10 recipes in [scenes.md](skills/design-scene/scenes.md) |\n\n### Meta - run the quiver itself\n\n| Skill | Draw it when… | What you get |\n|---|---|---|\n| [`/which-arrow`](skills/which-arrow/SKILL.md) | unsure which skill fits | One recommendation with the exact command, or the full chain |\n| [`/handoff`](skills/handoff/SKILL.md) | parking work or switching sessions | `HANDOFF.md`: state, decisions, gotchas, next steps - verified against the tree |\n| [`/to-issues`](skills/to-issues/SKILL.md) | a spec needs to become tracker work | Vertical-slice issues with acceptance criteria, via `gh` or as files |\n| [`/to-prd`](skills/to-prd/SKILL.md) | a discussion settled what to build | `PRD.md` distilled from the conversation, gaps marked as open questions |\n\n## How skills work (30-second primer)\n\nA skill is a folder with a `SKILL.md` - instructions Claude loads only when needed.\nTwo ways a skill fires:\n\n1. **You invoke it:** type `/readable src/billing/` - explicit, with optional arguments.\n2. **Claude invokes it:** say *\"this function is impossible to follow\"* and Claude loads `readable` on its own.\n\nSix Quiver skills are deliberately **manual-only** (`/ask-me`, `/design-discussion`, `/ship`, `/handoff`, `/to-issues`, `/to-prd`) - interviews, commits, and published artifacts happen on your schedule, never Claude's.\n\nSkills compose. A typical feature, end to end:\n\n```text\n/ask-me payments retry logic        → SPEC.md agreed\n/design-discussion queue vs cron    → ADR 0007 recorded\n/to-issues                          → 4 vertical slices\n  …build against the spec…\n/write-tests                        → behavior coverage, run green\n/deep-review                        → 1 blocker found and fixed\n/ship pr                            → atomic commits + reviewable PR\n```\n\nMore chains in **[docs/USAGE.md](docs/USAGE.md)**.\n\n## Documentation\n\n| Doc | What's in it |\n|---|---|\n| [docs/INSTALL.md](docs/INSTALL.md) | All three install methods, per-OS commands, verification, updating, troubleshooting |\n| [docs/USAGE.md](docs/USAGE.md) | Which skill when, chaining recipes, design-suite decision guide |\n| [docs/WRITING-SKILLS.md](docs/WRITING-SKILLS.md) | The authoring contract every Quiver skill is built to - write your own to the same bar |\n| [docs/TESTING.md](docs/TESTING.md) | The live-fire test log: how each skill is verified, with results |\n\n## FAQ\n\n**Do these conflict with Claude Code's bundled skills (`/code-review`, `/security-review`)?**\nNo - Quiver names avoid every bundled name (`deep-review` not `code-review`, `security-audit` not `security-review`).\nThat's a rule in the authoring contract, not a coincidence.\n\n**Can I install just one skill?**\nStandalone skills (workflow, design, meta): yes, copy the folder.\nWrappers need their core too: `ask-me`/`design-discussion` need `interviewing`; the four `*-audit` skills need `auditing`.\nThe pairs are listed in [docs/INSTALL.md](docs/INSTALL.md).\n\n**What happened to `/harden` and `/a11y`?**\nRenamed in 2.0: `/harden` became `/security-audit` and `/a11y` became `/a11y-audit`, joining the audit family on the shared core.\nDelete the old folders when updating a 1.x install.\n\n**Claude triggers a skill when I don't want it.**\nAdd `disable-model-invocation: true` to that skill's frontmatter, or set it to `\"off\"` under `skillOverrides` in your settings.\n\n**Why are the SKILL.md files so opinionated?**\nVague instructions produce average output, and average is the problem.\nDisagree with an opinion? Edit the file - it's markdown, and it's yours after install.\n\n## License\n\nMIT - see [LICENSE](LICENSE).\n","readmeFilename":"README.md","_rev":"1-0f0e0701d960fef291e21ed3b29d7f01"}