claude

yamlet-skills

Spec-driven development with yamlet: an interviewing author drills you down to minimal, testable `.yamlet.yaml` specs with EARS acceptance criteria, appending through the `yamlet` CLI so the file is correct by construction (the CLI owns all serialization and IDs). Two adversarial challengers guard the one-way init and commit gates, a verifier closes the loop, and a refresh skill projects the specs into a Gherkin feature tree and Markdown docs pages. A tech spec skill then plans each change against your code, across every spec it touches — a verdict per criterion and per obligation of the linked ADRs, then one task list covering every unmet one — and an ADR skill records each decision as a frozen `.adr.yaml` linked into the spec. Requires the `yamlet` CLI on PATH.

5 on GitHubby Ricardo Monteiro Simoesv0.8.0MITupdated 3 days ago
/

Plugin yamlet-skills from marketplace yamlet in RicardoMonteiroSimoes/Yamlet. Commands read from the repo's manifest — 2 days ago.

What it installs

Skills (10)

  • yamlet-adr-challenger

    Adversarial gate INSIDE the yamlet-adr flow, before options and before accept: checks the judgement the verifier cannot. Invoked by yamlet-adr; not a standalone tool.

  • yamlet-adr

    Writes a decision record (.adr.yaml) by interviewing the user and driving `yamlet adr`, never by hand-writing YAML. Use when a design choice must be recorded — standalone (`/yamlet-adr adr`) or inside yamlet-techspec's decision gate.

  • yamlet-author

    Creates and changes EARS spec files (.yamlet.yaml) by interviewing the user and driving the `yamlet` CLI — never by hand-writing YAML. Use when the user wants a new spec, a requirement or acceptance-criterion added to an existing one, an existing spec changed, or existing services wired together as

  • yamlet-code-research

    Read-only code research used INSIDE the yamlet-techspec flow. Given a code root, a spec's contract and one requirement with its EARS criteria (plus the obligations of the ADRs deciding it), it finds where each one's behaviour lives and reports facts with `file:line` references — what the code does,

  • yamlet-contract-challenger

    Adversarial gate used INSIDE the yamlet-author flow, immediately before `yamlet init` freezes a scope's contract. Given the proposed scope and its input/output contract, it pokes holes in them. Invoked by yamlet-author at the pre-init gate; not a standalone tool.

  • yamlet-criteria-challenger

    Adversarial gate used INSIDE the yamlet-author flow, before a requirement and its acceptance- criteria are committed. Given the proposed requirement, its intended EARS criteria and the scope's contract, it pokes holes in them. Invoked by yamlet-author before each `add-requirement`; not a standalone

  • yamlet-evidence-challenger

    Adversarial gate used INSIDE the yamlet-techspec flow, before a criterion or an ADR obligation is recorded as met. Given one EARS criterion (or obligation) and the exact `file:line` references offered as evidence, it opens those references and nothing else, and says whether each `shall` is really sa

  • yamlet-refresh

    Regenerates what is derived from a specs directory: the Gherkin `.feature` tree (`yamlet tests`) and the Markdown docs pages (`yamlet docs`). REQUIRES the specs directory (`/yamlet-refresh specs`); optional tests, docs and outside-records directories follow. Use as the closing step after a spec or d

  • yamlet-techspec

    Plans one change across every finished EARS spec (.yamlet.yaml) it touches, all of one system: reads the code, records a verdict per acceptance criterion and per obligation of the linked ADRs, then one task list covering every unmet one, all through `yamlet techspec` into a disposable `.techspec.yam

  • yamlet-verifier

    Verifies an EARS spec file (.yamlet.yaml) against the format rules and reports violations with stable rule IDs. REQUIRES the spec's path as its argument (e.g. `/yamlet-verifier specs/email.yamlet.yaml`). Use to self-verify a spec before relying on it.

View source on GitHub

Similar plugins

AgentBBS cross-host agent federation (ADR-164). Phase 1: register/publish/watch/human-join room coordination. Phase 2 (v3.40.0): signed cross-host federation — identity, peer_add (pin by nodeId+Ed25519 key), peers, serve (read-only pull), sync (pull + union-merge what verifies). Registry-anchored pinning; works on any network (no tailnet required); coordinates work claims (ClaimIssued/Released/Handoff/Ack). Degrades gracefully when agentbbs is absent.

1 skill

ruvnet/ruflo 81,589

clay

claudecodex

Work with Clay from Claude Code: set up and sign in to the clay CLI, query and analyze Clay tables, search Clay's GTM database for people and companies, manage audiences, signals, routines and workflows, and draft and review Sequencer campaigns. Includes hooks that auto-approve the plugin's own clay CLI calls and Clay skills; requires a Clay account.

38 skills · hooks

anthropics/claude-plugins-official 47,076

Require a human approval signal before an AI agent can post PR reviews, comments, merges, or writes to CI configuration. Joins protect-mcp and signed-audit-trails in the governance category; composes with protect-mcp for runtime enforcement.

1 skill · 2 commands · 1 agent · hooks

wshobson/agents 42,461

Maven Bio

claude

Evidence-backed BioPharma research workflows over Maven Bio's drug, trial, company, and deal knowledge graph. Skills for competitive pipelines, indication landscapes, asset profiles, deal and financing activity, and evidence synthesis grounded in FDA, SEC, clinical, and press sources. Requires a Maven Bio account.

16 skills · 1 agent · 1 MCP server

anthropics/knowledge-work-plugins 35,601

Per-deal-and-packaging Commercial domain. v2.8.0 ships 8 skills: orchestrator + pricing-strategist (model picker + Van Westendorp WTP + packaging) + deal-desk (deal scorer + discount approval routing + redline) + partnerships-architect (5-tier classifier + joint GTM + revshare modeler) + channel-economics (cost-to-serve + ROI + mix optimizer) + commercial-policy (data-backed discount matrix + exception flow + linter) + rfp-responder (Shipley structured RFP/RFI/RFQ + win-theme + winrate predictor, context: fork) + commercial-forecaster (4Q-weighted bookings + cohort NRR/GRR + funnel-confidence with mandatory assumption disclosure). Hard rules: pricing outputs model+range (never a single number), deal outputs route to named human approver (never auto-approve), forecast outputs surface conversion assumption, RFP never invents claims for GAP requirements. 21 stdlib Python tools, 28+ reference docs. Distinct from business-growth (sales execution), c-level-advisor/cro-advisor (strategic), finance (close+report).

8 skills · 9 commands · 1 agent

alirezarezvani/claude-skills 29,725

Real-time statusline showing context usage, active tools, running agents, and todo progress. Always visible below your input, zero config required.

1 skill

jarrodwatts/claude-hud 29,182

Maintain yamlet-skills?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex pluginslisted