Menu
Skills dans ce dépôt
SkillsMP a collecté 121 skills depuis kapilvirenahuja/garura. Ouvrez un skill pour examiner sa source et ses détails.
kapilvirenahuja/garuraAffichage de 40 skills collectés sur 121.
Infer the foundational project-profile.yaml (product identity, team shape, technology posture, compliance hints, platform targets, delivery maturity) from scan-index.json during /codify, with every field grounded in concrete scan-index evidence and tagged…
Langue du texte source : anglais
Infer the product's ISO 25010:2023 quality-profile.yaml (characteristic-level targets, security profile, risk register) from scan-index.json during /codify, grounding every characteristic level and every risk entry in concrete scan-index signals and tagging…
Langue du texte source : anglais
Synthesize a quality-vision proposal for a brownfield codebase by merging the already-inferred nfr-spec, quality-profile, physical-architecture, and logical-architecture proposals, then attaching scan-index signals (ADRs, CI/lint/test config files, commit…
Langue du texte source : anglais
For every domain in the upstream domain-selection proposal, derive a product-scoped research Markdown file from scan-index.json evidence plus the canonical domain KB, carrying the five KB-extension sections with inline knowledge_gap markers wherever code…
Langue du texte source : anglais
Infer the v1 scope.yaml (selected / deferred / rejected capabilities plus depth caps, within-domain coverage gaps, and constraint trace) by scoring KB capabilities against scan-index.json signals during /codify. Bounds the selection to the domains already…
Langue du texte source : anglais
Compose /validate's findings from CAPTURED results only — the judgment half of the finder's job. Reads the normalized check results (results/*.json + summary.json from run_checks) and the gates/benchmark map (gates-map.json from check_gates), and writes…
Langue du texte source : anglais
Search the empirical Knowledge Base for the best-fit architecture and technology learnings given a product's conditions. Use during context-building in the realize lenses (/arch, /run, /ux, /agentic) when you need to know what worked before for a product in…
Langue du texte source : anglais
Validates Garura components (plays, agents, skills) against structural, semantic, and cross-reference rules. Reads quality profile to classify violation severities.
Langue du texte source : anglais
Author the canonical 3-tier domain → capability → feature catalog (features.yaml) from enriched-capabilities.yaml using the 5-point status vocabulary (planned | development | rollout | released | cleanup). Use this skill whenever product-keeper needs to…
Langue du texte source : anglais
Enumerate every test file in a codebase, extract test subjects and assertions, detect the test framework in use, and emit test-surface.yaml. Used by test-engineer.
Langue du texte source : anglais
Author /validate's check manifest for one EPIC — the toolchain plan the run_checks orchestrator executes. Detects the product's stack(s) from the slice's architecture lens tech picks plus the repository's own manifests (package.json, pom.xml, *.csproj,…
Langue du texte source : anglais
The nothing-fits path for the KB router. When search-kb returns unmatched (a piece of work has no home in the knowledge base), research the gap, draft a properly-shaped node at the right level (new domain, capability, or functionality) following the shelf…
Langue du texte source : anglais
Rank /next's derived candidate set into one next-best-action plus a ranked list (≤11 entries total), each with the exact command and a plain-language explanation of why it is recommended and what it unblocks — weighing structural priority (repair first,…
Langue du texte source : anglais
Produce the MVP recommendation artifact at .garura/product/scope/mvp-recommendation.md. Narrows the capability walk by selecting primary use cases from the brief, deferring the rest with v1.1+ triggers, and recording any architecture directions committed at…
Langue du texte source : anglais
Parse a product idea, query web and LTM for market context, produce a quantified market brief with TAM/SAM/SOM, competitive landscape, market gaps, and risks. Fresh skill built in 214.5; not the deleted discover-product-opportunity.
Langue du texte source : anglais
Execute generated tests against the current codebase using the detected TEST_HARNESS and report pass/fail per test. Context-isolated — consumed ONLY by the test-runner agent, which receives no extraction context. Reports pass/fail plus stderr; does not…
Langue du texte source : anglais
Run the deterministic codebase scanner (core/components/plays/codify/lib/scan.py) over one or more repository roots and produce a bounded scan-index.json under STM. This skill is the sole structured-input producer for every infer-*-from-code skill. No LLM is…
Langue du texte source : anglais
Search the product knowledge base for where a piece of work belongs — its domain, capability, and functionality — by reasoning over the KB router interface. Runs the inference sandwich (list domains, reason to the domain, read that shelf, reason to the…
Langue du texte source : anglais
Given coverage gaps from blast-radius.yaml, author specifications for baseline tests that capture CURRENT behavior before changes begin. Writes baseline-tests.yaml. Used by test-engineer.
Langue du texte source : anglais
Bring one epic's increment up LIVE on the slice's LOCAL environment so a human can walk it — the deploy half of /launch's HITL gate. Reads the slice's structured run.yaml for the local environment's declared bring-up (its `local.run` command and any seed) and…
Langue du texte source : anglais
Scan product-stage artifacts (research/, specification/, scope/) for abstraction-layer deny-list tokens — specific database engines, SDK method names, framework identifiers, programming-language type signatures, wire-level protocol identifiers, cryptographic…
Langue du texte source : anglais
Blocking validator for the six-artifact arch output contract (refined quality-profile, systems-inventory, logical-architecture, physical-architecture, tech-stack, technical-risks) plus their decision manifests. Enforces 22 checks derived from arch intent.yaml…
Langue du texte source : anglais
Cross-validate YAML implementation artifacts against intent constraints for coverage, compartmentalization, audience separation, and structural completeness
Langue du texte source : anglais
Walk every feature in every domain-taxonomy markdown file and assert the 5 required KB extension sections (Inclusion, Success Criteria, Failure Scenarios, Cross-Tree Refs, Experiential) are present and non-empty. Also validates that cross-tree constraints…
Langue du texte source : anglais
Analyze branch and generate context-aware quality checklist
Langue du texte source : anglais
Quality assessment framework using 11 parallel explore subagents across code, testing, security, architecture, documentation, operations, frontend, backend, data, performance, and tech-debt governance. Reads KB quality standards calibrated by the project's…
Langue du texte source : anglais
Stage 2 skill of /arch. Reads the /specify quality profile, refines targets against architectural reality (inventory constraints, project-profile pins, epic constraints), and writes the refined quality profile to architecture/ with a delta log of every…
Langue du texte source : anglais
Read, create, close, comment, resolve, or list GitHub issues with optional sub-issue attachment
Langue du texte source : anglais
Merge a pull request on the configured platform, switch to main, pull latest, and delete the feature branch (local and remote)
Langue du texte source : anglais
Stable verb interface for code-host operations. Resolves the active platform from config and dispatches to the correct CLI (gh for GitHub, glab for GitLab). Exposes exactly 16 verbs — callers pass a verb name and arguments; the adapter handles platform…
Langue du texte source : anglais
Push branch and create pull request with formatted checklist
Langue du texte source : anglais
Author a structured intent.yaml file (the ICE clean triple) from interview material. Takes an extracted interview digest (goal, constraints, failure conditions) and produces a well-formed intent.yaml conforming to the Garura intent schema. Scenarios and…
Langue du texte source : anglais
Map change groups to existing open issues with confidence scoring. Use when you have grouped file changes and need to determine which issue each group belongs to before committing.
Langue du texte source : anglais
Create a plan.yaml artifact — execution order of features as vertical slices with scope items, exit gates, and scenario gates
Langue du texte source : anglais
Create a tech.yaml artifact with project structure, libraries, data model, components, design decisions, and feature mapping from features and architecture specifications
Langue du texte source : anglais
Create an architecture.yaml artifact with technology selections, NFRs, platforms, integrations, and agentic PCAM design from a features specification
Langue du texte source : anglais
Research vertical domain knowledge via web when LTM is insufficient
Langue du texte source : anglais
Create branch, push to origin, optionally use worktree for dirty trees
Langue du texte source : anglais
Author a failing regression-test artifact (a YAML eval-spec with grep or structural assertions) that captures the defect from rca.yaml / design.yaml, verify it is in a red state against the current codebase, and return the path. Enforces the TDD…
Langue du texte source : anglais
Given a completed rca.yaml, design a fix with at least one alternative considered and rejection reason, affected-files map with change specifications, and a self-sufficient execution plan. Writes design.yaml.
Langue du texte source : anglais