fr-e-d/gaai-framework
60 skills · 1 total installs
$npx skills add fr-e-d/gaai-frameworkSkillInstalls
ambiguity-detectorTakes surface scan results, optional LLM synthesis open-question entries, and optional tree-sitter AST signals to score project ambiguities (1-10).abort-safe-handlerOrchestrator-level Stage 4 entry gate for /gaai:bootstrap. Presents a pre-loop "Skip Q&A entirely" option, delegates to qa-loop-ui when the user proceeds, and…approach-evaluationResearch industry standards and best practices, identify viable approaches for a given technical or architectural problem, and produce a structured factual…architecture-extractConvert raw project structure into clear architectural understanding — module boundaries, data flows, service relationships, and architectural patterns.bootstrap-llm-synthesisConstruct the LLM synthesis prompt from project surface scan + optional tree-sitter context + optional Q&A answers. Call the LLM.bootstrap-memory-ingest-cloudWrite structured memory entries to the Cloud workspace via gaai_memory.store MCP tool with source='bootstrap'.browser-journey-testValidate user stories by simulating real user journeys in a live browser against deployed application.build-agents-indexScan all agent and sub-agent definition files in .gaai/core/agents/, extract YAML frontmatter, merge with specialists.registry.yaml, and generate a derived…build-skills-indexScan SKILL.md files in .gaai/core/skills/ and .gaai/project/skills/, extract YAML frontmatter, and regenerate separate skills indices for each layer.ci-watch-and-fixWatch GitHub Actions CI after PR creation, detect failures, extract logs, apply minimal fixes, and re-push — keeping the delivery session alive until CI…codebase-scanCreate a high-level map of the project structure and identify architectural pillars, entry points, and module boundaries.compose-teamAssemble the context bundles for each sub-agent based on evaluate-story output.consistency-checkDetect inconsistencies across related artefacts and governance constraints.context-buildingAssemble a minimal, high-signal execution context bundle from already-retrieved memory, governed artefacts, and applicable rules.coordinate-handoffsValidate sub-agent handoff artefacts, sequence phase transitions, and manage retry and escalation logic.create-skillGuide creation of a new GAAI skill following the agentskills.io spec and GAAI best practices.decision-extractionIdentify and formalize durable product and technical decisions from agent outputs into long-term memory.delivery-high-level-planTransform validated Stories into a clear, minimal, governed execution plan.delivery-readiness-auditSpot-check AC internal consistency and scan for pending revisions on delivery-ready stories. Activated by `/gaai-status --audit` as Section 5.eval-runEvaluate any output file against a structured evals.yaml assertions file and produce a score report with per-assertion pass/fail results.evaluate-storyAssess Story complexity, identify required domains, and determine delivery tier (MicroDelivery / Core Team / Core Team + Specialists).friction-retrospectiveScan delivery artefacts for friction log entries, detect recurring patterns, and produce retrospective reports.gaai-oss-askSearch local GAAI OSS project memory without using GAAI Cloud MCP tools.gaai-oss-bootstrapInitialize or refresh a project's GAAI OSS memory by activating the Bootstrap Agent and context-bootstrap workflow.gaai-oss-daemonStart, stop, or inspect the GAAI OSS autonomous delivery daemon from Codex.gaai-oss-deliverImplement validated GAAI OSS backlog Stories by activating the Delivery Agent and applying backlog-first delivery rules.gaai-oss-discoverActivate the GAAI OSS Discovery Agent to clarify intent and produce governed artefacts such as PRDs, Epics, Stories, and decisions.gaai-oss-statusSummarize current GAAI OSS project state, including backlog, memory, rules, skills, and framework health.gaai-oss-updateUpdate or redeploy the local GAAI OSS framework and Codex adapter without invoking GAAI Cloud behavior.i18n-glossary-syncMaintain a canonical i18n glossary file — sync new terms across all language pairs, detect drift, flag missing translations, and enforce consistent terminology…i18n-validateValidate translation completeness and consistency across all locale files — detect missing keys, untranslated strings, format mismatches, and glossary…idiomatic-translateTranslate strings idiomatically across multiple target languages using a project glossary, preserving tone, domain terminology, and format placeholders while…implementGenerate correct, minimal, maintainable code that satisfies a validated Story's acceptance criteria against an execution plan.memory-alignment-checkAfter QA PASS, compare the Story's implementation footprint against relevant memory entries.memory-archive-supersededMigrate a superseded DEC's index rows from active `index.md` to `archive/superseded-decisions.archive.md`. Idempotent.memory-compactEmergency single-pass memory compression when context window pressure is high mid-task. Activate when approaching token limits during active work.memory-delta-triageApply three deterministic heuristics to a single memory-delta file to produce a structured verdict block; invoke memory-ingest on ACCEPTED candidates only in…memory-index-compactCompact verbose memory index / registry files to pointer-only form.memory-index-lintValidate discoverability invariants of memory `index.md` and `archive/superseded-decisions.archive.md`.memory-index-syncDetect and heal index.md drift — finds memory files on disk not registered in index.md and registers them.memory-ingestTransform validated knowledge into structured long-term memory.memory-reconcileScan all memory files, documentation (**/docs/**/*.md), and README files (**/README.md) for drift, contradictions, and stale references.memory-refreshPeriodic memory maintenance — archive session files, convert recurring knowledge into summaries, update the memory index.memory-retrieveLoad only the minimum relevant memory for a task using 3-level progressive disclosure. Activate before context-building — never load full memory dumps.memory-searchSearch memory by frontmatter fields, full-text keywords, or cross-reference graph. Returns ranked file list — never loads full content.pattern-transferDiscover structurally similar patterns across domains, assess transfer viability via structural invariant checking, and propose domain adaptations with risk…post-mortem-learningAnalyze failures and suboptimal deliveries to identify root causes, contributing factors, and raw lessons.prepare-execution-planDecompose a high-level delivery plan into a precise, file-level execution sequence with explicit ordering, edge cases, and test checkpoints.project-surface-scanScan project root for file tree, dominant languages, and LOC estimate. Produces structured baseline context for Stage 2 LLM synthesis during bootstrap.qa-loop-uiPresents up to 5 questions from smart-question-generator one at a time, records answers, handles per-question skip and skip-all, captures per-question response…qa-reviewValidate that implemented code fully satisfies Story acceptance criteria, respects rules, and introduces no regressions.risk-analysisSystematically identify and structure product, delivery, and systemic risks before they become failures.rules-normalizeConvert implicit or scattered project conventions into governed GAAI rule files, and create or modify rule files with integrity.security-auditDetect security vulnerabilities and governance violations across delivered code, configurations, and deployed environments.skill-optimizeRun a structured evaluate-analyze-improve cycle on any GAAI skill to measure quality, detect regressions, and propose targeted improvements.skill-usage-auditScan all artefacts (epics, stories, PRDs) for Base Rule #2 compliance — verify that every artefact declares skills_invoked and related_decs in frontmatter.smart-question-generatorTakes aggregated ambiguity insights from the LLM synthesis stage and produces ≤5 ranked questions to surface to the user.success-metrics-evaluationEvaluate delivery outcomes against defined success metrics and acceptance goals.summarizationTransform large, noisy, or short-term memory into compact, durable, high-signal summaries.user-skip-telemetryCounts Q&A skip events from the abort-safe-handler and qa-loop-ui outputs. Shows an optional skip-reason dropdown when a user-initiated skip occurred.