engy

Plugin engy from marketplace engy-marketplace in ZanderAdam/Engy. Commands read from the repo's manifest — yesterday.

Skills (19)

• complete-project

  This skill should be used when the user asks to 'complete a project', 'wrap up a project', 'archive a project', or 'run project completion'.

• feature-docs

  This skill should be used when the user asks to "bootstrap feature docs", "write feature requirements", "establish the EARS baseline", "author FRs for the codebase", "create feature area docs", or "author requirements for a feature area". Sole owner of system/features/<area>.md — authors the complet

• implement-milestone

  This skill should be used when the user asks to 'implement milestone', 'implement all tasks', 'implement m5', or when working on an entire milestone's worth of tasks. Orchestrates milestone-level implementation across task groups with agent teams.

• implement

  This skill should be used when the user asks to 'implement', 'implement a task', 'implement a plan', 'execute a plan', 'work on task', or 'start implementation'.

• ingest

  This skill should be used when the user asks to "ingest", "capture this URL", "add this article to memory", "save this transcript", "ingest this document", or "add this to the knowledge layer". Snapshots non-durable sources, links durable ones, drafts a fleeting distillation, dispatches research, an

• investigate

  This skill should be used when the user asks to 'investigate X', 'look into X and file a task', 'research and track X', 'create a task from finding', or wants to explore a codebase concern and capture it as a tracked work item.

• knowledge-research

  This skill should be used when the user asks to "search knowledge", "what do we know about X?", "look up prior decisions on X", "find conventions for X", or "research the knowledge base".

• milestone-plan

  This skill should be used when the user asks to 'plan my project', 'plan milestones', 'break down into tasks', or 'create tasks for milestone'. Plans spec milestones in detail — task groups, tasks, dependencies, and priorities.

• plan

  This skill should be used when the user asks to 'write a plan', 'plan implementation', 'plan milestone', 'create implementation plan', or when planning complex changes — new features, architecture changes, multi-file work, or anything with ambiguous scope. Writes a validated implementation plan usin

• reindex

  This skill should be used when the user asks to "reindex", "rebuild the index", "force reindex", "refresh search", or "reindex workspace content".

• review-diff

  This skill should be used when a repoDir and an explicit diff scope (staged, unstaged, a commit, or a commit range) need reviewing with findings written back as inline diff comments — reviewing a colleague's branch, a pull request diff, or local uncommitted work, wherever the scope is given explicit

• review-memories

  This skill should be used when the user asks to "review memories", "review fleeting memories", "promote memories", or "run memory review". Reviews unpromoted fleeting memories in similarity clusters (singletons one by one, near-duplicates as one merged unit), proposes type/subtype/title/keywords/the

• review

  This skill should be used when the user asks to 'review changes', 'review my code', 'run a code review', 'review last commit', 'review recent changes', or 'check code against spec'.

• session-distill

  This skill should be used when the user asks to "distill this session", "save session learnings", "capture learnings from this session", "what's worth remembering from this session", "session distill", or "extract memories from this session". Reflects over the current conversation, extracts 1–3 atom

• validate-plan

  This skill should be used when the user asks to 'validate a plan', 'check plan against spec', or 'verify plan alignment'. Validates a project plan against its parent spec for alignment, missing requirements, and consistency.

• validate

  This skill should be used when the user asks to "validate workspace", "check knowledge integrity", "run validation", "check for broken links", or "verify memories before promoting".

• workspace-assistant

  This skill should be used when the user asks to create quick tasks, log bugs, track one-off work items, or manage tasks in the default project. Triggers on phrases like 'add a task', 'log a bug', 'track this', 'create a quick task', 'update task status'.

• write-spec

  This skill should be used when the user asks to 'write a spec', 'create SRS', 'generate spec', 'author spec', 'spec from vision', 'validate spec', 'review spec', 'check SRS', 'validate SRS against context', 'save context', 'add context file', or 'save this as context'. Creates or validates a Softwar

• write-sysdocs

  This skill should be used when the user asks to "bootstrap/generate/initialize system docs", "propose/update/refresh system docs", "edit/fix/browse a system doc", or "surface project knowledge to system docs". Dispatches in one of three modes depending on intent.

Subagents (4)

• feature-author

  Feature doc author — reads a BDD behaviour inventory for a feature area and authors the complete feature doc (prose body + EARS ## Requirements table + ## Sources + frontmatter) grounded in the inventoried behaviours. Writes uncommitted for human review.

• research

  Multi-collection knowledge researcher. Dispatch via Task tool to surface relevant prior decisions, patterns, facts, and conventions for a given question or planning context.

• reviewer

  Unified code reviewer — simplifies code directly (no behavior changes), then reviews and surfaces severity-tagged findings.

• srs-reviewer

  SRS validator and fixer — cross-references a spec.md against source documents (vision docs, context files), identifies missing/incorrect requirements, and fixes them in place.