personal-agents

Harvest every `deferred:` comment in the codebase into a debt ledger, so deliberate shortcuts and deferrals get tracked instead of rotting into "later means never". Use when the user says "debt ledger", "/debt-ledger", "what did we defer", "list the shortcuts", "ponytail ledger", or "what did we mark to do later". One-shot report, changes nothing.

Vertical-slice implementation with TDD inside each slice. Reads the plan and kanban-board artifacts to determine which slice to implement. Each slice crosses all layers (data → pure → edge → UI → integration) and follows Red-Green-Refactor. Clear context between slices. Use this skill whenever the user says "implement", "start coding", "proceed with implementation", "/implement", or wants to begin implementation after a plan exists. Entry point: /implement

Review diffs for over-engineering only. Finds what to delete: reinvented standard library, unneeded dependencies, speculative abstractions, dead flexibility. One line per finding with tag and replacement. Use when the user says "review for over-engineering", "what can we delete", "is this over-engineered", "simplify review", "yagni review", or invokes /yagni-review. Complements correctness-focused /review — this one only hunts complexity.

Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Produces a decision log artifact consumable by /plan. Invoke with "/grill-me [topic]".

Fetches a Jira ticket, detects its type, and generates a type-aware implementation plan with Kanban/DAG vertical slices. Presents the plan for approval before writing it back to Jira as a comment. Produces both a plan artifact and a kanban-board artifact. Use this skill whenever the user invokes /plan PROJ-123 or asks to generate an implementation plan for a Jira ticket. Entry point: /plan PROJ-123

Run the full verification suite (lint, type check, tests), gate on the review artifact, commit, push, and create a merge request. Use this skill whenever the user says "ship it", "commit and push", "create MR", "open a merge request", "push my branch", or wants to finalize and submit their work.

Codify a correction or convention from the current session into AGENTS.md (global) or .agents/conventions.md (project-specific) in "Always/Never [action] BECAUSE [reason]" format. Use this skill whenever the user says "remember this", "add a rule", "don't do that again", "learn this", "/learn", or wants to capture a lesson from the session before the conversation ends. Entry point: /learn [optional rule text]

Creates Architecture Decision Records (ADRs) when significant design choices are made. Captures context, decision, consequences, and alternatives rejected — the "why" that AGENTS.md doesn't hold. Use this skill whenever the user says "record this decision", "write an ADR", "document why we chose X", "capture this architecture decision", or wants to preserve design rationale for future reference. Stores under docs/decisions/ or .agents/decisions/ (whichever exists). Entry point: /adr [optional decision title or description]

Generate a hierarchical architectural codemap of the codebase — a high-level map of every folder explaining its responsibility, design patterns, data flow, and integration points. Use this skill when the user says "codemap", "understand the codebase", "map this repo", "what's in this codebase", or when entering an unfamiliar repository to get oriented. Entry point: /codemap

Guide the creation of a new skill or agent using the 10 research-backed OpenCode principles as a quality checklist. Produces a ready-to-lint SKILL.md or agent .md file. Use this skill whenever the user says "create a skill", "new skill", "add an agent", "build a slash command", "/create-skill", or wants to author a new workflow extension for this repo. Entry point: /create-skill [skill|agent] [name]

Review code changes on the current branch against main. Use this skill whenever the user asks to "review my branch", "check my changes", "code review", "review this PR", "what did I change", or any variation of reviewing uncommitted or unmerged work. Trigger even if the user just says "can you check this branch" or "look at my changes" — they almost certainly want a structured code review.

Enforces that all skill and agent edits happen in the source repo, not the deployed locations. Use this skill whenever you are asked to edit, update, modify, or create a skill or agent, or whenever a direct edit to ~/.config/opencode/skills/, ~/.config/opencode/agents/, or ~/.agents/ is requested. Entry point: /update-skill