j03fr0st-skills

Plugin j03fr0st-skills from marketplace j03fr0st in J03Fr0st/skills. Commands read from the repo's manifest — 12 days ago.

Skills (32)

• adlc-flow

  Route a piece of work through the agentic development lifecycle.

• adlc-gate

  Record a named human sign-off on an ADLC intent, spec, plan, or delivery slice.

• adlc-intent

  Capture a human's intent as a durable intent.md before agents build.

• adlc-plan

  Plan covered, assigned slices from an approved spec.md.

• adlc-spec

  Turn an approved intent.md into a testable spec.md.

• babysit-pr

  Carry an existing pull request through CI failures, review feedback, and merge. Use when asked to babysit a PR, keep it moving until completion, or resume an interrupted PR watch; a one-time status check or standalone review belongs elsewhere.

• code-review

  Review code changes read-only at quick, standard, or deep depth, with a bounded single-reviewer default and evidence-backed findings. Use when the user asks to review a branch, pull request, commit, working-tree changes, staged changes, a diff, or code before merge; asks for a quick or deep review;

• codebase-design

  Design or improve software architecture through cohesive modules, intentional dependency direction, explicit inter-module contracts, and evidence-gated abstraction. Use when the user asks about module or service boundaries, interfaces, coupling or cohesion, DRY/KISS/YAGNI, duplication versus abstrac

• coding-standards

  Supplies coding conventions for shared code, backend services, and frontend interfaces. Use when applying project coding standards during implementation, assessing convention violations in review, or defining standards for a project. Implementation stays with implement; review orchestration stays wi

• compound-learnings

  Capture and maintain durable engineering lessons - knowledge a future agent or engineer would otherwise rediscover the hard way or repeat. Use when a solved problem, incident, or surprising investigation may deserve a written lesson, when asked to document a learning or "remember this for next time"

• diagnosing-bugs

  Investigate an unexplained bug or performance regression when its cause requires evidence from code, runtime behavior, logs, or reproduction. Use for explicit diagnosis or root-cause requests, intermittent or environment-specific failures, and fix requests with an unknown cause. Answer quick questio

• git-workflow

  Git workflow - commits, pushes, branches, rebasing and syncing, branch freshness, stacks, backports, local integration, branch policy, and recovery. Use whenever committing or pushing changes, preparing a branch for review, rebasing, checking whether a branch is up to date or its changes already lan

• git-worktrees

  Git worktree lifecycle - selecting, creating, preparing, retiring, and recovering isolated checkouts. Use whenever setting up or cleaning up a worktree, when a task needs its own checkout, when parallel tasks or agents need separate working directories, when cleaning up a worktree after a merge, or

• implement

  Execute authorized software changes from direct requests, issues, specifications, or plans. Use when asked to build, change, refactor, or fix known-cause behavior. Diagnosis, explicit test-first work, review-only work, planning-only work, and research have dedicated workflows.

• orchestrate

  Coordinate non-trivial engineering work with bounded native subagents when independent execution, difficult diagnosis, current research, or an independent review materially helps. Use the active harness's own subagent and model mechanisms only; keep small, local, readily verifiable work with the roo

• planning-and-task-breakdown

  Plan technical work when clear requirements span dependent changes, multiple sessions, or an uncertain implementation order. Use for implementation plans, vertical slices, and task dependencies. A small clear change can go directly to implement.

• pr-description

  Pull request creation and PR titles and descriptions written from the final diff, with before/after evidence and a merge-danger section. Use whenever creating, opening, raising, or updating a pull request or PR (including `gh pr create` or a PR tool call), writing or rewriting a PR title or descript

• property-based-testing

  Property-based and generative testing - choosing properties, designing generators, and triaging shrunk counterexamples with Hypothesis, fast-check, QuickCheck, proptest, FsCheck, jqwik, or rapid. Use when the user asks for property-based, generative, or fuzz-style unit tests; when parsers, serialize

• prototype

  Build a small experiment to answer a design or feasibility question through observation. Use for trying a state model, comparing an interaction, or measuring an uncertain approach. Established bug diagnosis belongs to diagnosing-bugs; production changes belong to implement.

• research

  Investigate technical questions against primary sources and record cited findings. Use for repository comparisons, documentation or API research, and decisions that need external evidence. Use last30days when recent community discussion matters; local bug diagnosis belongs to diagnosing-bugs.

• security-review

  Review security and privacy risks read-only when a dedicated audit, threat model, dependency-risk assessment, or independent security gate is requested or needed. Routine changed-code review belongs to code-review; authorized remediation belongs to implement.

• ship-it

  Coordinates delivery of finished changes. Use when asked to ship completed work, take it to a merge-ready or merged PR, or resume an interrupted delivery across local work and a PR. A request only to commit or push belongs to git-workflow; only to create or open a PR, or write its title or descripti

• simplify

  Simplify working code for clarity and maintainability while preserving observable behavior. Use for requested cleanup of recent changes or a named area, reducing unnecessary nesting, duplication, or indirection. Architecture decisions belong to codebase-design; unknown failures belong to diagnosing-

• sprint-planning

  Plan a team sprint - sprint goal, capacity, breaking features into stories and investigation spikes, and assigning Fibonacci story points against the team's reference stories. Use when asked to plan or prepare a sprint, size or point a backlog, break an epic or feature into tickets, prepare for plan

• tdd

  Drive behavior changes through observable red, green, and refactor evidence. Use when the user asks for test-first development, TDD, red-green-refactor, a property or regression test before a fix, or when an implementation workflow or plan item needs a behavioral slice protected by an executable tes

• verification-before-completion

  Verify completion claims with fresh, claim-specific evidence and honest terminal states. Use before saying work is done, fixed, passing, ready, deployed, or compliant; when asked to verify, prove, double-check, or show that something works; or when another implementation, TDD, debugging, review, doc

• html-writeup

  Create and verify one standalone HTML report for a decision, comparison, audit, architecture explanation, plan, incident review, or research brief. Use when the deliverable needs document hierarchy plus tables, diagrams, evidence, or light navigation. Route production websites and application interf

• grilling

  Stress-test a consequential or ambiguous plan, decision, or idea through a live interview. Use when the user asks to be grilled, wants their thinking challenged, or material choices remain silently assumed. Do not use for clear mechanical work, information retrieval, or review of a completed artifac

• handoff

  Preserve resumable task state when work moves to another session, harness, directory, or person, or must survive a context reset. Use for pause, pickup, and portable handoff requests. Ordinary progress updates and final delivery summaries stay with the active workflow.

• skill-evolve

  Improve agent skills from session evidence, keeping only edits that beat the current version. Use when a transcript, retro, or feedback shows a skill failed to fire, skipped a rule, or missed a step and the skill should change because of it, or when deciding whether a proposed skill edit actually be

• writing-for-agents

  Write and revise documents that agents consume - skills, SKILL.md, AGENTS.md, CLAUDE.md, and reference files reached by a pointer. Use when creating, editing, reviewing, or splitting a skill, when writing or updating AGENTS.md or CLAUDE.md, when a skill triggers unreliably or gets ignored, when agen

• writing-for-humans

  Write and revise human-facing prose so it is clear, specific, natural, and faithful to the author's intent and genre. Use for emails, chat messages, articles, reports, documentation, announcements, talks, and other prose when the user asks to draft, diagnose, edit, rewrite, make writing less formula

Similar plugins