garyld1962

@garyld1962 source repo

231 skills
0 followers
12 hours ago last updated

▌
Spec Review Adversarial 2 · garyld1962
Adversarially review PRDs, requirements, user stories, or acceptance criteria using 1–4 lens reviewers (Skeptic, Coherence, Semantic, Devil's Advocate). The Semantic lens checks the deliverable against its sibling ONTOLOGY.md. Returns PASS/CONTESTED/REJECT.

0
installs
▌
Plan Format 2 · garyld1962
Canonical plan document format produced by /execute-prd and consumed by /execute-plan's runtime workflow. Defines frontmatter, task metadata (depends_on, milestone_end), and mechanical acceptance blocks. Not user-invokable.

0
installs
▌
Parallel Optimization 3 · garyld1962
Optimize a draft task graph's dependencies and file ownership for safe optional concurrency. Use before execution when scheduling needs work; do not change requirements or create a second lane/wave plan.

0
installs
▌
Code Review Professional 2 · garyld1962
Seniority-calibrated craft grade (junior/mid/senior/staff) across 7 axes with line-cited reasoning. Use at the PR boundary after domain-review.

0
installs
▌
Modernization Rubric 2 · garyld1962
Internal calibration rubric for /modernize. Encodes project-shape detection, sample-read strategy, per-theme finding patterns, admissible-moves matrix, and cull criteria. Embedded by /modernize. Not user-invocable.

0
installs
▌
Goal 4 · garyld1962 bundle
Turn a rough idea into a clear outcome, problem statement, success measures and scope before requirements work. Use for goal discovery, not an already written PRD or an implementation request whose outcome is clear.

0
installs
▌
Ship 3 · garyld1962 bundle
Unified delivery workflow for checkpoint, commit preparation, push, PR creation, release steps, and fast hotfix mode. Uses explicit approval for mutating remote actions.

0
installs
▌
Vault 4 · garyld1962 bundle
Search, read, create or organize Markdown notes in a configured Obsidian vault, including wiki links and backlinks. Use when the user names their vault or Obsidian notes; do not assume a personal filesystem path or use it for ordinary repository docs.

0
installs
▌
Drawio 4 · garyld1962 bundle
Create or edit editable draw.io diagrams, optionally export PNG/SVG/PDF with embedded diagram data, or produce a diagrams.net URL. Use when draw.io format is requested; use native text diagrams for simple explanations that need no draw.io artifact.

0
installs
▌
Ideate 3 · garyld1962 bundle
Shape a rough idea, document, or folder into clear product, business-analysis, or technical directions before planning. Does not produce an implementation plan.

0
installs
▌
Thesis 3 · garyld1962 bundle
Interrogate a product, architecture, or content idea to find a single-sentence thesis, then audit proposed scope against that thesis.

0
installs
▌
Triage 3 · garyld1962 bundle
Investigate a bug from reproduction through root cause and recommended next step. Produces a structured report and does not write fixes.

0
installs
▌
Grill Me 3 · garyld1962 bundle
Stress-test a plan, design, architecture decision, PRD, or implementation approach by asking one focused challenge question at a time. Use when the user says 'grill me', wants assumptions challenged, or needs decision-tree gaps exposed before planning or coding. Does not implement changes or produce a full adversarial review report.

0
installs
▌
Simplify 5 · garyld1962 bundle
Explain dense progress reports, task or wave summaries, blockers and decision requests in plain language. Use $simplify, 'explain that simply', or before user-facing PRD/plan execution updates. Simplifies explanations, not code.

0
installs
▌
Changelog 3 · garyld1962 bundle
Generate or update changelog content from git history and Conventional Commits. Use for release notes, version summaries, and tag preparation.

0
installs
▌
Configure 4 · garyld1962 bundle
Fill missing project or user configuration required by Savviety workflow skills. Use when a pre-flight check reports placeholders or missing config.

0
installs
▌
Dep Audit 3 · garyld1962 bundle
Audit dependencies for vulnerabilities, outdated packages, unused dependencies, and license risk before release or major changes.

0
installs
▌
Env Check 3 · garyld1962 bundle
Detect shell, OS, repo root, package manager, path, and command-routing constraints before giving commands across local, WSL, remote, or container environments.

0
installs
▌
Modernize 3 · garyld1962 bundle
Audit an older or dormant codebase against current Codex/agent capability and produce a prescriptive within-stack refactor plan. Use for phrases like 'modernize this codebase', 'refresh the code', 'what would this look like today', 'AI-time refresh', or 'modernization audit'. Focuses on structure, boundaries, types, error handling, tests, infra organization, and dead code. Does not recommend framework changes, language switches, public API rewrites, dependency-upgrade campaigns, or broad redesigns.

0
installs
▌
Sync Main 3 · garyld1962 bundle
Safely sync the current branch with main or the default branch. Checks worktree state, fetches, rebases or merges as requested, and handles conflicts carefully.

0
installs
▌
Test Plan 3 · garyld1962 bundle
Create or refresh a TDD-first test plan from requirements. Produces test specifications, priority, analysts, and optional test stubs.

0
installs
▌
Work Item 3 · garyld1962 bundle
Fetch and normalize Azure DevOps or Linear work-item context for planning, triage, hotfix, and PRD workflows.

0
installs
▌
Checkpoint 3 · garyld1962 bundle
Quality gate for changed scope. Discovers package tooling, then runs lint, typecheck/build, tests, and a quick security-oriented diff review before push or PR.

0
installs
▌
K8S Verify 4 · garyld1962 bundle
Post-deploy Kubernetes verification: pods, rollout status, services, endpoints, events, logs, and optional smoke checks after a deployment.

0
installs
▌
Postmortem 3 · garyld1962 bundle
Structured retrospective after a completed plan, delivery run, incident, or failed workflow. Produces causes, lessons, and process changes.

0
installs
▌
Prd Create 4 · garyld1962 bundle
Create a PRD, ONTOLOGY.md and AERS from an idea, goal, thesis or codebase via interview. Modes: greenfield, feature, refresh, rewrite. Not for an existing artifact (use /prd-validate).

0
installs
▌
Bug Session 4 · garyld1962 bundle
Capture several reported bugs, inspect relevant code, and turn them into distinct actionable GitHub issues. Use for a bug intake session; use triage to diagnose one existing bug and execute-plan to implement fixes.

0
installs
▌
Dep Migrate 3 · garyld1962 bundle
Plan major dependency migrations. Analyze breaking changes, repo impact, sequencing, tests, rollback, and risk.

0
installs
▌
Execute Prd 6 · garyld1962 bundle
Turn a PRD, RFC, prompt, story or ticket into an audited, readiness-scored task graph, validate it and implement when requested. Includes lightweight kickoff; use execute-plan for an existing execution plan.

0
installs
▌
Repo Status 3 · garyld1962 bundle
Read-only live repo snapshot: branch, upstream, working tree, stashes, recent commits, unpushed commits, and current user's open GitHub PRs. Use at session start, before delivery, or when repo state is unclear.

0
installs
▌
Design Twice 4 · garyld1962 bundle
Compare at least three contrasting module or API interfaces before committing to architecture. Use for unresolved interface design in feature/refactor work; skip settled designs, small bug fixes, and implementation-only requests.

0
installs
▌
Execute Plan 6 · garyld1962 bundle
Execute or resume a written task graph plan with ownership checks, acceptance proof, milestone reviews, bounded retries and final-head gates. Use for an existing plan; use execute-prd when requirements still need planning.

0
installs
▌
Gh Readiness 4 · garyld1962 bundle
Check GitHub access, target repository and required capabilities before creating issues, PRs, releases or other GitHub changes. Use when access is unknown or changed; avoid repeated probes once this session established the needed capability.

0
installs
▌
Issue Slices 4 · garyld1962 bundle
Break a PRD or parent issue into demonstrable vertical GitHub issues with acceptance and dependency links. Use to create an implementation backlog; use execute-prd for a local execution plan and bug-session for unrelated bug reports.

0
installs
▌
Prd Validate 3 · garyld1962 bundle
Turn a rough story, PRD, BRD, AERS draft, or product idea into an implementation-ready requirements spec by closing ambiguity.

0
installs
▌
Pr · garyld1962
Full PR lifecycle: branch, commit, checkpoint, push, create PR, and optionally squash-merge. Automates the entire pull request workflow with quality gates.

0
installs
▌
Goal · garyld1962
Clarify and validate a development goal before writing a PRD. Use when the user has an idea or intent but hasn't shaped it into requirements yet — phrases like 'I want to build X', 'I'm thinking about adding Y', 'we should improve Z', 'what should we work on next', 'help me think through this idea'. Separates outcomes from solutions before any implementation work begins. When NOT to Use: requirements already written (use /prd-validate); specific bug to fix (use /triage); design decision to explore (use /design-twice).

0
installs
▌
Ship · garyld1962 bundle
Ship completed work through the repo's actual delivery flow: checkpoint, commit, push, PR, and release steps. Reads project-specific delivery commands from config.

0
installs
▌
Vault · garyld1962
Search, create, and manage notes in the Obsidian vault at /data/obsidian. Use when user wants to find, create, link, or organize notes — phrases like 'find my note on X', 'create a note about', 'add this to the vault', 'search my notes', 'open the vault'.

0
installs
▌
Drawio · garyld1962
Generate native .drawio diagram files (flowcharts, ER, sequence, class, architecture diagrams) as draw.io XML, with optional export to PNG/SVG/PDF or a browser URL that opens in app.diagrams.net. No MCP setup required. Triggers on '/drawio', 'create a diagram', 'draw.io', 'flowchart', 'sequence/ER/class diagram'. When NOT to use: for Azure resource-group / cloud-architecture diagrams, use create-diagram instead.

0
installs
▌
Hotfix · garyld1962
Apply an expedited fix for a critical production issue: branch from main, apply a scoped fix, run targeted tests, and fast-track merge.

0
installs
▌
Ideate · garyld1962
Use before superpowers:writing-plans or brainstorming to shape a rough ask, doc, or folder into a direction. Three modes: idea (general), ba (business-analysis), tech (technical options).

0
installs
▌
Thesis · garyld1962
Interrogate to discover the single-sentence product or architectural thesis, then audit all planned features and decisions against it.

0
installs
▌
Triage · garyld1962
Investigate a bug from reproduction through root cause analysis and produce a structured triage report (classification, risk, recommended next step) — the deliverable is the report, not a fix. Preferred over superpowers:systematic-debugging when the goal is a handoff document for /hotfix, /execute-prd, or a human decision rather than an in-session fix.

0
installs
▌
Kickoff · garyld1962
Use for operator-supervised feature work from a PRD/story/AERS: readiness → plan → implement → review, with the operator at the keyboard. Does not produce audit-grade governed artifacts; for an unattended run use /execute-prd.

0
installs
▌
Grill Me · garyld1962
Use when user says 'grill me', wants to stress-test a plan, or validate assumptions. Walks the decision tree one question at a time, exploring the codebase when it can.

0
installs
▌
Simplify · garyld1962 bundle
Explain dense progress reports, task or wave summaries, blockers and decision requests in plain language. Use /simplify, 'explain that simply', or before user-facing PRD/plan execution updates. Simplifies explanations, not code.

0
installs
▌
Changelog · garyld1962
Use to generate a release from Conventional Commits. Groups commits since the last tag, auto-bumps the version, updates CHANGELOG.md, tags, and releases.

0
installs
▌
Configure · garyld1962 bundle
Use when a skill's pre-flight says config is missing, or with no arg to see what needs configuring. Interviews the user and writes the config file.

0
installs
▌
Dep Audit · garyld1962
Audit project dependencies: check for vulnerabilities, outdated packages, unused deps, and license compliance. Use periodically or before releases.

0
installs
▌
Env Check · garyld1962 bundle
Detect the current shell environment and choose safe command routing. Use when working across different shells, OSes, or remote hosts. Reads user-specific shell config from ~/.claude/env.config.md.

0
installs
▌
Modernize · garyld1962
Audit a codebase against current AI toolchain capability and produce a prescriptive refactor plan. Use when revisiting an older project (months of dormancy or older-AI-era patterns) to identify structural improvements — abstraction, separation of concerns, types, error handling, tests, infra organization — that newer models can now execute safely. Default --handoff invokes /execute-prd --type=refactor on the resulting plan. Trigger phrases: 'modernize this codebase', 'refresh the code', 'what would this look like today', 'AI-time refresh', 'modernization audit'. Strictly within the current platform/stack — does not propose framework changes, language switches, or public-API rewrites.

0
installs
▌
Sync Main · garyld1962
Sync current branch with main: fetch, rebase, resolve conflicts. Use when your branch is behind main or before creating a PR.

0
installs
▌
Test Plan · garyld1962 bundle
Use before implementing a feature to generate it.todo() stubs from requirements (TDD-first). Supports plan, validate, and refresh modes. TypeScript monorepos.

0
installs
▌
Work Item · garyld1962
Retrieve a work item from Azure DevOps or Linear. Extracts title, description, acceptance criteria, status, assignee, and tags. Presents in clean markdown format for use by other skills.

0
installs
▌
Checkpoint · garyld1962
Quality gate: discovers project tooling, runs linter, typecheck/build, and tests for changed packages. Use before pushing or creating PRs.

0
installs
▌
K8S Verify · garyld1962
Post-deploy verification for Kubernetes: checks pod health, service endpoints, recent events, log errors, and rollout status. Use after any K8s deployment to verify it succeeded.

0
installs
▌
Postmortem · garyld1962
Structured retrospective over a completed execute-plan run. Reads the run folder, writes postmortem.md + postmortem.json, and appends to the postmortem index.

0
installs
▌
Prd Create · garyld1962 bundle
Create a PRD, ONTOLOGY.md and AERS from an idea, goal, thesis or codebase via interview. Modes: greenfield, feature, refresh, rewrite. Not for an existing artifact (use /prd-validate).

0
installs
▌
Skill Help · garyld1962
List available skills or show detailed help for a specific skill. Use when the user asks 'what skills are available', 'help with a skill', 'what can you do', 'list skills', or '/skill-help'.

0
installs
▌
Bug Session · garyld1962
Interactive bug-reporting session: user describes problems conversationally, agent explores the codebase for domain context, and files durable GitHub issues. Use when user wants to report bugs, do QA testing, capture defects — phrases like 'let's do a bug session', 'I found some issues', 'QA session', 'help me file these bugs'. When NOT to Use: single known bug to investigate (use /triage); existing issue to fix (use /hotfix or /execute-prd).

0
installs
▌
Dep Migrate · garyld1962
Plan a dependency migration: analyze breaking changes, assess impact on your codebase, produce a step-by-step migration plan. Use when upgrading Node, TypeScript, frameworks, or major dependencies.

0
installs
▌
Execute Prd · garyld1962 bundle
Use when a written requirements source exists (PRD, RFC, prompt.md, spec file, or ADO/Linear ticket) and the user wants it planned and built — phrases like 'build this PRD', 'execute prompt.md', 'turn this RFC into a plan and run it'. Not for vague ideas (use superpowers:brainstorming) or when a validated plan already exists (use /execute-plan).

0
installs
▌
Repo Status · garyld1962
Reports live repo state: branch, working tree, unpushed commits, stashes, and open PRs. Read-only snapshot for orienting at the start of a session or after a long break.

0
installs
▌
Skill Audit · garyld1962
Use periodically or when setting up a new project to audit Claude Code skills/plugins/agents, research marketplaces, gap-analyze, and implement recommendations.

0
installs
▌
Design Twice · garyld1962
Explore multiple radically different API/module designs using parallel agents before committing. Use when designing a new interface, module API, or public surface — phrases like 'design it twice', 'explore the design space', 'what are my options for this interface', 'compare API shapes', 'how should this module look'. When NOT to Use: implementation details inside an existing interface (use superpowers:writing-plans); evaluating existing code (use /code-review).

0
installs
▌
Execute Plan · garyld1962 bundle
Use when the user has a written implementation plan file (typically produced by /execute-prd, in the plan-format contract) and wants it executed — phrases like 'execute the plan', 'run docs/plans/X.md', 'resume the plan'. Not for writing plans (use /execute-prd) or trivial single-file edits.

0
installs
▌
Gh Readiness · garyld1962
Verify GitHub CLI (gh) is installed, authenticated, and able to reach github.com before running skills that create PRs, issues, or releases. Use before /pr, /ship, /hotfix, /issue-slices, /bug-session, or /changelog when gh status is unknown.

0
installs
▌
Issue Slices · garyld1962
Break a PRD into independently-grabbable GitHub issues as vertical tracer-bullet slices. Use when user wants to convert a PRD to tickets, create implementation issues from a PRD — phrases like 'break this PRD into issues', 'create tickets from the PRD', 'slice the PRD into work items'. When NOT to Use: want the PRD executed end-to-end automatically (use /execute-prd); rough idea not yet a PRD (use /goal → /prd-create first); want a plan doc not issues (use /execute-prd step 1).

0
installs
▌
Prd Validate · garyld1962
Turn an existing story, BRD, PRD, or AERS draft into an implementation-ready AERS. Interviews the author, closes structural and semantic ambiguity against the AERS and ontology rubrics, generates missing sections. Use before planning, /kickoff, or /execute-prd. When NOT to Use: vague intent without a problem statement yet (use /goal first to validate the outcome before writing requirements); no artifact at all (use /prd-create, which owns the blank start and writes the PRD folder).

0
installs
▌
Process Tune · garyld1962
Read accumulated postmortems, group taxonomy-tagged recommendations, and propose edits to skills, rubrics, closed decisions, or plan templates.

0
installs
▌
Domain Review · garyld1962 bundle
Domain-based PR review controller (formerly code-review). Preferred over the built-in /code-review when you need the 11-domain controller/worker review with per-domain findings; use the built-in for a fast single-pass diff review or the ultra cloud review. Supports two profiles: 'breakpoint' (light mid-flow review covering security, correctness, and tests only) and 'full' (comprehensive PR-boundary review covering all 11 domains). Conditional domains fire only when triggers match: data-integrity fires when the diff touches persistence (migrations, schemas, SQL, repositories, ORM models); api-contract fires when the diff touches a public surface (API routes, controllers, handlers, .proto files, OpenAPI/Swagger specs, library surface, message schema, CLI, or SDK). Do NOT use for trivial changes (typo fixes, mechanical refactors, dependency bumps with no logic changes). Do NOT use for reviewing a GitHub PR by number where a standard pass suffices — the built-in /review handles that. Do NOT use when you want prof

0
installs
▌
Feature Sweep · garyld1962
Audit installed skills against the latest Claude Code and API releases, then propose and optionally apply surgical integrations. Use when you want to capitalize on a new model release or Claude Code update — phrases like 'what new features can improve our skills', 'sweep for new integrations', 'update skills for the new model', 'what Claude features are we not using'. When NOT to Use: improving skill quality or fixing bugs in a single skill, or adding a new skill from scratch (use superpowers:writing-skills).

0
installs
▌
Validate Plan · garyld1962 bundle
Lightweight readiness gate for a plan file: checks structure, task discreteness, acceptance criteria, milestones, and forbidden placeholders.

0
installs
▌
Audit Existing · garyld1962
Audit a repository before planning or extending it. Produces an implemented/missing/duplicated/broken checklist without editing files.

0
installs
▌
Prd Acceptance · garyld1962
Validate implementation against PRD acceptance criteria. Reads a PRD, extracts checkboxes, verifies each with evidence, produces a pass/fail scorecard.

0
installs
▌
Refactor Brief · garyld1962
Plan a refactor through structured interview, then file it as a GitHub issue RFC with a tiny-commit sequence and decision record. Use when user wants to plan a refactor before implementing — phrases like 'plan a refactor', 'create a refactor issue', 'refactor RFC', 'break this refactor into safe steps'. When NOT to Use: refactor already planned and ready to execute (use /execute-plan); quick code cleanup (make focused edits directly); feature work disguised as a refactor (use /prd-validate first).

0
installs
▌
Review Gauntlet · garyld1962
Use when a code review's conclusions need scrutiny. Reviews THE REVIEW via 3 lenses (Skeptic, Architect, Pragmatist). Returns SOLID / MIXED / UNRELIABLE.

0
installs
▌
Code Investigate · garyld1962 bundle
Search one or more repos for a code pattern or behavior and produce a versioned Markdown investigation report. Supports literal, regex, and semantic (behavioral) search across multi-repo scope.

0
installs
▌
What Is It About · garyld1962
Interrogate to discover the single central thesis of a planned YouTube video, then produce an outline where every segment serves that thesis.

0
installs
▌
New Skill · garyld1962
Scaffold a new skill with correct structure and frontmatter for both claude/ and copilot-native/ platforms.

0
installs
▌
New Domain · garyld1962
Scaffold a new domain-review domain (concept, dialect, or platform) with correct frontmatter, and update the relevant profiles.

0
installs
▌
Port Skill · garyld1962
Port a skill between claude/ and copilot-native/ formats, applying platform conventions and stripping platform-specific bake-in.

0
installs
▌
Review Adversarial · garyld1962 bundle
Cross-model adversarial code review via Codex/Gemini. Use for high-stakes diffs (auth, payments, migrations) or diffs over 200 lines after domain-review passes.

0
installs
▌
Ubiquitous Language · garyld1962 bundle
Use when you need a domain glossary. Derives UBIQUITOUS_LANGUAGE.md from the PRD's ONTOLOGY.md; falls back to extracting terms from conversation when no ontology exists.

0
installs
▌
Ba Ideation · garyld1962
Facilitate business analysis ideation from a rough idea, a single document, or a folder of documents by extracting context, surfacing gaps, comparing options, and producing workshop-ready outputs for both business and technical audiences.

0
installs
▌
API Patterns · garyld1962
Backend and service review rubric for shared types, validation, auth, logging, and operational correctness.

0
installs
▌
Test Quality · garyld1962
Test review rubric for behavior-focused coverage, async correctness, isolation, and meaningful test naming.

0
installs
▌
Disposition · garyld1962
Rules for dispositioning domain-review and adversarial-review findings in the CodeGen flow. Not user-invokable — referenced by execute-plan. Defines status vocabulary, evidence standard, and blocking rules.

0
installs
▌
Plan Format · garyld1962
Canonical plan document format produced by /execute-prd and consumed by /execute-plan's runtime workflow. Defines frontmatter, task metadata (depends_on, milestone_end), and mechanical acceptance blocks. Not user-invokable.

0
installs
▌
Parallel Optimization · garyld1962
Analyze a PRD or plan and produce a parallel-agent execution map with dependency barriers, write scopes, and task ownership for LLM code generation. TRIGGER on: 'parallelize the plan', 'parallel execution map', 'concurrency shape', 'optimize task ownership', 'parallel-safe lanes', 'split this plan into waves', 'after I draft the plan run parallel-optimization', 'add a Parallel Execution section'. Auto-invoked by /execute-prd step 6 — humans rarely need to call this directly except when reshaping a sequential plan into parallel before re-running /execute-plan.

0
installs
▌
Test Writer · garyld1962
Test file generator — converts TestSpecification objects into valid Vitest .test.ts files with it.todo() stubs.

0
installs
▌
Prd Readiness · garyld1962
Interactive checklist and workflow for turning a story, BRD, AERS draft, or rough idea into an implementation-ready artifact for GitHub Copilot workflows.

0
installs
▌
Repo Delivery · garyld1962
Delivery and quality-gate playbook for executing plans, running checkpoints, shipping changes, and handling hotfixes in a repo-specific way.

0
installs
▌
Review Engine · garyld1962 bundle
Shared domain-based review controller for copilot-native. Powers domain-review and professional-review with profile-based domain selection, overlays, and merged findings.

0
installs
▌
Tech Ideation · garyld1962
Explore technical solution directions from a rough idea, a single document, or a folder of documents by clarifying constraints, systems impact, architectural options, data and integration implications, and recommended next validation steps without turning the work into implementation planning.

0
installs
▌
Test Planning · garyld1962 bundle
TDD-first planning rubric for generating test specifications and validating test readiness before implementation.

0
installs
▌
Ado Work Items · garyld1962
Retrieval and normalization workflow for Azure DevOps work items used as planning or implementation inputs.

0
installs
▌
Validate Skills · garyld1962
Lint and validate all skill files in this repo: check frontmatter, cross-references, naming conventions, and structural integrity across both claude/ and copilot-native/ platforms.

0
installs
▌
Diff Manifest · garyld1962
Canonical schema for the `diff_manifest` object passed by `/execute-plan` to `/domain-review` and `/code-review-professional`. Defines clusters, language tagging, and `touches` flags so the producer and all consumers agree on shape. Not user-invokable.

0
installs

231 published skills · page 2 of 3