Menu
SkillsMP has collected 75 skills from robert-chiniquy/dotfiles. Open a skill to review its source and details.
Showing 40 of 75 collected skills.
Sweep open issue trackers, TODOs, active branches, and source evidence to find narrowly scoped, independent, verifiable tasks suitable for remote agents or parallel delegation. Use when asked to find pebbles, small delegatable work, fire-and-forget…
Write a scorecard — a dark, skimmable one-screen readout of the current situation in the user's work, rendered as a terminal (TUI) artifact by the `scorecard` binary from a structured markdown file. Use ONLY when the user explicitly asks for a scorecard (or a…
Present comparisons as narrow ASCII bar charts in the terminal. Use when user asks to compare items, metrics, counts, or coverage between things.
Check for feature flag ID number conflicts before adding new flags. Use before adding a new FEATURE_FLAG_ID enum value to a proto file, when reviewing PRs that add feature flags, or when planning work requiring new feature flags.
Ensure developer-facing features include all three DX components: Tools, Documentation, and Agents. Use when planning developer-facing features, designing APIs/CLIs/SDKs, evaluating if a feature is ready to ship, or reviewing developer experience proposals.
Default voice for engineering output. Shapes code review comments, commit messages, design explanations, and documentation style. Always active. Complements CLAUDE.md rules with specific output patterns.
Systematic scan for work-in-progress across repositories. Use at end of day/week, before context switches, when resuming after a break, or before machine migrations. Finds uncommitted changes, unpushed commits, unmerged branches, and non-main branch state.
Safe git-to-PR workflow. Classifies changes, stages by explicit filename, runs final-pass checks, commits with approval, pushes, creates PR via gh. Encodes all git safety rules. Use when ready to ship code as a PR.
Pre-PR quality checklist encoding recurring review feedback. Run before creating a PR to catch common mistakes. Covers: error handling, naming, resource cleanup, test coverage, documentation, commit hygiene, and language-specific gotchas. Use when code is…
Multi-phase workspace cleanup. Stops background agents, inventories uncommitted work, switches to main, prunes stale branches, cleans worktrees, verifies clean state. Safe by default — never destroys work without confirmation. Use for end-of-day cleanup,…
Systematically locate, analyze, and resolve incomplete work markers in a codebase. Use when user asks to find TODOs, show unfinished work, audit incomplete items, or find and fix TODOs. Covers TODO, FIXME, TBD, XXX, HACK, stub, placeholder, and documentation…
Patterns for working with large JSONL files, debug logs, and event streams. Use when processing .jsonl files, agent debug logs, or newline-delimited JSON data. Covers line-by-line processing, sampling, filtering, and field extraction.
Check status of open pull requests: comments, reviews, CI failures, and recent activity. Use when user asks about their PRs, wants to check CI status, review comments, or do a morning PR check. Works with gh CLI and GitHub MCP tools.
Initialize current directory with the global project process framework. Creates DATA_SOURCES.md, LEARNINGS.md, GLOSSARY.md, .Codex/AGENTS.md, .envrc, and Makefile. Usage: /project [topic] where topic describes the project focus (e.g., /project research-ducks).
Systematically identify problems in a design before implementing it. Use after creating an implementation plan, when a design feels overly complex, to validate benefit vs cost, or as a forcing function for double-back. Applies three lenses: unnecessary…
Use progressively revealing questions to build consensus and illustrate why changes are needed. Use when stakeholders are skeptical, requirements seem obvious to you but not others, or you need to validate assumptions before committing to solutions.
Rigorous 11-step methodology for designing new features and systems. Use when starting new feature design, planning major refactoring, designing developer-facing tools or APIs, or any work requiring architectural decisions. Covers research, compare, refine,…
Long-form technical writing voice for blog posts, deep dives, architecture explanations, and conference talks. Use when writing technical articles, blog posts, or any long-form content for external audiences. Distinct from dry-witted-engineering (terse work…
Use when working with Terraform or OpenTofu - creating modules, writing tests (native test framework, Terratest), setting up CI/CD pipelines, reviewing configurations, choosing between testing approaches, debugging state issues, implementing security scanning…
Grok documentation and configuration help. Use when users ask about setup, configuration, MCP servers, authentication, skills, slash commands, keyboard shortcuts, or any Grok feature. Also use proactively when you detect a user is having trouble with setup or…
Explicit protocol for a management agent to verify web workflows after a subagent completes a task, without writing Playwright or browser automation. Trigger only when the user explicitly asks to verify workflows, run a named flow, or mentions agent-verify /…
Enables ultra-granular, line-by-line code analysis to build deep architectural context before vulnerability or bug finding.
Stand up a full c1 dev stack inside a Squire env — process-compose, postgres, envoy, pub-api, pub-auth, be-* services — wired so an external client can drive c1's gRPC surface end to end with TLS + OAuth2 client_credentials. Use when testing a Latchkey or…
Build and iterate on a personal master schedule across travel, parenting, school/camp, festivals, conferences, administrative deadlines, and work travel. Pulls from Google Calendar + web research. Emits a single date-prefixed line per item, chronologically…
Reviewer persona for gestalt inconsistencies — code that works and is documented correctly, yet whose behavior is the odd one out relative to its sibling APIs or the implicit contract the rest of the system follows. Catches CRUD/shape asymmetry,…
Reply to and resolve GitHub PR review threads after pushing fixes. Use after committing changes that address PR feedback — matches threads to commits, posts replies with commit references, and resolves threads. Triggers on: resolve threads, reply to PR…
Reviewer persona for the full lifecycle of cryptographic keys and high-value secrets: generation, storage, distribution, rotation, revocation, and destruction. Trail of Bits' `zeroize-audit` covers the destruction half; this skill covers the other four phases…
Guardrails, protocols, and operating constraints for large-scale, long-running, or parallelized AI coding tasks — migrations, codebase-wide refactors, framework upgrades, and any task touching 50+ files. Prevents scope creep, context drift, silent compounding…
Reviewer persona for OAuth 2.0 / 2.1 and OpenID Connect flow implementations. Catches the well-documented attack classes that still ship: missing PKCE, wildcard redirect URIs, mishandled refresh tokens, scope creep, mixed flows on a single endpoint, leaking…
Always active in any coding context. At every stopping point that is NOT a direct answer to a discrete user question, default to appending a recap: first, a list — with full URLs — of every OPEN PR / ticket / issue that still needs action or has a live status…
Post-run elicitation protocol for subagents. Adapted from the PEACE model (UK College of Policing) and the Cognitive Interview (Fisher & Geiselman) — the evidence-based, non-coercive replacement for the Reid Technique. Use after a subagent returns a poor or…
Mandatory verification protocol after code changes for Go projects. Use after any code modification to ensure quality.
Deep, multi-agent review of a PR or branch diff: fan out one focused subagent per dimension (security, scale, performance, correctness, idiomatic style, plus frontend when the diff warrants), adversarially verify every finding to kill false positives and…
Refine AI-generated illustrations through successive, controlled visual adjustments while preserving approved details and character continuity. Use for iterative image-generation or image-editing sessions involving follow-up directions such as changing…
Run a multi-agent code review on recent changes. Spawns a team of specialized reviewers (bugs, security, perf, tests, usability, etc.), collects findings, triages into fix-now vs defer, and optionally applies fixes. Use when asked to "review code", "review…
Reviewer persona for Rust `unsafe` blocks and FFI (foreign function interface) boundaries. Catches the well-documented soundness violations: aliasing rule breaches, lifetime extension into 'static, raw-pointer arithmetic past bounds, `repr` mismatches with C,…
Tactically assemble a short-term plan of many parallel options, then pursue as much local action as possible in the moment — rebases, protogen, PR pushes, tracker state updates, sqfan fleet dispatch. Not a survey (orient/sitrep) and not a single-threaded…
Reviewer persona for AI-generated code and logs: did the agent embed a real secret in a diff, commit message, log line, error message, comment, README, screenshot, or test fixture? With AI-mediated codebases this is now a distinct attack-surface class —…
Identifies error-prone APIs, dangerous configurations, and footgun designs that enable security mistakes. Use when reviewing API designs, configuration schemas, cryptographic library ergonomics, or evaluating whether code follows 'secure by default' and 'pit…
Length discipline for skill authoring. Use whenever writing a new skill, editing an existing SKILL.md, or reviewing/minimizing a skill collection.