Menu
SkillsMP has collected 15 skills from matheuspoleza/skills. Open a skill to review its source and details.
Showing 15 of 15 collected skills.
Implement a milestone autonomously inside a Conductor worktree without stop-and-ask checkpoints, strictly enforcing scope-first and logging anything out of scope. Use when running parallel Conductor lanes, asked to "build autonomously", "run this in the…
Implement a milestone's tasks one at a time using BDD then TDD, with live progress tracked in three places and a Review Contract filled per task. Use when ready to implement, given a milestone path, or asked to "build the next milestone" or "start…
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism,…
Build a product field guide for an unfamiliar app — one markdown file per feature with pages, flows, screenshots, and the gotchas only a human knows. Use when starting on a new project, joining an existing codebase, or asked to "map the product", "understand…
Build a single progressive PRD doc that captures problem, product requirements, tech design, and milestones — grilling the user via /grill-me at each section to reach shared understanding. Use when starting a feature, scoping a non-trivial change, or asked to…
Validate a completed milestone in two phases — agentic QA (run tests, hit endpoints, screenshot visuals) then human-eyes pass (manual test guide, feedback collection) — and end with a PR-ready description. Use after a milestone is built, or asked to "review",…
Build and refine a personal writing-style profile that /humanizer auto-loads, by sampling real writing (Slack, Linear), interviewing the user, and calibrating with example rewrites. Use when setting up voice matching, when /humanizer output still needs the…
Interview the user one question at a time about a plan, decision, or design until a shared understanding emerges. Use when planning, designing, scoping, picking among options, or asked to "grill me", "interview me", "drill into this", or "pressure-test the…
Reproduce a bug, capture evidence to a cleared log, propose 2-3 fix options for the human to pick, implement, validate by re-running the repro, and add a regression test. Use when given a bug report, a Jam URL, a stack trace, asked to "debug", "fix this bug",…
Install or update the skills toolkit (skills, rules, templates, prompts, CLAUDE.md) in the current project from the canonical GitHub repo. Use when starting a new project, when asked to "install skills", "set up the toolkit", "update skills to latest", or…
Compact the current Claude session into a cold-readable handoff doc so a fresh session can resume with no context loss. Use when context is getting long, before switching tasks, before closing the session, or asked to "handoff", "save context", "wrap this up…
Survey a codebase or product surface in PM-mode and produce a research note with hot picks per dimension, without making decisions or writing code. Use when starting product discovery, exploring an unfamiliar area, asked to "research", "explore", "look around…
Cut a list of N candidates down to the M most-worth-doing using RICE or a simpler heuristic, with the user making the final call. Use when picking what to ship next, prioritizing a backlog, asked to "triage", "prioritize this list", "what should I do first",…
Author a new skill in this toolkit that conforms to the contract — strict frontmatter, 100-line cap, explicit trigger language. Use when adding, rewriting, or auditing any SKILL.md in this toolkit.
Go up one layer of abstraction from the current code or file and map the modules around it plus who calls into them. Use when stuck in details, asked to "zoom out", "show me the bigger picture", "where does this fit", or "what calls this".