Menu
SkillsMP has collected 17 skills from adeonir/agent-skills. Open a skill to review its source and details.
Showing 17 of 17 collected skills.
Creates and evaluates copy for brand, editorial, product, UX, conversion, and informational surfaces. Use when writing, extracting, editing, syncing, critiquing, or auditing copy. Not for visual identity, page layout, or standalone social bios.
Git workflow for conventional commits, pull request creation, and pull request merging. Use when committing, opening or pushing a pull request, or merging one. Not for code review, acceptance-criteria checks, general branch management, or session wrap-up.
Spec-driven feature work with traceable requirements, design, tasks, audit, and validation. Use when planning, designing, implementing, or validating a feature. Not for unknown-bug diagnosis, standalone product or technical documents, PR or commit mechanics,…
Evidence-led debugging for unexpected, silent, or intermittent failures. Use when tracing bugs, adding targeted logs, or verifying fixes. Not for known one-line fixes, runtime review of deployed services, or PM bug triage.
Clear, precise technical prose that preserves facts, requirements, and terms. Use for explanations, procedures, specifications, documentation, incident reports, and brief factual answers. Not for code-only output, raw logs, compliance certification, or…
Code review in quick and deep modes, with confidence-scored findings. Use for diff review, guideline audits, re-reviewing fixes, or applying findings before a pull request. Not for acceptance-criteria verification, visual design review, or commit and branch…
Claude Code rule management at project and user level. Use when defining conventions, scoping, listing, editing, extracting, or deleting rules. Not for procedural workflows, lifecycle hooks, or one-off task instructions.
Prose editing that removes AI-writing patterns while preserving facts, voice, and format. Use when humanizing or checking a draft for machine-written patterns. Not for authorship detection, source-code changes, fact-checking, translation, or product-copy…
Conversation handoff scoped to the current project, for resuming work across sessions. Use when checkpointing, ending a session, loading prior context, or clearing a handoff. Not for handoffs between projects, durable session notes, or repository-wide project…
Obsidian note creation and updates for projects, challenges, achievements, transcriptions, companies, and job applications. Use when documenting work or preserving meeting and lecture notes. Not for session handoffs or repository-wide project context.
End-of-session context persistence to Obsidian. Use when closing a session, saving work, or documenting what was accomplished. Not for mid-session notes, conversation handoffs, or repository-wide project context.
Idea exploration from a blank problem space or stress-testing an existing plan before building. Use when comparing approaches, finding gaps, reconsidering a direction, or weighing a pivot. Not for documenting a finalized direction.
Creates lo-fi wireframes for UI structure and hi-fi mockups for visual directions. Use for landing pages, dashboards, product UI, and app screens. Not for visual identity, copywriting, single-component design, built-UI audits, or code review.
Visual identity development and validation through the official `DESIGN.md` schema and CLI. Use when creating, refreshing, syncing, previewing, exporting, or diffing design tokens. Not for page layout, rendered variants, product copy, feature specs,…
Product and technical document creation through guided discovery, including PRDs, positioning docs, Design Docs, and ADRs. Use when defining requirements, strategy, trade-offs, or architecture decisions. Not for UI design, implementation specs, or meeting…
Roadmap and delivery artifact management in Linear or GitHub. Use when creating, editing, decomposing, moving, or updating roadmaps, epics, stories, bugs, or tasks. Not for implementing a named story, feature status in a spec, project overviews, or quick…
Analyzes a skill's end-to-end reliability — trigger precision plus compound workflow risk (step count, step nature, variance hotspots) — and proposes verifiable fixes it can apply on confirmation. Use when evaluating a skill's hit rate, checking whether a…