hyper

Starts or resumes structured development work through the Hyper workflow. Reads the current task state on disk under .hyper/, picks the right phase (explore, plan, implement, verify, docs), and dispatches to the matching hyper-* skill. Use when the user asks to build a feature, fix a non-trivial bug, refactor, investigate something in the codebase, resume a specific task by id (e.g. "resume T3"), or continue in-progress Hyper work. Keywords: hyper, structured work, workflow, task, phase, explore, plan, implement, resume.

Safety Notice

This listing is imported from SkillsMP metadata and should be treated as untrusted until upstream source review is completed.

Copy this and send it to your AI assistant to learn

Install skill "hyper" with this command: npx skills add galatanovidiu/skillsmp-galatanovidiu-galatanovidiu-hyper

No markdown body

This source entry does not include full markdown content beyond metadata.

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Open in GitHub

Related Skills

Related by shared tags or category signals.

Coding

install-hyper

Installs, uninstalls, or checks the status of Hyper skills across every supported agent skill directory on this machine — Claude Code (~/.claude/skills/), Codex (~/.codex/skills/), ~/.agents/skills/, and PI (~/.pi/agent/skills/). Symlinks the skill folders from this repo so local edits take effect immediately. Use when the user asks to install Hyper, set up Hyper for testing, refresh the installed skills, uninstall Hyper, or check whether Hyper is installed. Only meaningful when Claude Code (or another agent) is running inside the hyper7 development repo. Keywords: install, hyper, setup, symlink, refresh, uninstall, status, codex, claude, pi.

Repository SourceNeeds Review

-0galatanovidiu

Coding

hyper-plan-review

Reviews a Hyper feature-scope plan (exploration.md + spec.md + subtask files) before implementation starts. Runs calibrated criteria across completeness, spec-vs-exploration alignment, task decomposition, done-when specificity, out-of-scope and edge cases, and buildability, plus a codebase-verification sub-step that classifies every file / function / pattern reference in the plan as EXISTING vs PROPOSED and verifies only the EXISTING set. Writes a single `plan-review.md` at the task folder root with a `pass | needs-changes | blocked` verdict and a `continue | fix-in-place | rethink` recommendation. Invoked by `hyper-plan` after self-review; not user-invocable. Keywords: hyper, plan review, spec, exploration, verdict, plan-review.md.

Repository SourceNeeds Review

-0galatanovidiu

Security

hyper-verify

Runs the verify phase of a Hyper task. Three lenses in one pass, written to a single checks.md with a pass/needs-changes/blocked verdict. Runs the project's test suite (stabilize), reviews the diff for correctness and security issues (review), and verifies user-facing acceptance criteria against real behavior (QA). Use when a Hyper task is in the 'verify' phase, after implementation is done. Keywords: hyper, verify, tests, review, QA, code review, security review, checks.md.

Repository SourceNeeds Review

-0galatanovidiu

Security

review-hyper-skills

Reviews Hyper skill source for repo-maintainer problems that make the suite harder to execute or maintain: non-operational provenance/history text, stale skill inventories and counts, contract drift across SKILL.md/templates/reference files, non-portable path references, and dead or duplicated instruction surface. Use when the user asks to audit Hyper skills, review the skill suite for maintainer drift, or check whether README.md / AGENTS.md / bundled references still match the shipped skills. Works on current state or a local diff. Keywords: hyper, skill review, maintainer, drift, provenance, inventory, contract, README, AGENTS.

Repository SourceNeeds Review

-0galatanovidiu