Skip to main content
Run any Skill in Manus
with one click
infohata
GitHub creator profile

infohata

Repository-level view of 19 collected skills across 1 GitHub repositories.

skills collected
19
repositories
1
updated
2026-07-07
repository explorer

Repositories and representative skills

compound
computer-occupations-all-other

Route a just-learned lesson to the right destination — project-local solution doc, mind-vault skill/rule/agent/command, or auto-memory. Uses a hybrid narrative-probe + taxonomy-quiz router. Also consumes review-loop output (Cursor Bugbot or GitHub Copilot) as input. Final stage of the mind-vault sprint workflow; the lever that makes each sprint easier than the last.

2026-07-07
deployment
network-and-computer-systems-administrators

Deploy Docker Compose web applications across any project — branch strategy, change-aware scripts, database backup + rollback safety, screen-session remote execution, Let's Encrypt SSL, health checks, and CI/CD wiring.

2026-07-07
shell
network-and-computer-systems-administrators

Base shell-language layer beneath deployment + the devops persona — strict-mode hazards, quoting/input hygiene, trap cleanup + locking, plus live-host ops machinery (DRY-RUN/--apply/--verify contracts, operator gates, SSH fleet sweeps, validator-less config edits, evidence-gated remediation).

2026-07-07
review-loop
software-quality-assurance-analysts-and-testers

Drive a bounded-autonomy review-fix-rerun loop against one or more pluggable review engines (Cursor Bugbot, GitHub Copilot, Claude Code Review, future N-engines) on a PR. Triages findings into Tier 1 / 2 / 3, batches per-cycle fixes into single commits, retriggers engines after each push, tracks each engine through a review-state machine (NOT_TRIGGERED → TRIGGERED → RUNNING → DONE) read from its check-run status, treats an engine as clean only when DONE with zero active findings, and hands back to the user with a structured report. Engine-agnostic core; per-engine specifics live in references/engine-<name>.md per the adapter contract.

2026-07-05
dependabot-triage
software-developers

Triage and batch-merge accumulated Dependabot PRs in multi-requirements-file Python repos (web + lsp + dev + per-workspace) — diff-based duplicate detection across the root vs per-workspace ecosystems, risk-tier batching for git-bisect cleanliness, worktree-isolated verification, live-staging smoke, post-merge forward-sync of remaining branches. TRIGGER when the user says "review dependabot PRs", "merge dependabot batch", "dependabot sweep", "what to do with these dep PRs", "clean up the dep updates", or asks for a roadmap merging multiple `chore(deps)` PRs. Includes the vendored-static variant — synthetic npm-ecosystem manifest tracking vendored browser assets + a re-vendor CI workflow (stuck "unstable" PRs, major-bump map src changes, re-vendor reproduction, consolidation-as-unblock).

2026-06-24
django-frontend
software-developers

Apply Django frontend conventions — HTMX partial responses, Alpine.js state, Bulma components, HTMX modal/formset JS contracts, safe query-string generation, dynamic hx-* attribute handling, and Cotton component primitives — pairing with django backend patterns. Includes hard hazard rules every template edit must respect — multi-line `{# …

2026-06-24
django
software-developers

Apply cross-project Django backend conventions — BaseModel abstractions, DRF viewsets, ORM optimisation (select_related / prefetch_related), multi-tenancy boundaries, generic-FK patterns, permission probes, and translation workflow — before hitting templates.

2026-06-24
work
software-developers

Execute a plan produced by /plan — reads the plan at docs/archive/YYYY-MM-idea-NNN-<slug>/YYYY-MM-DD-<slug>-plan.md, enforces RULE_parallel-worktree-docker and RULE_git-safety, dispatches per the persona dispatch matrix, checks off plan items as commits land. Third stage of the mind-vault sprint workflow.

2026-06-17
Showing top 8 of 19 collected skills in this repository.
Showing 1 of 1 repositories
All repositories loaded