sickn33/agentic-awesome-skills v16.1.0

on GitHub

[16.1.0] - 2026-08-25 - "Specification-First Delivery and Mistake-Proofing"

Added specification-first delivery and software mistake-proofing workflows,
aligned durable project-state lifecycle semantics, refreshed Lore's complete
operating surface, and hardened the protected skill-review path. The
published catalog contains 2,028 skills.

This release helps Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and
related AI coding assistants freeze requirements before implementation, design
controls that prevent predictable mistakes, preserve consistent project-state
transitions, and query durable repository knowledge without weakening approval,
provenance, or path-safety boundaries.

Start here:

• Install: npx agentic-awesome-skills
• spec-driven-loop for a specification-first
  workflow with frozen artifacts, non-overlapping agent ownership, and an
  independent delivery judgment.
• poka-yoke for replacing reminders with controls,
  warnings, and bounded detection that make software mistakes impossible or
  immediately visible.
• Choose your tool
• Bundles

Added

• Added spec-driven-loop with PRD, technical
  design, acceptance-criteria, ownership, and completion artifacts; explicit
  approval before implementation; bounded rework; and independent lead-agent
  judgment backed by diffs, tests, and evidence
  (#1242).
• Added poka-yoke for identifying software error traps
  and selecting the strongest practical device on a control, warning,
  detection, or instruction ladder
  (#1240).

Changed

• Aligned project-state-governor
  workstream completion with COMPLETED and retained CANCELLED in the
  canonical milestone lifecycle vocabulary
  (#1241).
• Synchronized lore to its reviewed upstream layout, moved
  workflow guidance into the supported reference tree, refreshed its scripts
  and compatibility documentation, and preserved the repository's stricter
  mirror-target containment rules
  (#1244).
• Upgraded the catalog web app from @supabase/supabase-js 2.111.0 to 2.112.0,
  including upstream authentication, PostgREST, storage, retry, and opt-in
  tracing fixes (#1244).
• Bounded the external semantic skill-review attempt to ten minutes and routed
  timeouts to the truthful manual-review-required path instead of allowing an
  indefinitely running review job
  (#1244).
• Regenerated the canonical catalog, offline AAS Core data, tracked web assets,
  marketplaces, editorial bundles, compatibility reports, and Codex/Claude
  plugin distributions for 2,028 skills.

Fixed

• Fixed Lore full-history queries so the absence of a since value no longer
  injects Git's epoch cutoff and silently omits existing commits.
• Kept multi-entry successor-history results bound to each entry's own code
  path and time boundary while retaining fail-closed path validation.

Security

• Kept spec-driven-loop implementation behind explicit specification
  approval, separated agent ownership, and evidence-based completion instead
  of treating generated artifacts or self-reported status as proof.
• Kept poka-yoke read-only and analysis-first: consequential code or process
  changes still require proposal, authorization, and validation, and detection
  is not presented as equivalent to a preventive control.
• Preserved Lore's canonical path-containment hardening, rejected unsafe mirror
  targets, and pinned license provenance to the reviewed upstream commit.
• Made a timed-out or unavailable external semantic review fail into an exact
  head maintainer-review requirement; it is never reported as an automated
  semantic pass.

Who should care

• Teams coordinating multi-agent implementation that need requirements,
  ownership, acceptance evidence, and final judgment to stay independently
  inspectable.
• Maintainers and reviewers who want software error traps converted into
  concrete preventive or self-announcing controls.
• Long-running projects using durable state or Lore histories across sessions,
  repositories, mirrors, and successor entries.
• Catalog web-app users relying on current Supabase authentication, storage,
  PostgREST, retry, and tracing behavior.

Validation

• Passed repository and reference validation, documentation-security checks,
  warning-budget enforcement, the complete 113-group repository test suite,
  web-app tests and production build, npm package dry-run, plugin compatibility,
  bundle checks, and protected canonical synchronization.
• Reviewed the complete tracked trees for both added skills and the full Lore
  refresh for semantics, safety, provenance, declared risk, limitations,
  references, scripts, and exact-head evidence before protected merge.
• Added regression coverage for bounded skill-review execution and retained
  upstream Lore test coverage for history, containment, and mirror behavior.

Limitations

• spec-driven-loop structures planning and evidence; it does not prove domain
  correctness, replace stakeholder approval, or authorize implementation
  outside the approved scope.
• poka-yoke helps select stronger controls, but compatibility and system
  constraints may leave only warning or detection fallbacks; those weaker
  rungs must remain explicit.
• Lore can only query repository and entry history that still exists locally;
  it cannot reconstruct missing commits or validate external systems by itself.
• Supabase remains an independently evolving upstream dependency, so its live
  documentation and service behavior remain authoritative.

Credits

• @Linji-x and the MIT-licensed
  spec-driven-loop source for
  spec-driven-loop in
  PR #1242.
• @rainmanjam for
  poka-yoke in
  PR #1240.
• @Ghost011118 for the project-state
  lifecycle correction in
  PR #1241.
• @TheaDust for the reviewed Lore upstream
  synchronization proposed in
  PR #1237 and
  integrated through
  PR #1244.
• Snyk for the Supabase dependency update proposed in
  PR #1239 and
  integrated through
  PR #1244.