Goal: Install a strict, stack-appropriate quality sensor layer—linter, formatter, type checker, static/dependency/architecture analysis, pre-commit, and CI—so every code change is checked locally and in CI with zero divergence before reaching main.
★not rated 12▲
+1
changed 3d agoASkillSpector: warn37 tokens
originalMIT
Goal: Adversarial decision support for costly wrong choices. Five advisors analyze independently, five fresh reviewers critique anonymously, chairman produces final verdict + report artifacts.
Goal: Analyze a market landscape and deliver an evidence-backed market-analysis artifact—competitors, TAM/SAM/SOM, trends, SWOT, and customer segments—that downstream skills can consume as evidence.
Goal: Ensure every shipped performance fix removes a measured or static-risk-labeled bottleneck across data access, compute, runtime/GC, network, client delivery, and concurrency/resilience; calibrate every number against a known anchor, preserve behavior/authorization/semantics, prove before/after evidence, pass…
★not rated 12▲
+1
changed 3d agoASkillSpector: warn35 tokens
originalMIT
Goal: Produce a concise, evidence-backed implementation plan that fixes direction and proof while leaving code-level discovery and mechanics to the executing agent.
★not rated 12▲
+1
changed 3d agoC52 tokens
originalMIT
Goal: Produce a defensible ranked ordering of 3+ planned work items using RICE, MoSCoW, or Value-Effort frameworks so the team works highest-value items first — every rank backed by a score and tech-agnostic rationale (value/effort/risk/impact).
Goal: Ensure service/API changes are production-ready across observability, reliability, data integrity, and database performance: score each dimension with evidence and expose operational gaps.
★not rated 12▲
+1
changed 3d agoASkillSpector: warn34 tokens
originalMIT
Goal: Keep the configured project-config file (default docs/project-config.json) valid and accurate while adding only optional project details supported by evidence.
Goal: Initialize or re-evaluate portable project context through one idempotent route, requiring a valid project identity while configuring only capabilities supported by the project and task.
★not rated 12▲
+1
changed 3d agoASkillSpector: warn55 tokens
originalMIT
Goal: Give a project a registry of named protocol overlays — extra project rules layered onto framework skills — with create / read / update / delete over that registry, so a skill picks up this project's conventions on every run without the portable framework being edited.
★not rated 12▲
+1
changed 3d agoASkillSpector: warn42 tokens
originalMIT
Goal: Improve readable, actionable instructions with preserved meaning. Agent guides use the shared content-value branch; other targets use two-phase optimization — (1) Caveman Compression strips stop words + grammatical scaffolding while preserving semantic meaning; (2) Prompt Enhancement applies AI attention…
Goal: Generate a professional release document from git history at any scope — tag-to-tag, branch-to-branch, or a time range ("last 30 days") — with automated categorization, thematic AI analysis, service detection, and validation, plus a rich standalone HTML release presentation written FOR REAL USERS — user-visible…
Goal: Generate a copy-ready architecture foundation that follows the project's chosen paradigm—applicable abstractions, infrastructure, examples, and quality gates—before feature implementation.
Goal: Detect structural rot — dead code, count-drift, orphan files, stale configs, dead feature flags and broken cross-references — in AI-assisted codebases through docs/project-config.json, then report evidence-backed maintenance actions.
Goal: Scan one selected built-in or explicitly generic custom reference doc and deliver a surgical, evidence-backed update that preserves action-changing rules, exceptions and verified discovery without report bulk.
★not rated 12▲
+1
changed 3d agoA38 tokens
originalMIT
Goal: Build configurable local-development seeders that exercise happy paths through public application commands, produce realistic QC/performance data, and remain idempotent and restart-safe.
★not rated 12▲
+1
changed 3d agoASkillSpector: warn41 tokens
originalMIT
Goal: Author, extend, validate, and package Claude Code skills with proper structure, progressive disclosure, SYNC protocol compliance, and AI attention anchoring.
★not rated 12▲
+1
changed 3d agoASkillSpector: warn29 tokens
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: