Productivity
xerg
Audit and reduce AI agent runtime spend in dollars. Use for AI costs, agent spend, token waste, runtime attribution, detector coverage, and FinOps. Works with OpenClaw, Hermes, QM,…
Engineering
tiered-audit
Runs a three-tier codebase audit (git history, targeted scans, full review) with gating
Engineering
architecture-paradigm-cqrs-es
Applies CQRS and Event Sourcing for read/write separation and audit trails
Engineering
shell-review
Audits shell scripts for correctness, portability, and common pitfalls
Testing
quality-playbook
Explore any codebase from scratch and generate six quality artifacts: a quality constitution (QUALITY.md), spec-traced functional tests, a code review protocol with regression test…
Design
impeccable
Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend …
Security
code-audit
Perform a structured audit of a codebase covering security, code quality, performance, dependencies, architecture, and testing hygiene, then produce a prioritized findings report. …
Design
ui-ergonomics
Use when auditing whether a view/screen is correctly built against usability & ergonomic dimensions. Checks a UI against 18 usability dimensions — prompting, grouping by location/f…
Security
solana-auditor
Audit and research Solana smart contracts for security vulnerabilities and exploits. Use this skill whenever the user asks to audit, review, analyze, or security-test any Solana pr…
Productivity
skill-reviewer
Skill 质量审查与规范脚手架。审查 Claude/Cursor Agent Skill 是否符合高质量规范（渐进式加载、description 关键词、工作流 checklist、确认节点、脚本封装、参数系统、references 组织、Pre-Delivery、CLI+Skill 模式、反 Slop），并按 P0–P3 分级输出报告；也能 --temp…
Productivity
grading-claude-agents-md
Grades and improves CLAUDE.md (Claude Code) and AGENTS.md (Codex/OpenCode) configuration files. Use when asked to grade, score, evaluate, audit, review, improve, fix, optimize, or …
Productivity
claude-memory-kit
Persistent memory for Claude Code agents with an agent-audit-ritual architecture. User only talks; the agent captures, audits, proposes promotions, and writes. Memory lives in laye…
Web
seo
Comprehensive SEO analysis for any website or business type. Full site audits, single-page analysis, technical SEO (crawlability, indexability, Core Web Vitals with INP), schema ma…
Security
skill-security-reviewer
Security review and threat analysis for agent skills. Use when reviewing, auditing, or validating skills for security issues including prompt injection, code execution risks, data …
Security
ovhcloud-live-kms-key-destruction-guard
Gate and audit OVHcloud KMS key version destruction requests by enforcing five mandatory checks: confirmed key ID and KMS service URN, named approving identity, usage audit confirm…
Security
forter-agentic-readiness-audit
Audit a website against the Forter Agentic Readiness Guide. Loads the 25 weighted rubrics in `audit/`, probes the target site (and optional source code), scores each guideline Pass…
DevOps
ssh-command-screenshot
Run SSH commands in Windows Terminal and capture per-command screenshot evidence into a new folder. Use early whenever a task involves Linux/Unix system inspection, troubleshooting…
Business
statutory-audit-workflow-base
Tier 1 statutory audit workflow covering the full lifecycle from engagement acceptance through risk assessment, planning, fieldwork, and reporting under ISA and country-specific ov…
Productivity
hermes-usage-hook
Appends the provider's own rate-limit windows under every reply (Codex 5h/weekly, MiniMax). Reads Codex OAuth credentials read-only; optional Codex weekly auto-reset is **off by de…
Security
hipaa-review
Performs a HIPAA Security Rule compliance review across all Administrative, Physical, and Technical Safeguards in 45 CFR Part 164, Subpart C. Auto-invoked for healthcare data secur…
DevOps
playbook-cli-audit
Audit all packmind-* skills for CLI compatibility issues: deprecated commands, invalid options, wrong file formats, missing flags, and version mismatches against the locally instal…
Design
design-review
Web / iOS / Android の UI を multi-axis でスコアリングし、フォント/余白/画像密度/モダン度の「ダサさ」シグナルを機械的に拾って md+html レポート化する design audit skill。general (一般フィードバック) と diff (目標デザインとの差分) の 2 モード × strict/norma…
Security
auditing-skills
Scans AI agent skill directories for dangerous bash patterns, prompt injection, supply chain risks, and SKILL.md structure violations. Use when reviewing, validating, or security-a…
Security
dependa-audit
Supply-chain audit of a Dependabot PR. For every dependency the PR bumps, diff the current vs target version (install hooks, new deps, publisher/provenance, network endpoints, code…
Security
mcp-server-vet
Read-only safety inspection of a third-party MCP server before it is added to a config or trusted. Analyzes declared tools, schemas, scopes, transport, and secret surface, compares…
Security
defi-risk-analysis
Analyze a DeFi protocol's risk profile across smart contract, off-chain, and track-record dimensions. Use when the user wants a risk analysis of a DeFi project, to check protocol s…
Engineering
complete-codebase-review
Use when asked to review, audit, assess, or evaluate an entire codebase holistically — not a PR diff. Covers architecture, security, tech debt, test health, deps, docs, CI, standar…
Automation
goal-evidence-ledger
Maintains append-only evidence ledgers as sidecar files under `.flow/runs/<run-id>/evidence/`, storing structured metadata in `.evidence.yaml` and raw outputs in matching `.txt` fi…
Business
board-pack
Assembles quarterly security or audit-committee packs by reading each producer’s *.board.json against a versioned contract, ordering sections, consolidating decisions for board vot…
Business
fz-personalkosten-und-stundennachweis
Defines eligible personnel costs for the research tax credit: gross wages plus employer contributions, 70-euro hourly flat rate for owner-managers, and 60 percent (70 percent for S…
DevOps
audit-automation-gaps
Scans a repository's automation surface (hooks, MCP servers, skills, subagents, scheduled tasks) against the enforcement hierarchy and returns PASS/REJECT/CONDITIONAL verdicts with…
Security
chialisp-auditor
Expert adversarial security and logic review of ChiaLisp puzzles and spend construction—singletons, DIDs, NFTs, CATs, offers, custom inner puzzles, delegated-puzzle flows, and nove…
Security
sap-audit-evidence-packaging
Packages SAP audit evidence for Segregation of Duties, change management, access, and financial controls. Defines evidence taxonomy, maps controls to artifacts, enforces chain-of-c…
Documentation
audit-derivability
Audit whether a documentation file earns its existence by checking if an agent could re-derive its conclusions from the code, config, metadata, and structure itself. Returns a verd…
Research
ontology-review
Audits ontologies, knowledge graphs, and schemas for structural integrity using a seven-axis review covering orthogonality, granularity, taxonomic hygiene, identity, relationship s…
Productivity
rz-quarterly-review
Triggers on first Sunday of January/April/July/October or explicit quarterly review commands. Runs an 80-100 minute process: pulls metrics, re-scores channels on a 5-criteria frame…
Documentation
ara-report-writer
Create, review, and refine standalone annual reports or audit syntheses styled after institutional oversight bodies. Use for drafting, restructuring, quality assurance, or guidance…
Business
auditar-mis-libros
Audits accounting records for uncategorized entries, reconciliation gaps, overdue accruals, cutoff candidates, draft journals, missing opening balances, and duplicate vendors. Rank…
Documentation
reference-audit
Audit tool that detects missing cross-references between corpus documents and a reference base in both directions, surfacing authoritative sources a document should cite and newly …
Engineering
audit-deep
Composite skill — full project health check across testing, config, hooks, performance, security, MCP, and plugins. Runs audit skills in parallel and reconciles into one severity-r…
Productivity
account-health-check
Audits an account or workspace against established best practices, generating a read-only health report grouped by area with severity, evidence, and fix recommendations. Outputs to…
Web
internal-linking-auditor
Audits a site's internal linking structure by sampling up to 50 URLs, mapping the link graph, identifying pillar and cluster pages, and diagnosing issues such as orphans, broken li…
Productivity
skill-explorer
Manages the skill ecosystem: audits existing skills for duplicates or consolidation opportunities, researches web sources for new capabilities, and installs lightweight modular sub…
Testing
audit-accessibility
Automated WCAG 2.2 accessibility audit that crawls every page, runs axe-core checks, validates keyboard navigation, color contrast, ARIA labels, heading hierarchy, form labels, and…
Engineering
system-audit
System-wide evidence-based audit of orchestrator, docs, rules, memory, subagents, tools, and claimed delivery, followed by immediate fixes and ranked backlog. Triggered by explicit…
DevOps
eks-operation-review
Audits live EKS clusters across ten operational domains—networking, autoscaling, observability, identity, add-ons, workloads, deployments, lifecycle, IaC, and processes—delivering …
Research
research-to-paper-write
End-to-end academic manuscript drafting and revision in Build-From-Materials or Rewrite modes across journals, conferences, reports, reviews, and competitions; plans per-unit ratio…
Documentation
skill-description-audit
Cross-validates an Agent Skill's SKILL.md frontmatter and description against its implementation body, checking compliance, claim accuracy, non-emptiness, trigger words, rename res…
Engineering
deep-assessment
Performs comprehensive whole-project audits on demand, orchestrating layered validation instruments plus specialized checks for gate efficacy, citation sampling, adoptability, and …
Data
amazon-catalog-auditor
Audit Amazon Category Listing Reports (CLRs) for catalog health issues. Use when analyzing CLR files (.xlsx/.xlsm), checking for missing attributes, RUFUS bullet optimization, titl…
Business
ru-financial-statements
Prepares accurate guidance on Russian financial reporting duties for self-employed individuals, ИП, and any ООО or АО they form. Clarifies that ИП and самозанятый have no filing ob…
Automation
schedule-effective-dated-changes
Schedule future-dated changes (plan, tier, price, deactivation) via a pending-changes table holding the payload, effective date, and status. A scheduled job applies due rows transa…
Productivity
utility-pm-critic
Runs adversarial review on a PM artifact via the pm-critic sub-agent. Dispatches natively on Claude Code with the pm-skills plugin; on other clients reads agents/pm-critic.md and e…
Productivity
coaching-models
Generates coaching session preps, cycle plans, or plan audits with explicit goals, evidence-based reality checks, options, owner/date commitments, and feedback checkpoints. Flags g…
Engineering
db-naming
Audit naming conventions — inconsistent table/column casing and pluralization, ambiguous or reserved-word identifiers, untyped/opaque columns, inconsistent FK and boolean naming, a…
Productivity
spiral
Bootstrap and audit the structural-discipline scaffold (GDD tree, coverage ledger, progress log, open questions, followups, playtest gate) that turns a vision into a delivered syst…
Security
audit-ppmplugin
Statically audits a built `.ppmplugin` archive for layout, manifest, bundle integrity, Android DEX/SDK issues, iOS framework structure, and PCF transport contract compliance. Repor…
Business
financial-reporting-workflow-base
Foundation workflow for US GAAP and IFRS financial reporting. Supplies the universal runbook, two-layer output contract, journal-entry format, dual-standard convention, AUDIT FLASH…
Testing
grounding-conformance
Audits frozen acceptance-contract.yaml files against the current system-state snapshot, classifying each as GROUNDED, UNGROUNDED, or STALE using structural and consistency validato…
Business
pm-progress-auditor
Audit a status update, exec review, board email, all-hands talking point, or dashboard callout for credibility leaks before sending. Flags overstated claims, cherry-picked windows,…
Showing the top 60 of 3,592. See the full list →