/agent-governance â Agent Capability Management
openbooklet.com/s/agent-governance-agent-capability-managementopenbooklet.com/s/agent-governance-agent-capability-management@1.0.0GET /api/v1/skills/agent-governance-agent-capability-managementManage which agents can do what, with approval gates for adding/removing capabilities. From Paperclip's governance framework.
Scaffold REST or GraphQL API endpoints with route handlers, validation, types, tests, and documentation stubs. Auto-detects the project's API framework and follows existing code conventions.
System design and architecture decision-making. Propose multiple architectures, analyze tradeoffs explicitly, discuss with the user, and document the decision. Never present a single option as the only way.
When a task is too large (L or XL), automatically split it into smaller, independently executable sub-tasks.
Systematic 6-phase auto-recovery skill. Detect service failures, diagnose root causes from logs and metrics, categorize the failure type, attempt an appropriate fix, verify recovery, and produce an incident report. Safety-first: never touch production databases or auth systems without human approval
From gstack's test bootstrapping pattern. When a project has no test framework, automatically detect the stack and set up testing infrastructure.
When browser automation hits a wall (CAPTCHA, MFA, OAuth, complex multi-step auth), hand control to the user instead of failing. Based on gstack's browser handoff pattern.
A protective mode that warns and asks for explicit confirmation before any destructive operation. When enabled, the agent creates checkpoints, logs all dangerous actions, and requires human approval before proceeding.
Generate structured changelogs from git history using conventional commit parsing. Categorizes commits by type, groups them into Keep a Changelog sections, includes PR links, and optionally writes to CHANGELOG.md.
Initialize and manage long-running projects with workstreams, recurring operations, and autonomous execution loops. Works for companies, SaaS, open source, agencies, research, or any ongoing effort.
Manage your sales pipeline, score leads, track contacts, and generate sales reports. Detects your CRM platform (Salesforce, HubSpot, Pipedrive) or operates in local mode using markdown files as the data source. All operations work without a CRM platform configured.
Get an independent code review from a different model for critical changes. Catches blind spots that a single model misses. Based on gstack's multi-AI review pattern.
Scans the actual project â plan files, package.json, git history, source tree â and generates (or regenerates) the HTML dashboard and knowledge base with real data. Opens the result in a browser.
Systematic 5-phase data analysis methodology. Discover the data, explore its structure, answer the question, visualize the results, and deliver a report. Every analysis produces re-runnable Python scripts and actionable insights.
Full autonomous deployment from local code to a live production URL. Detects the project type, runs pre-deploy checks, sets up hosting, configures environment variables, deploys, and verifies the live site. Supports Vercel, Railway, Netlify, and Docker.
Inspect Figma designs, export assets, extract design tokens, compare design versions, and manage project design assets. Requires `FIGMA_TOKEN` for Figma integration. Without it, operates on local assets and can generate CSS from screenshots.
Perform systematic error analysis to find the root cause of failures, not just the symptoms.
Evaluate the quality of a skill, agent, or hook. From wshobson/agents PluginEval pattern. Scores across multiple dimensions to identify weak components.
Auto-indexed from fainir/best-agent
Are you the author? Claim this skill to take ownership and manage it.
Related Skills
graceful-error-recovery
Use this skill when a tool call, command, or API request fails. Diagnose the root cause systematically before retrying or changing approach. Do not retry the same failing call without first understanding why it failed.
audience-aware-communication
Use this skill when writing any explanation, documentation, or response that will be read by someone else. Match vocabulary, depth, and format to the audience's expertise level before writing.
Refactoring Expert
Expert in systematic code refactoring, code smell detection, and structural optimization. Use PROACTIVELY when encountering duplicated code, long methods, complex conditionals, or any code quality issues. Detects code smells and applies proven refactoring techniques without changing external behavior.
Research Expert
Specialized research expert for parallel information gathering. Use for focused research tasks with clear objectives and structured output requirements.
clarify-ambiguous-requests
Use this skill when the user's request is ambiguous, under-specified, or could be interpreted in multiple ways. If proceeding with a wrong assumption would waste significant work, always ask exactly one focused clarifying question before doing anything.
structured-step-by-step-reasoning
Use this skill for any problem that involves multiple steps, tradeoffs, or non-trivial logic. Think out loud before answering to improve accuracy and transparency. Apply whenever the answer is not immediately obvious.