workflows-work
Execute work plans efficiently while maintaining quality and finishing features
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-20 00:12
41,964 results
Execute work plans efficiently while maintaining quality and finishing features
Review another agent session's plan or finished work, or a contributor's PR, for gaps, missing cases, unproven claims and contradictions. Fixes a plan still in…
Use after migrating/refactoring features (especially tables/data grids) when reviewing component structure - enforces merging over-split components, colocating…
Conditional code-review persona, selected when the diff is large (>=50 changed lines) or touches high-risk domains like auth, payments, data mutations, or…
Conditional code-review persona, selected when the diff touches API routes, request/response types, serialization, versioning, or exported type signatures.…
Optimize Claude Code permissions by finding safe Bash commands from session history and auto-applying them to settings.json. Can run from any coding agent but…
Reviews CLI source code, plans, or specs for AI agent readiness using a severity-based rubric focused on whether a CLI is merely usable by agents or genuinely…
Conditional code-review persona, selected when the diff touches migration files, schema changes, data transformations, or backfill scripts. Reviews code for…
Conditional code-review persona, selected when the diff touches error handling, retries, circuit breakers, timeouts, health checks, background jobs, or async…
Remove AI tells from prose, code, or tests when asked to unslop or humanize an artifact, or prune low-value tests from a suite; preserve meaning, behavior, and…
Expert in merging branches, resolving Git conflicts, worktree management, PR readiness checks, merge strategies, rollback, and GitHub workflow automation.…
Regenerate the Management API OpenApi.json for Umbraco CMS from a running backend, and optionally regenerate the backoffice hey-api client so its generated…
Build MCP tool collections from discovered API groups. Reads .discover.json and generates tools and collection registrations. Use after running 'npx…
Count MCP tools in an SDK-based project and analyze implementation gaps against .discover.json. Use when the user asks about tool counts, progress, or…
Run a retro on what a project's coding agents keep getting wrong - repeated causes with counts, evidence and checked fixes - with the learn-from-mistakes-axi…
Djangoproject (djangoproject.com) for agents: Search django — through Unbrowse's scoped MCP for djangoproject.com (unofficial), which replays…
Metacpan (metacpan.org) for agents: Search metacpan — through Unbrowse's scoped MCP for metacpan.org (unofficial), which replays metacpan.org's own first-party…
Packagist (packagist.org) for agents: Search packagist — through Unbrowse's scoped MCP for packagist.org (unofficial), which replays packagist.org's own…
Python (python.org) for agents: Search pythondocs — through Unbrowse's scoped MCP for python.org (unofficial), which replays python.org's own first-party API…
Autonomous experiment/evaluate/iterate loop for code, prompts, skills, or workflows. Use when optimizing a measurable metric with repeated keep/discard…
Debug Hermes TUI slash commands: Python, gateway, Ink UI.
Add and validate market-specific frame-feature label forks in ict-engine when raw pre-Bayes labels are wrong even though factor signal quality is strong.
Use when auditing Hermes SKILL.md files for YAML/frontmatter breakage and repairing invalid frontmatter safely at scale.
Throwaway experiments to validate an idea before build.