Loading...
Loading...
Found 11,572 Skills
Monitors TrueFoundry deployment rollouts after deploy/apply. Polls status, checks pod health and readiness, fetches logs on failure, and reports a final summary. Use after deploying or applying a manifest to track rollout progress.
CEO/Founder-mode plan review. Rethink the problem, find the 10-star product, challenge premises, expand scope when it creates a better product. Four modes: SCOPE EXPANSION (dream big), SELECTIVE EXPANSION (hold scope + cherry-pick), HOLD SCOPE (maximum rigor), SCOPE REDUCTION (strip to essentials). Adapted from gstack/plan-ceo-review (Garry Tan, MIT license).
Explore requirements and approaches through collaborative dialogue before writing a right-sized requirements document and planning implementation. Use for feature ideas, problem framing, when the user says 'let's brainstorm', or when they want to think through options before deciding what to build. Also use when a user describes a vague or ambitious feature request, asks 'what should we build', 'help me think through X', presents a problem with multiple valid solutions, or seems unsure about scope or direction — even if they don't explicitly ask to brainstorm.
Draft or update architecture documents under `easysdd/architecture/` — describe what a subsystem/module looks like currently, how it is divided, and how external interfaces operate, to provide pre-positioning input for subsequent feature-design. Information sources include code + user materials (oral accounts, scattered documents, compound deposits, existing decisions), and the output can be reverse-validated by anchoring to specific `file:line`. Two modes: new (draft a new architecture document from scratch), update (refresh an existing document based on the latest code status and new user materials). Single-target rule — only modify one document at a time. Trigger scenarios: user says "fill in an architecture doc", "draft an architecture document", "update the architecture directory", "write down the structure of this module", or when it is found that "something that should be in the architecture is missing" during the feature-design / feature-acceptance phase.
Shows a structured progress dashboard for an album with percentage complete per phase, blocking items, and status breakdown. Use for a quick visual overview of album progress.
Audit experiment integrity before claiming results. Uses cross-model review (GPT-5.4) to check for fake ground truth, score normalization fraud, phantom results, and insufficient scope. Use when user says "审计实验", "check experiment integrity", "audit results", "实验诚实度", or after experiments complete before writing claims.
Read-only Q&A mode — answers questions about the codebase, architecture, or any topic without modifying files. Use for research and exploration before making changes.
LIME Go integration. Manage Organizations. Use when the user wants to interact with LIME Go data.
Cloud Convert integration. Manage Deals, Persons, Organizations, Leads, Projects, Pipelines and more. Use when the user wants to interact with Cloud Convert data.
Orchestrate multi-agent collaborative document synthesis through 6 phases - Divergence, Synthesis, Commentary, Consolidation, Reality Check, Final Merge. Produces authoritative founding documents from complex multi-perspective inputs. Use for constitutional documents, architecture decisions, organizational charters, or any document requiring rigorous multi-perspective synthesis. Activates on "synthesize document", "multi-agent authorship", "collaborative synthesis", "founding document", "architecture document", "recursive synthesis", "constitutional document", "multi-perspective document". NOT for simple document writing, single-author tasks, quick summaries, or documents that don't require adversarial review.
Execute implementation phase-by-phase following tasks.md
Unified review skill — auto-detects plan or code, assembles the right panel, runs a bounded review-fix loop with severity gating. Use when a plan or implementation needs review.