biaoo
- 19 skills
- 0 followers
- 9 hours ago last updated
- ▌ Tiangong Wiki Skill · biaoo bundleUse when you need to retrieve historically accumulated knowledge, methods, or behavioral patterns before answering or acting; when a conversation or workflow produces durable insights worth preserving for future reuse; or when existing wiki content is outdated or incorrect. On Windows native shells or Codex automation, invoke the CLI as tiangong-wiki.cmd.
- ▌ Harness Check Designer · biaoo bundleUse when designing or implementing Agent Harness CLI checks, Stop hooks, workflow-controller specs, or project AGENTS.md instructions that turn ambiguous agentic task criteria into deterministic checks, workflow graphs, state transitions, and Codex continuation loops.
- ▌
- ▌ Docpact · biaoo bundleUse `docpact` as the direct workflow entrypoint for agentic documentation governance. Use when an agent needs to decide what to read before coding, what docs should have been reviewed or updated after coding, how to drill into one lint finding, how to record completed review evidence, or how to check whether governed documents have gone stale.
- ▌ Docpact Governance · biaoo bundleRoute governance-maintainer work to the right internal docpact workflow reference without redefining CLI semantics. Use when the task is about onboarding a repository, designing or auditing rules, backfilling coverage, maintaining routing aliases, integrating CI, or remediating stale governed docs as governance maintenance rather than as a normal coding-task workflow.
- ▌ Word Meaning Lens · biaoo bundleUse whenever the user is learning English or asks about an English word, phrase, meaning, or usage.
- ▌ Living Documentation · biaoo bundleUse when writing or revising living project documentation or agent guidance, especially before adding warnings, correction notes, resolved incidents, superseded approaches, or other historical context, or when such residue has already accumulated. Keep active documentation focused on what is valid now: remove obsolete residue, rewrite lasting lessons as current rules, and move only history with ongoing value to a separate path read when needed.
- ▌ Externalize Thinking · biaoo bundleUse when the user wants to externalize a fuzzy intuition, unnamed judgment, unease about an AI response, or meta-cognitive question into candidate language, a cognitive map, validation probe, grounded principle, prompt, or reusable framework. Trigger when something feels missing or too smooth, the user cannot explain why a framing feels wrong, wants to analyze their thinking or AI collaboration, is overloaded by abstraction, needs to distinguish levels from dimensions, roles, states, or operations, or wants an abstract principle to change concrete action. Do not use for ordinary brainstorming, summarization, domain explanation, or decisions with explicit criteria and output.
- ▌ Personal Essay Writing · biaoo bundleUse when drafting, rewriting, editing, or evaluating Chinese-language essays and long-form intellectual content in the user's personal voice, especially writing that needs precise concepts, faithful problem scale, variable explanatory resolution, strong claims, deliberate logical space, and an intellectually open ending.
- ▌ Agent Skill Design · biaoo bundleUse when creating, extracting, naming, rewriting, diagnosing, splitting, or polishing an agent skill, especially when aligning metadata, SKILL.md, references, scripts, assets, CLI output, and soft-boundary judgment around a clear behavior-changing principle.
- ▌ Mechanism Guided Analysis · biaoo bundleUse when a problem's visible symptoms, repeated local fixes, or apparently adequate solution may conceal a different generating mechanism; helps Codex notice weak signals, question hidden assumptions and relationships, form plausible competing mechanisms, and derive better designs or discriminating validations. Do not use when the cause is already established, the task is straightforward execution, or the user only needs a direct factual answer.
- ▌ Design Intent Translator · biaoo bundleUse when a user wants to design or revise a frontend or UI but cannot express the desired look, feel, layout, hierarchy, interaction, or visual direction in professional design language, including vague reactions, reference images, aesthetic preferences, and requests for a UI brief.
- ▌ Adaptive Formalization · biaoo bundleUse when designing or changing AI/Agent-native product entities, schemas, database models, JSON schemas, DTOs, events, workspace artifacts, memories, profiles, plans, evaluations, or agent outputs; guides Codex to choose the right degree of formalization and freedom instead of defaulting to either rigid schema or unbounded text.
- ▌ AI Friendly CLI Design · biaoo bundleUse when designing or changing public CLI command behavior, help text, output shape, pagination, JSON modes, file-output behavior, error messages, or Agent-facing next-action guidance; guides Codex to make CLI commands useful as both execution tools and context delivery tools.
- ▌ Calibrated Assertiveness · biaoo bundleUse when a response, document, implementation, or test may dilute a clear user objective or best-supported direction through defensive caveats, excessive disclaimers, imagined edge cases, protective alternatives, one-sided risk weighting, conservative scope reduction, or success criteria that prove only the absence of failure. Preserve the intended outcome, detect when defensibility is replacing evidence or user value as the optimization target, and let only constraints or uncertainties that materially change the decision alter the result.
- ▌ Report Biaoo Skill Feedback · biaoo bundleUse when direct use of a skill from Biaoo/skills reveals something that may help the project improve that skill, or when a fresh independent session receives a sanitized handoff to prepare or submit such feedback. Preserve the active task, report the observation faithfully without deciding how it should be absorbed, isolate feedback preparation from the originating work, and complete a narrowly scoped GitHub submission whenever verified authority and access are available.
- ▌ Outcome First Implementation · biaoo bundleUse when choosing or designing an implementation path and the agent may trade away requested quality, fidelity, capability, or completeness to reduce implementation effort, code volume, technical unfamiliarity, or default to KISS or MVP. Encodes the user's preference to give the agent's own execution effort little weight unless it creates a concrete user-relevant consequence or violates an explicit budget. Do not use when the user explicitly prioritizes speed, minimum change, or lowest cost.
- ▌ Context Efficiency Evaluation · biaoo bundleUse when reviewing recorded agent runs for avoidable context consumption, comparing quality-qualified matched traces, designing a context-efficiency experiment, or validating the evaluator skill itself. Applies to broad or repeated retrieval, oversized tool results, premature reference loading, weak continuation, hidden cost transfer, and unsupported efficiency claims; do not use for generic context-window explanations, prompt shortening without run evidence, or directly implementing an optimization.
- ▌ Design Agentic Content Generation · biaoo bundleUse when designing or materially reviewing an Agentic content-generation or content-transformation project, especially when its purpose, routes, artifacts, evidence, authority, evaluation, feedback, human intervention, recovery, or adoption boundaries remain unsettled; applies an inquiry-led method and stops before implementation or production authorization.