33 tagged fable, measured the same way as everything else here.
Browse within: anthropic-ai 11claude-science-ai 8
Skill Claude CodeCodex
A harness that makes Opus (or any Claude model) behave like Fable — it enforces seeing a task through to the end, with evidence and verification, as procedure. Use when starting a multi-step task (2+ sequential stories), long autonomous work, debugging or root-cause investigation, building render/executable artifacts…
Skill Claude CodeCodex
A session mode that applies a defined approach to communication, tool use, verification, and writing across coding, research, and documentation tasks.
Skill Claude CodeCodex
Use when deciding whether to spawn subagents — explicit rules for when delegation pays off and when direct work is faster. Opus 4.8 under-delegates by default; these rules correct that.
Skill Claude CodeCodex
Use when recording lessons learned in a project, or when a project contains lessons/ or MEMORY.md — file-based memory format and read/write rules that measurably improve long-horizon performance.
Skill Claude CodeCodex
Use when a task spans more than a few steps or files — establishes a checkable definition of done, a verification cadence, and fresh-context verifier subagents before claiming completion.
Skill Claude CodeCodex
One-time setup and health check for fable-baton. Use when the user asks to set up, configure, verify, or troubleshoot fable-baton - sets the default model to "best" (Fable 5 with Opus fallback) in /.claude/settings.json and verifies the plugin is fully installed.
ConnorRX56/presentation-delivery-skills
Skill Claude CodeCodex
Enforce traceability from natural-language intent to machine predicates, final observables, evidence, and owner-readable acceptance. Use when conducting any audit, review, QA pass, parity or compliance check, security assessment, code or architecture review, visual or behavioral comparison, data validation, system…
ConnorRX56/presentation-delivery-skills
Skill Claude CodeCodex
Use for every progress update, status report, problem explanation, ETA, review, acceptance, or completion report to the operator/owner, especially when they ask “到哪了”, “什么问题”, “做了什么”, “结果呢”, “还要多久”, or “说人话”. Translate technical evidence into visible or operational outcomes before details.
ConnorRX56/presentation-delivery-skills
Skill Claude CodeCodex
A Chinese-language design skill for creating polished HTML prototypes, slide decks, animations, and visualizations.
Shoko-official/Claude-Science-System-Prompts
Skill Claude CodeCodex
Generate clinical trial protocols for medical devices or drugs. This skill should be used when users say "Create a clinical trial protocol", "Generate protocol for [device/drug]", "Help me design a clinical study", "Research similar trials for [intervention]", or when developing FDA submission documentation for…
Shoko-official/Claude-Science-System-Prompts
Skill Claude CodeCodex
Conduct rigorous, reproducible multi-step scientific work with literature, databases, local files, Python, R, shell, artifacts, reviewers, and approved compute. Use for evidence synthesis, data or statistical analysis, machine learning, simulation, study design, scientific figures or manuscripts, reproduction audits…
Shoko-official/Claude-Science-System-Prompts
Skill Claude CodeCodex
Performs quality control on single-cell RNA-seq data (.h5ad or .h5 files) using scverse best practices with MAD-based filtering and comprehensive visualizations. Use when users request QC analysis, filtering low-quality cells, assessing data quality, or following scverse/scanpy best practices for single-cell analysis.
Skill Claude CodeCodex
Trigger when users say "explain with a story," "tell me a fable," "give me an analogy," "ELI5," or "help me understand intuitively" about a concept. Uses fables to illuminate abstract concepts — the story never mentions the term, only revealing it at the end.
Skill Claude CodeCodex
A Chinese-language teaching tool that explains abstract ideas through short fables and reveals the formal concept at the end. It is designed for requests such as “explain it with a story” or “give me an analogy.”
Skill Claude CodeCodex
Use when delegating heavy, deep, or boundary-pushing work to the Fable 5 model as a background subagent — deep binary analysis, long multi-step audits, hard multi-hop reasoning, anything where Fable's extra capability is worth it. USE THIS WHENEVER you spawn a subagent with model "fable" (Agent tool model:fable, or…
Skill Claude CodeCodex
Rules distilled from past session friction (errors, edit loops, corrections), analyzed by a stronger model and applied to guide future work. Regenerated from glean/artifacts/ plus an index of trigger-loaded protocols from GLEANPROTOCOLDIRS by sync.sh — load every session via CLAUDE.md.
Skill Claude CodeCodex
Install root role on a session. The user's base session.
Skill Claude CodeCodex
Install verify role on a session. The fast independent check that a claimed artifact is actually done — spawned proactively before any parent reports done, opens a PR, deploys, or publishes.
Skill Claude CodeCodex
Decompose a PROJECTBRIEF.md into vertical, TDD-ready implementation slices. Each slice is independently demoable. Use when user wants to break down a project into slices.
Skill Claude CodeCodex
Fable 5 behaviour for Opus-family models - working doctrine injected at session start, plus deep reference playbooks (planning, debugging, verification, review, orchestration...) loaded per task. Also invocable manually via /fabulous.