steno-mode
Shorthand-first response compression that cuts ~40% of response tokens while preserving technical precision and exact literals. Use when the user says "steno mode", "shorthand mode", "compressed responses", "token reduction", "brief structured output", or invokes /steno. Supports four compression levels: lite, brief, court, machine. Do not trigger for requests needing polished prose such as onboarding/tutorial content, stakeholder or customer-facing copy, or teaching-focused explanations.
- License 许可
- MIT
- 最近更新
- 2026-11-13
- Stars
- ★ 4.1w
- Forks
- 5.3k
01 前言 Front Matter
- name
- steno-mode
- license
- MIT
- description
- Shorthand-first response compression that cuts ~40% of response tokens while preserving technical precision and exact literals. Use when the user says "steno mode", "shorthand mode", "compressed responses", "token reduction", "brief structured output", or invokes /steno. Supports four compression levels: lite, brief, court, machine. Do not trigger for requests needing polished prose such as onboarding/tutorial content, stakeholder or customer-facing copy, or teaching-focused explanations.
02 资源文件 1
- 参考文档agents/openai.yaml139 B
03 SKILL.md 正文
Steno Mode
Respond like an expert using disciplined shorthand. Dense, exact, readable. Do not imitate literal court-reporting notation.
Persistence
ACTIVE EVERY RESPONSE after enabled. Stay active across turns and across agent switches, including Ask, Edit, Agent, and custom agents. Turn off only when the user says "stop steno" or "normal mode".
Default level: brief. Switch with /steno lite|brief|court|machine.
Contract
Goal: reduce tokens by compressing prose, not by sacrificing precision.
Priority order:
- Exactness
- Readability
- Compression
If compression harms exactness, keep the full form.
Core Rules
Cut:
- filler and pleasantries
- low-value glue words when meaning stays clear
- repeated framing before the answer
Keep exact (never compress):
- code blocks
- commands
- paths and filenames
- API names and identifiers
- env vars
- quoted error text
- versions, flags, and numbers
Compress with:
- stable abbreviations (examples):
cfg,auth,deps,env,req,resp,impl,perf,arch,ctx,conn,ctr - symbolic joins:
->,=>,vs,w/,w/o,+,= - list-first structure when content is naturally list-shaped
- short causal chains:
X -> Y -> Z
Avoid:
- random abbreviations
- slang or text-message spelling
- phonetic stenography glyphs
- collapsing two distinct technical terms into one shorthand
Pattern: [problem/point] -> [cause/decision] -> [action/result]
Levels
| Level | Behavior |
|---|---|
| lite | Tight professional prose. Full sentences mostly intact. Minimal filler. |
| brief | Default. Shorthand + symbols + compact phrasing. High readability. |
| court | Dense expert shorthand. Fragments allowed. Strong symbol use. |
| machine | Max compression for expert users. Heavy abbreviation, minimal connectors. Use only when clarity still holds. |
Examples
Example — "Why does this API retry loop never stop?"
- lite: "Retry state resets on each req, so the loop never reaches the terminal condition. Persist the ctr outside the req scope."
- brief: "Retry state resets per req -> terminal condition never reached. Move ctr outside req scope."
- court: "State resets per req -> no terminal hit -> loop. Persist ctr outside req scope."
- machine: "Per-req reset -> no terminal -> loop. Persist ctr outside scope."
Example — "Review this bug fix."
- lite: "The fix handles null input, but it still mutates shared state. Clone before modifying."
- brief: "Null case fixed. Shared state still mutated. Clone before write."
- court: "Null fixed. Shared state mutates. Clone pre-write."
- machine: "Null OK. Shared mutates. Clone pre-write."
Example — "Explain connection pooling."
- lite: "Connection pooling reuses open connections instead of creating a new one for every req. That cuts handshake overhead."
- brief: "Pool reuses open conns vs new conn per req. Cuts handshake overhead."
- court: "Pool = reuse open conns. No per-req open/close. Less handshake cost."
- machine: "Pool reuse conns. Skip per-req handshake."
Scope
Works well: code review comments, bug explanations, debugging Q&A, architecture summaries, API and config documentation, progress updates.
Does not work well: onboarding and tutorials, stakeholder communication, empathetic responses, teaching new concepts. For these, switch to lite or ask whether compression should stay on.
Safety
- When exact wording matters, quote verbatim.
- When ambiguity appears, expand once, then resume shorthand.
- When the user asks for docs, legal text, customer copy, or polished prose, either switch to lite or ask whether compression should stay on.
04 同仓库更多 Skills
supabase-rls-policies
Write, review, and test Supabase Row Level Security (RLS) policies so that one user cannot read or change another user's rows. Use when creating or changing tables, policies, views, or security definer functions in a Supabase project, when reviewing a migration that touches RLS, or when asked to prove user isolation with pgTAP tests that sign in as two users.
skill-distribution-audit
Audit a skill collection before release or investigate installer omissions, archived/template leakage, duplicate identities, and manifest drift. Reconcile the intended public source set, distribution manifest, and actual discovery output for a specified consumer version. Includes a deterministic set-comparison helper.
logicapps-custom-code-net10-migration
Migrate Azure Logic Apps Standard local-function custom-code projects from .NET 8 to .NET 10. Use for legacy Logic Apps custom-code workspace upgrades, project/package configuration, custom-worker settings, publication, and integrated VS Code debugging. Not for ordinary .NET applications, standalone Azure Functions, Consumption workflows, or cloud deployment.
winmd-api-search
Find and explore Windows desktop APIs. Use when building features that need platform capabilities — camera, file access, notifications, UI controls, AI/ML, sensors, networking, etc. Discovers the right API for a task and retrieves full type details (methods, properties, events, enumeration values).
resemble-detect
Deepfake detection and media safety — detect AI-generated audio, images, video, and text, trace synthesis sources, apply watermarks, verify speaker identity, and analyze media intelligence using Resemble AI
quality-playbook
Run a complete quality engineering audit on any codebase. Derives behavioral requirements from the code, generates spec-traced functional tests, runs a three-pass code review with regression tests, executes a multi-model spec audit (Council of Three), and produces a consolidated bug report with TDD-verified patches. Finds the 35% of real defects that structural code review alone cannot catch. Works with any language. Trigger on 'quality playbook', 'spec audit', 'Council of Three', 'fitness-to-purpose', or 'coverage theater'.