Sticky logo

Sticky

CommunityPopular
jeremylongshore
sticky

Use when the user wants to set auto-routing mode: on (every task-shaped message routes), auto (intent-verb messages route — default), or off (no auto-routing). Intent-detection runs by default; use this skill to expand to full sticky or disable entirely. Trigger with /hyperflow:sticky, "make hyperflow sticky", "stop using hyperflow", "is hyperflow sticky", "auto-route to hyperflow", "disable hyperflow auto-routing".

Overview

Publisherjeremylongshore
Repositorytons-of-skills-marketplace
Skill namesticky
Stars
2.8K
Forks
402
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by jeremylongshore on GitHub. Read the source before you install it.

Installation

Install the Sticky AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/jeremylongshore/tons-of-skills-marketplace.git /tmp/tons-of-skills-marketplace
mkdir -p .claude/skills
cp -r /tmp/tons-of-skills-marketplace/plugins/ai-agency/hyperflow/skills/sticky .claude/skills/sticky
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Sticky in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Sticky on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Sticky is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Sticky

Set per-project auto-routing mode. Three states:

StateDefault?Behavior
autoyes (when .sticky absent)Intent-detection routing — messages containing chain-starter verbs (audit, debug, fix, brainstorm, scope, deploy, review, …) auto-route. Pure conversation passes through.
onFull sticky — every task-shaped message routes, even without explicit intent verbs
offAll auto-routing disabled — only explicit /hyperflow:* slash commands trigger chains

Intent-detection is the floor — the user gets it without any opt-in (the orchestrator scans every user message for chain-starter verbs and routes when matched). Sticky on raises the ceiling; sticky off lowers the floor.

Full doctrine: DOCTRINE.md Layer 1 auto-routing clause (intent verb taxonomy + routing contract + bypass patterns).

Subcommands

SubcommandDescription
onSet state: on — full sticky routing on every task-shaped message
autoSet state: auto — intent-verb routing only (the default)
offSet state: off — disable ALL auto-routing including intent detection
statusShow current state (on / auto / off / when toggled)

Default subcommand when none provided: status.

State persistence

Sticky state is stored at .hyperflow/.sticky (project-scoped, gitignored). File format:

state: on
since: 2026-05-17T14:30:00Z
trigger: user-mention   # or: explicit-toggle | session-default

The session-start hook reads this file and prints a one-line advisory when sticky is on (Sticky mode: ON since 2026-05-17 14:30 — task-shaped messages auto-route through hyperflow). Sticky persists across sessions until explicitly toggled off.

Subcommand Details

on

Write .hyperflow/.sticky with state: on + ISO-8601 timestamp + trigger: explicit-toggle. Print:

Sticky mode: ON (full routing)
Every task-shaped message now routes through hyperflow, even without intent verbs.
Disable with /hyperflow:sticky off · or relax to verb-only routing with /hyperflow:sticky auto.

auto

Write .hyperflow/.sticky with state: auto + timestamp. This is the default state when no file exists; explicitly setting it is useful after off to re-enable intent-detection without going to full sticky. Print:

Sticky mode: AUTO (intent-detection routing, default)
Messages containing chain-starter verbs (audit, debug, fix, brainstorm, scope, deploy, review, …) auto-route.
Pure conversation passes through. Expand to full routing with /hyperflow:sticky on.

off

Replace .hyperflow/.sticky contents with state: off + timestamp. (Keep the file rather than delete so the session-start hook can show recent history.) Print:

Sticky mode: OFF
All auto-routing disabled — even intent verbs (audit, debug, fix, brainstorm, …) will no longer route.
Use explicit /hyperflow:* invocations. Re-enable with /hyperflow:sticky auto or /hyperflow:sticky on.

status

Read .hyperflow/.sticky. Print one line:

Sticky mode: ON since 2026-05-17 14:30 (trigger: user-mention)

or:

Sticky mode: AUTO since 2026-05-17 14:30 (trigger: default · intent-detection routing)

or:

Sticky mode: OFF (last changed: 2026-05-16 09:12)

or, if file absent:

Sticky mode: AUTO (default · file not yet written · intent-detection routing active)

Behavioural contract

When sticky is ON, the orchestrator MUST follow this routing on every new user message:

  1. Chat-shaped messages (questions about prior output, "yes" / "no" answers to a pending gate, acknowledgments like "ok"/"thanks", short clarifications) — pass through normally, no chain routing.
  2. Task-shaped messages (any verb-led request for new work: "add X", "fix Y", "refactor Z", "build", "implement", "create", "design", "scope out", "decompose", "ship") — auto-route:
    • New work (whether the user asks what / should we or describes how and names concrete files / functions) → invoke /hyperflow:plan with the user's message as ARGUMENTS. Plan internally bounces past the design phase straight to decomposition when the request is already clear.
    • Existing task file referenced (e.g. "resume the auth task") → invoke /hyperflow:dispatch with the matching slug.
  3. Bug reports ("X is broken", "Y test fails", "Z throws…") → invoke /hyperflow:trace.
  4. Review requests ("review this", "audit the diff", "any issues?") → invoke /hyperflow:audit.
  5. Ship intent ("ship it", "push", "release", "deploy") → invoke /hyperflow:deploy.

The routing decision is made silently — print one short line (Routing to /hyperflow:plan (sticky mode) …) and invoke. Don't ask the user to confirm the routing (that would be an invented gate per DOCTRINE rule 8). The Step 0 chain-mode question still fires inside the routed skill.

Override: if the user message starts with / (any slash command) OR contains "without hyperflow" / "skip hyperflow" / "don't route" → bypass routing for that message; respond directly.

Activation triggers

Intent-detection routing (state: auto) is the default — active for every project without any user action. The orchestrator scans every user message for chain-starter verbs (per the DOCTRINE intent verb taxonomy) and routes when matched. No file write needed.

Upgrades and downgrades:

  1. Upgrade to full sticky (on):
    • Explicit: user runs /hyperflow:sticky on.
    • Implicit: user mentions the word "hyperflow" in a non-slash-command message AND .hyperflow/.sticky does not exist OR is auto. Orchestrator writes state: on · trigger: user-mention · since: <ISO-8601> and prints Sticky mode: ON (upgraded from auto, activated by mention). Disable with /hyperflow:sticky off.
  2. Downgrade to intent-only (auto): user runs /hyperflow:sticky auto.
  3. Disable entirely (off): user runs /hyperflow:sticky off. Disables intent detection too — only explicit /hyperflow:* slash commands route after this.

State is never silently changed by the orchestrator. Only the user's explicit /hyperflow:sticky <state> invocation (or the one-time implicit hyperflow-mention upgrade) modifies .hyperflow/.sticky.

Anti-patterns (when sticky is ON)

  • Asking the user "should I route this to hyperflow?" — that's an invented gate; the user already opted in via sticky
  • Skipping the Step 0 chain-mode question inside the routed skill — sticky controls routing, not gates
  • Routing chat-shaped messages — answering a question shouldn't fire a chain
  • Routing messages that start with / — those are explicit slash commands; honor them as-is
  • Echoing the routing decision as a long paragraph — one short line is enough (Routing to /hyperflow:plan (sticky mode) …)

Flow

  1. Parse subcommand from invocation (default: status).
  2. Read .hyperflow/.sticky (if absent, treat as empty).
  3. Execute subcommand: write the file (on / off) or print state (status).
  4. Print confirmation.

Overview

/hyperflow:sticky toggles per-project sticky-session routing. It does not itself perform routing — that's the orchestrator's behavioral contract when sticky is ON. This skill is the user-facing on/off switch and status reader.

Prerequisites

  • .hyperflow/ directory writable. If absent, the skill creates .hyperflow/ and writes .sticky inside.

Instructions

See Subcommands and Behavioural contract. Summary:

  1. Parse subcommand (default status).
  2. Read or write .hyperflow/.sticky per the chosen subcommand.
  3. Print one-line confirmation.

When sticky is ON, the orchestrator routes per the Behavioural contract on every subsequent user message — this skill itself isn't re-invoked, the contract lives in DOCTRINE.

Output

Single one-line status per subcommand (on / off / status). No multi-line output.

Error Handling

FailureBehavior
.hyperflow/ missingCreate the directory, then write .sticky.
.hyperflow/.sticky exists but malformedPrint one-line warning + treat as OFF. Backup the malformed file to .sticky.bak.
Invalid subcommand (not on/off/status)Print the valid subcommand list and exit.

Examples

Enable sticky mode

/hyperflow:sticky on

Sticky mode: ON
Task-shaped messages now auto-route through /hyperflow:plan (which bounces straight to decomposition when the design is clear).
Chat-shaped messages (questions, answers, acknowledgments) still pass through normally.
Disable with /hyperflow:sticky off.

Sticky activates from a casual mention

You: hey, let's use hyperflow for the next feature
[orchestrator: detects "hyperflow" mention, .hyperflow/.sticky doesn't exist yet]
Sticky mode: ON (activated by mention)
Task-shaped messages now auto-route. Disable with /hyperflow:sticky off.

You: add a search bar to the dashboard with debounced input
[orchestrator: task-shaped, clear request → routes to /hyperflow:plan]
Routing to /hyperflow:plan (sticky mode) …

Check status

/hyperflow:sticky status

Sticky mode: ON since 2026-05-17 14:30 (trigger: user-mention)

Bypass for one message

You: without hyperflow, just tell me what hooks.json controls
[orchestrator: contains "without hyperflow" → bypass for this message]
hooks.json declares the session lifecycle hooks the plugin registers with Claude Code…

Disable sticky

/hyperflow:sticky off

Sticky mode: OFF
Task-shaped messages will no longer auto-route. Use explicit /hyperflow:* invocations.

Resources

  • DOCTRINE.md — Layer 1 sticky-session clause (the behavioural contract the orchestrator follows when sticky is ON).
  • output-style.md — one-line confirmation format.

Frequently asked questions

What does the Sticky AI skill do?

Use when the user wants to set auto-routing mode: on (every task-shaped message routes), auto (intent-verb messages route — default), or off (no auto-routing). Intent-detection runs by default; use this skill to expand to full sticky or disable entirely. Trigger with /hyperflow:sticky, "make hyperflow sticky", "stop using hyperflow", "is hyperflow sticky", "auto-route to hyperflow", "disable hyperflow auto-routing".

Why use Sticky on TypingMind?

Because you install it once and use it with any model. Sticky is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Sticky in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/jeremylongshore/tons-of-skills-marketplace/tree/main/plugins/ai-agency/hyperflow/skills/sticky. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Sticky?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Sticky?

As many as you like. As long as a model supports skills, you can use Sticky with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Sticky AI skill free?

Yes. It is published on GitHub by jeremylongshore under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇