Habit · loads whenever its situation comes up, at any step

show-me

about 1,100 tokens

show-me as it installs, each line coloured by where its words came from.

  • 2 files
  • 1 edit
  • 4 sentences left out
  • 1 source
  • last changed 2026-10-19

The text

SKILL.md

about 1,000 tokens
  • HumanLayer
  • greenline

---

name: "show-me"

description: "Explain the current topic visually in the reply: pseudocode, call trees, component trees, shallow file trees, shape diffs, and diagrams or a one-file HTML view where a renderer exists. Use whenever a reply would walk through a flow, a hierarchy, a state machine, a comparison, or a change to an existing shape, and whenever the owner asks to be shown."

---

greenlineOpens the habit: visuals sit in the reply; durable diagrams are offered

# Show me

show-me is the habit for the moment a reply would walk through a flow, a hierarchy, a state machine, a comparison or a change to an existing shape, and for the owner asking to be shown, at whatever step the work is in or in a plain answer. It applies on your own judgment, unasked, and it writes no record of its own: the visual sits in the reply, beside the answer, in a form the current client renders, and earns its place only when it makes the explanation clearer. Answer first, then show: the prose habit governs the claim and the prose around the visual. A durable diagram the owner did not ask for is offered in one line. On the ask or the yes, `diagram-design` (extra, installs on request) draws it where it is installed; where it is not, offer it as AGENTS.md says, or draw the diagram as text into the repository's existing docs home.

greenlinePoints at the skill's references page for paths and commands

Greenline's paths and commands for this skill stand on its references page, [references/greenline.md](references/greenline.md): read it when the work lands in the workspace.

HumanLayershow-me/SKILL.md

Help the user understand the current topic of conversation visually. Skip the preamble and keep prose brief. Pick the smallest view that makes the key point clear.

- Show logic or an algorithm as pseudocode:

```text

on(save)

if content is unchanged

return cached result

write new content

return fresh result

```

- Show runtime control flow as a call tree:

```text

submitForm

createSession

persistPrompt

launchAgent

navigateToSession

```

- Show UI structure as a component tree, including state and module boundaries that matter:

```tsx

<SessionPage> (apps/example/src/routes/session.tsx)

useSessionEvents()

<SessionToolbar>

<RunSkillButton> (packages/ui)

```

- Show file responsibility or a broad refactor as a shallow file tree:

```text

src/

├── commands/ # parses user actions

├── sessions/ # owns session state

└── transport/ # sends API requests

```

HumanLayershow-me/SKILL.md

- Use `diff` when the point is what changes and the surrounding shape already exists. Match the diff shape to the topic.

For a component change:

```diff

<SessionPage>

useSessionEvents()

<SessionToolbar>

+ <RunSkillButton />

<SessionTimeline>

+ <SkillResultCard />

```

For a file-layout change:

```diff

src/

├── commands/

+│ └── show-me.ts # expands the slash command

├── sessions/

-└── transport.ts

+└── transport/

+ ├── client.ts

+ └── stream.ts

```

For a call-tree or call-stack change:

```diff

submitForm

createSession

persistPrompt

+ expandSkillMention

launchAgent

- navigateToSession

+ navigateToSession

+ subscribeToEvents

```

For a state or control-flow change:

```diff

on(save)

- write content

+ if content is unchanged

+ return cached result

+ write new content

+ invalidate cache

```

- Show the whole block when most of it is new, when omitted context would hide ownership or order, or when the user needs a copyable target shape:

```ts

function expandSkill(command: string): string {

const skillName = command.slice(1)

return `use the ${skillName} skill`

}

```

greenlineThe HTML file goes in working files, or outside the repository

- For a visual UI, layout, state comparison, or concept too dense for a text view, write one focused HTML file, a diagram, an infographic, or a short slide deck, whichever fits the point. Match the product's colors, type, spacing, and components; use real labels and data; support desktop and mobile. During a change the file is one of the change's working files; a plain answer writes it outside the repository. Then open it for the user with the harness's shell tool:

greenlineShows the plain open command, not Claude Code's tool-call notation

```

open .greenline/tmp/<id>/{description}.html

```

HumanLayershow-me/SKILL.md

### guidance

Place each visual next to the short text it supports. Keep only the calls, files, props, states, and boundaries needed to answer the user's current question or the options to resolve the current discussion point.

You may use one of these, you may use several, it is unlikely you will use all of them. Use your judgement and don't overwhelm the user.

greenlineThe closing line agrees: nothing durable, the visual in the reply

Durable output: none. The visual lives in the reply, and an HTML view in the change's working files under `.greenline/tmp/<id>/`, deleted when the change closes.

SKILL.md as installed, byte for byte SHA-256 a45f8beddbfebae652203153e1037054a387ce1560e08c4cfb14c2639baffc0a

references/greenline.md

about 90 tokens
  • greenline
greenlineOpens the skill's mechanics page, read with SKILL.md

# Show me: the practice's mechanics

This page holds where show-me's work lands in the workspace and the commands it runs, which `SKILL.md` names by their nouns. Read it with `SKILL.md` when the work lands in the workspace.

greenlineThe working files a page sits in

## Where its work lands

During a change a page is a working file under `.greenline/tmp/<id>/`, such as `.greenline/tmp/<id>/{description}.html`.

The edits

Red is upstream's text; green is what greenline shipped in its place.

What the edit kinds mean
method
changes what the method does, under a recorded ruling
correction
fixes an error
scope
fits the text to this skill
pointer
re-points a reference
smaller edits
rename, relocate or adjust tool details
1 smaller edit

Renames, locations and tool details, each with its reason.

  1. Edit 1 relocate SKILL.md:111

    Upstream: For a visual UI, layout, state comparison, or concept too dense for Mermaid, write one focused HTML file — a diagram, an infographic, or a short slide deck, whichever fits the point.

    Shipped: For a visual UI, layout, state comparison, or concept too dense for a text view, write one focused HTML file, a diagram, an infographic, or a short slide deck, whichever fits the point.

    HTML views go in working files; a text view replaces Mermaid

    Full reason

    the HTML bullet keeps its file in the change's working files under .greenline/tmp/<id>/ and a plain answer's outside the repository, and compares density against a text view instead of the Mermaid option the copy removed because neither harness renders it

What greenline wrote

The full reason for every passage greenline wrote, in the order of the text.

  1. SKILL.md:6 scope

    The title and the opening paragraph in the habit's own voice: the situations its block row keys it by, that it applies unasked and writes no record of its own, the visual living in the reply; the prose habit beside it for the claim; and a durable diagram offered in one line, drawn by diagram-design where it is installed and offered as the block offers an extra where it is not, or drawn as text into the repository's docs home. Re-cut at S18b: the prose habit replaces answer-plainly and unslop, which S18a merged into it, show-me stays implicit against upstream's explicit-only invocation (R22), and the extra is marked as the block marks it.

  2. SKILL.md:10 pointer

    The front points at the skill's references page, where greenline's paths and commands for it stand since J-93 S2, so the front holds the method alone.

  3. SKILL.md:111 relocate

    The HTML bullet keeps its file in the change's working files under .greenline/tmp/<id>/, and a plain answer's outside the repository, and compares density against a text view instead of the Mermaid option the copy removed because neither harness renders it. Since J-93 S2 the front names greenline's homes and commands by their nouns, their paths and commands on the skill's references page.

  4. SKILL.md:113 tool details

    Upstream's Bash(open ...) is Claude Code's tool-call notation; the copy shows the plain shell command the harness's shell tool runs, at the change's working files.

  5. SKILL.md:123 scope

    The habit's closing line agrees with the opening paragraph: nothing durable, the visual in the reply and an HTML view in the change's working files; the durable diagram's offer is the opening paragraph's.

  6. references/greenline.md:1 scope

    The skill's references page opens: greenline's mechanics for the skill, the paths and commands its front names by their nouns, held apart from the upstream prose since J-93 S2.

  7. references/greenline.md:5 relocate

    show-me's mechanics: the working files a page sits in during a change, held apart since J-93 S2.

What it left out

HumanLayer

HumanLayer, show-me/SKILL.md: 4 of 34 sentences left out
  1. Show component interaction, control flow, or data flow with Mermaid:
  2. ```mermaid sequenceDiagram participant User participant UI participant Daemon User->>UI: choose command UI->>Daemon: send expanded prompt Daemon-->>UI: stream result ``` 2 sentences left out: mermaid renders in neither harness TUI, so the worked sequenceDiagram taught a form the reader cannot see.
  3. 14 sentences taken
  4. Then open it for the user: left out: the HTML bullet keeps its file in the change's working files under .greenline/tmp/<id>/ and a plain answer's outside the repository, and compares density against a text view instead of the Mermaid option the copy removed because neither harness renders it
  5. ``` Bash(open path/to/show-me-{description}.html) ``` left out: Upstream's Bash(open ...) is Claude Code's tool-call notation; the copy shows the plain shell command the harness's shell tool runs, at the greenline scratch path.

The ledger entry

greenline's ledger logs how each skill was made and changed, with a reason for each entry.

2026-10-19 2026-10-19-show-me-front-and-references

show-me's paths and commands move to a references page

The front names greenline's homes and commands by their nouns and points at a references page, which holds their paths and commands (J-93 S2).

Authorised by
2026-10-18 The operator's words of 2026-10-18 on the redesign (N-56, items 2 and 7), "we need the upstream prose upfront and references hold how to work meaning the artefacts etc" and, on the ingest procedures, "we wanna have there prose .. what we don't wanna have is there artefact system and fit them to use ours"; and J-93 S2's finalise words of 2026-10-19, "Fast route, merged slices, parallel jobs (Recommended)": a skill's front is the upstream prose its recipe cuts, and its mechanics, where its work lands, its section's form, its depths at each mode and its commands, stand on its references page
Pages it touched
SKILL.md, references/greenline.md
Rulings, R1 to R4
  1. R22 of 2026-10-08, the re-cut brief accepted as recommended ("yes amend, with one change"): the names of the roster table and the trial names stand, and show-me stays implicit
  2. the operator's rulings of 2026-10-04, "cool then lock everything in": every change in every mode has one record its steps write, which replaced the tickets' execution accounts, and a habit writes none of its own
  3. J-59, on the operator's words of 2026-10-09 ('okay then implement all of this'): a gist of at most twelve words on every account whose reason is stated; no text, measure or method changes
  4. The operator's words of 2026-10-18 on the redesign (N-56, items 2 and 7), "we need the upstream prose upfront and references hold how to work meaning the artefacts etc" and, on the ingest procedures, "we wanna have there prose .. what we don't wanna have is there artefact system and fit them to use ours"; and J-93 S2's finalise words of 2026-10-19, "Fast route, merged slices, parallel jobs (Recommended)": a skill's front is the upstream prose its recipe cuts, and its mechanics, where its work lands, its section's form, its depths at each mode and its commands, stand on its references page
4 earlier entries

  1. 2026-10-09 2026-10-09-show-me-gists

    Every account gets a short gist for the website

  2. 2026-10-08 2026-10-08-show-me-recut

    Re-cut on the block, with prose in place of two skills

    Pages it touched: SKILL.md

  3. 2026-10-07 2026-10-07-show-me-refresh

    No text changed; upstream's flag and agent file are not taken

  4. 2026-10-07 2026-10-07-show-me-recipe

    Moves to its recipe byte for byte, nothing changed