Files
orca/config/scripts/skill-stub-composition.mjs
T
Jinwoo Hong fb322046e8 skills: rewrite and trim the seven non-orchestration guides (#19128)
* skills: rewrite the seven non-orchestration guides to one outcome-first standard

Every guide leads with Result / Done / Safe failure, states conditions instead of case lists, keeps one done bar and one autonomy envelope, and loads references at the point of use via `skills get <topic> --full`. orca-cli drops from 424 to 260 always-loaded lines with three references; orca-per-workspace-env from 794 to 397 with five.

Defects fixed in shipped guides: `emulator camera` (no such command), iOS `permissions` (backend refuses it), Android pane described as in development, `relayGracePeriodSeconds: 0` documented as immediate teardown (it is unbounded), doctor `ok: true` hiding `warn`, an SSH exemplar setting both `jumpHost` and `proxyCommand`, a provisioned-root fetch from `origin`, and the Linear unconfirmed-write rule keyed on four verbs when ten emit it.

The resolver ladder, placeholder rule, and older-binary fallback shared by every installable SKILL.md now come from one skill-stubs/_shared/cli-resolution.md fragment composed by the generator, which also bundles per-guide references into --full. New guards: every ORCA invocation and flag resolves against COMMAND_SPECS, descriptions carry no angle-bracket tokens, reference routing is checked both ways, and an always-loaded size ratchet (300 lines) that guides may leave but never join.

* skills: address review on the SSH recipe and the parity guard

- ssh-host create script: route the bootstrap ssh through the chosen jump host or proxy command, refuse both at once, use StrictHostKeyChecking=accept-new instead of a blind ssh-keyscan append, and pass gh_token/project_root/repo_url/repo_ref to the remote bash via printf %q so a quote in a value cannot break out of the command.
- per-workspace-env envelope: the step-10 workspace test the user asked for is no longer forbidden by the same paragraph.
- linear guides: name the full verb, ORCA linear list-issues.
- parity guard: a prefix reference such as ORCA linear --help or ORCA emulator --webcam now has its flags checked against every command under that prefix; only an exact path or an explicit ... was checked before.

* skills: tighten prose in the seven rewritten guides

Shorter outcome spines, one idea per sentence, no restated rationale after a rule. No rule, command, or pinned phrase changes; 47 net lines fewer across the guides and references.

* skills: route orca-cli and per-workspace-env gates through --reference

Both guides told agents to load --full at a gate because the per-reference
selector did not exist when they were written. Now that main serves
`skills get <topic> --reference references/<file>.md`, load only the
named file and keep --full as the fallback for an older CLI, matching the
orchestration kernel.

* skills: drop outcome-spine boilerplate from the CLI-wrapper guides

The Result/Done/Safe-failure preambles and Next Action closers restated
rules the body already carries. Agents stop fine without them, and for
a CLI wrapper the command surface is the guide. Keeps the one substantive
rule computer-use's Done block added (never report unverified as success)
inside Action Rules. orchestration and per-workspace-env keep theirs:
those are multi-step workflows where the done bar is load-bearing.

(cherry picked from commit 44a74baf73)

* skills: trim the guides and stubs to what agents actually need

- Drop the Result/Done/Safe-failure preambles and Next Action closers from
  the six CLI-wrapper guides; the one substantive rule (never report an
  unverified computer-use action as success) moves into Action Rules.
- Drop the 'guide may be stale, trust --help' lines: the guide is served by
  the binary that runs the commands, so it cannot be stale relative to it.
- Drop the status --json / open --json preflight from every guide; the stub
  no-guessing paragraph now says to start Orca only when a command reports
  it is not running.
- Cut the ORCA placeholder paragraph in each guide to one line that points
  back at the stub's resolution.
- Trim the orchestration, orca-cli, and computer-use descriptions to trigger
  phrases plus one line of scope.
- Remove the older-binary fallback section from every stub (and its two
  shared blocks); a binary without skills get gets one sentence.
- Remove the guide size ratchet test.

* skills: apply independent review cleanup

* skills: clarify guide loading and Linear command discovery

* skills: harden environment recipe examples

* test: complete branch rename journal doubles

* skills: clarify custom Codex launch and refresh model example

* test: deduplicate journal fix now present on main
2026-09-07 00:03:48 -04:00

85 lines
2.7 KiB
JavaScript

// Keep executable resolution and command-discovery guidance consistent across stubs.
const SHARED_STUB_SOURCE = 'skill-stubs/_shared/cli-resolution.md'
const BLOCK_DEFINITION_PATTERN = /^<!-- block: (?<id>[a-z][a-z0-9-]*) -->$/u
const INSERTION_MARKER_PATTERN = /^<!-- shared: (?<id>\S+) -->$/u
// Lines before the first `<!-- block: -->` are the fragment's own header comment and are
// not projected. Input must already be LF-normalized.
function parseSharedStubBlocks(markdown, sourcePath) {
const blocks = new Map()
let open = null
const close = () => {
if (!open) {
return
}
const text = open.lines.join('\n').replace(/^\n+/u, '').replace(/\n+$/u, '')
if (!text) {
throw new Error(`Shared stub block is empty: ${sourcePath} (${open.id})`)
}
blocks.set(open.id, { text })
}
for (const line of markdown.split('\n')) {
const definition = BLOCK_DEFINITION_PATTERN.exec(line)
if (!definition) {
if (open) {
open.lines.push(line)
}
continue
}
close()
const { id } = definition.groups
if (blocks.has(id)) {
throw new Error(`Shared stub block is defined twice: ${sourcePath} (${id})`)
}
open = { id, lines: [] }
}
close()
if (blocks.size === 0) {
throw new Error(`Shared stub source defines no blocks: ${sourcePath}`)
}
return blocks
}
// Why: an insertion that silently vanished would let a stub drop the safety ladder while the
// generator stayed green, so an unknown marker and a missing or repeated insertion both throw.
function renderSharedStubBody(stubBody, { blocks, sourcePath }) {
const insertions = new Map()
const composed = stubBody
.split('\n')
.map((line) => {
const marker = INSERTION_MARKER_PATTERN.exec(line)
if (!marker) {
return line
}
const { id } = marker.groups
const block = blocks.get(id)
if (!block) {
throw new Error(
`Unknown shared stub block "${id}" in ${sourcePath}. Known blocks: ${[...blocks.keys()].join(', ')}`
)
}
insertions.set(id, (insertions.get(id) ?? 0) + 1)
return block.text
})
.join('\n')
for (const [id, block] of blocks) {
const count = insertions.get(id) ?? 0
if (count !== 1) {
throw new Error(
`${sourcePath} must insert <!-- shared: ${id} --> exactly once; found ${count}.`
)
}
// Why: re-inlining a copy beside the marker is exactly the drift this fragment ends.
const [firstLine] = block.text.split('\n')
if (stubBody.includes(firstLine)) {
throw new Error(
`${sourcePath} re-inlines shared block "${id}"; insert it with a marker instead.`
)
}
}
return composed
}
export { SHARED_STUB_SOURCE, parseSharedStubBlocks, renderSharedStubBody }