intent
Paved command paved.intent. Start a repository change by classifying its type and recording the request before planning. Use when the user asks to begin a feature, bug fix, refactor or performance improvement, or asks a question about the code that needs a cited answer.
- License 许可
- MIT
- 最近更新
- 2026-11-14
- Stars
- ★ 1
- Forks
- 0
01 前言 Front Matter
- name
- intent
- description
- Paved command paved.intent. Start a repository change by classifying its type and recording the request before planning. Use when the user asks to begin a feature, bug fix, refactor or performance improvement, or asks a question about the code that needs a cited answer.
03 SKILL.md 正文
<!-- Generated by Paved plugin paved@2.29.0 from paved.intent; edit Paved Core instead. -->
Paved intent command (paved.intent)
Start a repository change by classifying its type and recording the request before planning. Use when the user asks to begin a feature, bug fix, refactor or performance improvement, or asks a question about the code that needs a cited answer.
Input: The user's request, verbatim; classify with --workflow <id> --because <evidence>, or let the user decide. Output: The run, its Intent document, its classification or the decision that settles it, and context and discovery results. Required lifecycle: RESOLVED, GENERATED, VALIDATED, READY Required context: .paved/manifest.yaml, .paved/project/, .paved/rules/, core workflows Required capabilities: none declared Allowed side effects: .paved/generated/runs/, .paved/documents/intents/, disposable Paved evidence
Execution contract
- Invoke
node "${CLAUDE_PLUGIN_ROOT}/scripts/paved.mjs" intent --jsonfrom the repository root, passing the user's command inputs as supported CLI arguments. The launcher loads the pinned project-local runtime and returns the canonical structured result. Always run it from the repository being worked on, never from the plugin directory. - Follow the structured result's status, diagnostics, evidence, and next action. When
data.remediationnames a Paved command, run it right away, present any decisions it returns, then repeat the original command. Stop only when the runtime blocks on something it cannot remediate. - Pass the user's request verbatim. When the evidence shows the kind of change, add
--workflow <feature|bug|refactor|performance|investigation> --because "<evidence>". When it does not, omit--workflow(optionally--recommend <id> --because …) and present the returned decision. When the request mixes kinds of change, pass each part with--partand present the split decision. Never classify on a guess. - When the result has a
reviewblock, startpaved preview start <target> --jsonand follow thepaved.previewreview loop.
Phase Tool policies
Follow the active data.phaseContext, including its composed skills, declared Tools and bound fragment bodies. Apply each phaseContext.toolPolicies entry's effective allow, ask and deny Tool ids: deny excludes use; ask requires the host's own approval flow; allow is a workflow recommendation only and never grants execution permission or replaces host approval. Host policy can always be stricter. Policies do not add Tools to the phase's declared set. Omitted Tools retain existing host behavior, and an empty policy list preserves existing behavior.
Run autonomy
For a new intent or execute request, pass the user's explicit --autonomy <guided|balanced|autonomous> selection. It overrides the workflow's optional autonomy.default_profile; pending classification preserves the explicit selection. The recorded data.autonomy_profile is fixed on resume. If no selection or workflow default exists, leave the profile absent and keep current behavior.
For guided, stop after every completed phase and wait for the user to advance; do not immediately repeat --auto or another advance call. For balanced, continue through ready phases with execute --auto. For autonomous, use balanced continuation and automatically dispatch only ready tasks from an approved delegation plan, respecting its dependencies and bounded scope, through native host tools. The CLI creates no sessions.
Every profile preserves gates, human approvals, required input stops, failures, verification, evidence and completion requirements. Host permissions remain authoritative; an autonomy profile is never an approval or tool permission. Apply this policy to the continuation and routing guidance above.
Before asking the user
Triage every question of your own before you ask it. When the answer is observable (current behavior, output, timing, layout, whether a test fails), find it out by reading the code, running it or trying a throwaway experiment outside the repository; an experiment inside the repository follows the prototyping skill. Ask only about preferences: product, scope, priority or taste calls that no experiment settles. When you raise one with paved decision raise, set questionKind; an observable question needs an observationBlocker saying why you could not observe it. Triage never skips a human step: present every decision Paved emits, and plan approval and confirmation of destructive actions stay with the user.
Failure behavior
- A workflow choice without evidence is refused.
- When the kind of change is uncertain, the user decides; Paved never guesses.
- A bug needs a failing regression test and a refactor a passing baseline before planning.
- If a required ToolImplementation or runtime is unavailable, stop and explain the missing prerequisite. Never infer or execute a command from repository scripts.
- Do not edit human-owned Paved state or bypass lifecycle, ownership, approval, or verification gates.
Conversational contract
- Invoke the command. If it returns
"status": "awaiting_input", it is waiting on the user. - Present every decision in
decisions[]to the user: what Paved detected, what remains to decide, why it matters, the options, Paved's recommendation and its evidence. - Collect the user's answer. Do not answer on their behalf.
- Resume the same command with
--answer <decision-id>=<value> --answered-by <identity>, repeating--answeronce per value for a multi-choice decision. - Present the result.
Follow core.decisions.decisions for the full interaction protocol and its prohibitions.
04 同仓库更多 Skills
sample-skill
Does a sample task. Use when a sample is needed.
unexplained-contract
Does a sample task. Use when a sample is needed.
shell-block
Does a sample task. Use when a sample is needed.
project-identifier
Does a sample task. Use when a sample is needed.
oversized
Does a sample task. Use when a sample is needed.
no-activation
Does a sample task.