一键在 Manus 中运行任何 Skill

sandstorm-spec

星标6

分支0

更新时间2026年4月19日 23:39

Use this skill whenever the user wants to run the Sandstorm spec quality gate on a ticket, check whether a ticket is ready for agent dispatch, or iterate on a ticket that failed the gate. Trigger phrases include: 'run spec check on ticket N', '/spec-check N', 'is ticket 123 ready', 'check the spec for 178', 'refine the spec for N with these answers', 'here are my answers: ...', 'add my answers and re-check ticket N', 'iterate on the gaps for 42'. This skill wraps the spec_check and spec_refine workflows with a single deterministic script so the orchestrator doesn't have to carry the evaluation logic in its own context. Prefer this skill over the generic sandstorm skill whenever the user's intent is spec-gate evaluation or refinement on a named ticket. Do NOT trigger for: dispatching tasks, creating stacks, reviewing code diffs, or any workflow that isn't specifically about running the spec quality gate.

安装

用 Codex 或 Claude 帮你安装复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。

在 Manus 中运行

来源

onomojo

onomojo/sandstorm-desktop

打开 GitHub 仓库查看创作者相关仓库

下载

在 Manus 中运行

/sandstorm-spec

Wraps the Sandstorm spec quality gate (spec_check and spec_refine) behind a single script. Two subcommands.

Identify the subcommand from the user's message

Use check when the user is asking whether a ticket is ready, running a fresh spec check, or there's no prior question-and-answer context in this conversation.

Use refine when the user is providing answers to gaps that were surfaced by a previous check. Look for cues like "here are my answers," "the answers are," or a direct reply to a gap question you just surfaced.

Run the script exactly once per turn

For check:

bash "$SANDSTORM_SKILLS_DIR/sandstorm-spec/scripts/sandstorm-spec.sh" check <ticket-id>

For refine (user's answers piped verbatim on stdin):

echo "<user's answers verbatim>" | bash "$SANDSTORM_SKILLS_DIR/sandstorm-spec/scripts/sandstorm-spec.sh" refine <ticket-id>

The script prints a JSON payload from the underlying spec agent. Relay its key fields to the user:

If passed: true → report "spec gate passed" and stop.
If passed: false with questions → present the questions to the user and wait for their reply. On the reply, invoke refine.
If the script prints an error line starting with ERROR, relay the error.

Hard rules

NEVER call the spec_check or spec_refine MCP tools directly. This skill is the only path.
NEVER edit the ticket yourself. The spec agent inside the script handles updates.
One script invocation per user message. Do not re-run without user input.

同仓库更多 Skills

同仓库

stack-failure-diagnostic

onomojo/sandstorm-desktop

Use this skill when the user reports a stack appears broken, stuck, looping, failed, or otherwise not working — and wants to understand WHY (not just restart it). Trigger phrases include: 'stack N doesn't seem to be working', 'stack N isn't working', 'stack N failed for some reason / why did stack N fail / what went wrong with stack N', 'stack N seems stuck / got stuck / stuck in an infinite loop / keeps looping / did N loops and failed', 'take a look at stack N, something went wrong / it's broken / something's clearly wrong', 'stack N hit NEEDS HUMAN INTERVENTION / keeps failing / errored out', 'figure out what's happening / going on with stack N', 'give me a summary of what happened with stack N / diagnose stack N'. The skill reads the stack's dual-loop artifacts (phase timings, review verdicts, execution summaries) from inside its container and returns one structured report — avoiding the 40+ Bash-exploration sub-turns the orchestrator would otherwise make. Make sure to use this skill for ANY request that

2026-04-216

check-and-resume-stack

onomojo/sandstorm-desktop

Use this skill whenever the user asks to CHECK the status of an existing stack AND optionally RESUME it if it's not finished. Trigger phrases include: 'check stack N', 'is stack N done', 'what's the status of stack N', 'is N finished', 'pick up where N left off', 'resume stack N', 'we paused stack N can you continue', 'take a look at stack N and if it's not done start it again'. The skill is for EXISTING stacks the user names explicitly by ID — not for new stack creation. Prefer this skill over the generic sandstorm skill whenever the user's intent is a status-check-then-maybe-resume pattern on one named stack; this skill collapses what would otherwise be 10+ MCP calls into a single script. Do NOT trigger for: creating new stacks, dispatching new work, reviewing diffs on demand, tearing down stacks, or listing multiple stacks.

2026-04-206

list-stacks

onomojo/sandstorm-desktop

Use this skill whenever the user asks for a listing / overview / enumeration of their Sandstorm stacks. Trigger phrases include: 'list my stacks', 'what stacks do I have', 'show me all my stacks', 'list stacks', 'what's running', 'give me a rundown of the stacks', 'which stacks are active'. This is a pure listing — it returns every stack with its status and services. Do NOT trigger for: asking about ONE specific stack (that's check-and-resume-stack or stack-inspect), creating a new stack (that's spec-and-dispatch), or any action on a stack.

2026-04-196

stack-inspect

onomojo/sandstorm-desktop

Use this skill whenever the user wants to see DETAILED output, logs, or uncommitted changes from a specific Sandstorm stack. Trigger phrases include: 'show me the output of stack X', 'what did stack X log', 'show the task output for X', 'show container logs for stack X', 'what changed in stack X', 'show me the diff in stack X', 'what's happening inside stack X', 'dump stack X's output', 'get logs for stack X's claude container'. The skill covers three read-only probes — task output, container logs, and uncommitted diff — as subcommands. Do NOT trigger for: a quick status check (that's check-and-resume-stack), listing all stacks (that's list-stacks), or anything that modifies state. Prefer the narrower subcommand (output / logs / diff) over 'all' when the user is specific about what they want.

2026-04-196

spec-and-dispatch

onomojo/sandstorm-desktop

Use this skill whenever the user wants to take an existing ticket / issue, run the Sandstorm spec quality gate on it, and then (once it passes) create a stack with the ticket's verbatim body as the initial task. Trigger phrases include: 'take ticket N and build it', 'spec and dispatch N', 'fire up a stack for ticket N', 'let's work on #N', 'start issue N in a stack', 'create a stack for issue N, run the gate first'. This skill is the full start-to-dispatch flow for a ticket: fetch ticket → spec_check → (refine loop if needed) → create_stack with gateApproved=true and the ticket body as the initial task. Do NOT trigger for: dispatching follow-up work to an EXISTING stack (that's the sandstorm / check-and-resume flow), running the spec gate in isolation (that's the sandstorm-spec skill), or creating a stack without a ticket.

2026-04-196

review-and-pr

onomojo/sandstorm-desktop

Use this skill whenever the user is ready to publish the work from an existing Sandstorm stack — reviewing the diff, pushing to its branch, opening a pull request, and recording the PR on the stack. Trigger phrases include: 'make a PR for stack X', 'publish stack X', 'push and PR stack X', 'the diff looks good, ship it', 'open a pull request for stack X', 'finalize stack X', 'commit and push stack X to a PR'. This is the end-of-workflow publish step for a stack that has completed its task and whose diff the user has seen (or is about to see via this skill). Do NOT trigger for: pushing WITHOUT a PR, creating a stack from scratch, dispatching new work, or any workflow where there are no changes to publish. Do NOT trigger if the stack is still running — the skill assumes the task is finished.

2026-04-196

name

sandstorm-spec

description

/sandstorm-spec

Wraps the Sandstorm spec quality gate (spec_check and spec_refine) behind a single script. Two subcommands.

Identify the subcommand from the user's message

Use check when the user is asking whether a ticket is ready, running a fresh spec check, or there's no prior question-and-answer context in this conversation.

Run the script exactly once per turn

For check:

bash "$SANDSTORM_SKILLS_DIR/sandstorm-spec/scripts/sandstorm-spec.sh" check <ticket-id>

For refine (user's answers piped verbatim on stdin):

echo "<user's answers verbatim>" | bash "$SANDSTORM_SKILLS_DIR/sandstorm-spec/scripts/sandstorm-spec.sh" refine <ticket-id>

The script prints a JSON payload from the underlying spec agent. Relay its key fields to the user:

If passed: true → report "spec gate passed" and stop.
If passed: false with questions → present the questions to the user and wait for their reply. On the reply, invoke refine.
If the script prints an error line starting with ERROR, relay the error.

Hard rules

NEVER call the spec_check or spec_refine MCP tools directly. This skill is the only path.
NEVER edit the ticket yourself. The spec agent inside the script handles updates.
One script invocation per user message. Do not re-run without user input.