Suede Recommend Next Action
Recommend one action and package it as a short runnable prompt. Inspect
current state read-only; do not execute the recommended action unless the
user separately authorizes execution. Keep the full operator contract hidden
until the user asks to expand it.
Recommendation Workflow
- Resolve the target and the user's actual done outcome from the current
request, conversation, handoff, plan, repo, or live surface.
- Check only the evidence needed to distinguish the next move. Prefer, in
order: current terminal/repo/live state, current source documents, current
plans or handoffs, then older memory. Run the reads, don't assume them:
git -C <target-repo> status --short --branch for dirty files and
ahead/behind, git -C <target-repo> log --oneline -5 for what actually
landed, a direct read of the named plan/STATE/handoff file at its exact
path, and — when a live surface is in scope — a fetch of the URL itself
(curl -sS -o /dev/null -w '%{http_code}' <url>) instead of trusting the
last recorded deploy. Skip any read that cannot change which candidate wins.
- Generate 2-4 candidate actions internally. Exclude work already verified as
complete, adjacent cleanup, and actions outside the user's authorized scope.
- Score each candidate from 0-2 on every criterion below. Recommend the
highest total.
| Criterion |
2 points |
1 point |
0 points |
| Goal alignment |
Directly produces the user's done signal |
Required prerequisite |
Merely adjacent |
| Unblocking |
Unlocks a core path or at least two downstream steps |
Unlocks one step |
Unlocks nothing known |
| Evidence |
Confirmed by current source |
Confirmable with one read-only check |
Depends on an assumption |
| Urgency |
Active failure, deadline, security risk, or release gate |
Needed for the active milestone |
No current pressure |
| Leverage |
Fits one focused session and prevents rework or creates a reusable result |
Bounded work with moderate payoff |
Unscoped, multi-day, or low-payoff work |
- Break ties by preferring a required prerequisite, then current-evidence
verification, then the more reversible action. If the top two remain within
one point and target ambiguity would change the answer, run at most three
additional read-only checks. If still tied, show both choices and state the
single fact that decides between them.
- Turn the recommendation into a 2-4 sentence quick prompt. Keep the scoring
and full operator contract internal unless the user asks to compare choices,
expand prompt, or make it granular.
Routing Rules
- If a repo or task already has its own plan, progress doc, issue tracker, or
project board, do not create a second one. Treat its recorded next step as
one candidate, verify it against current source, and recommend the winner —
don't replace the existing tracker.
- If the user needs options explored before a commitment can be made, say so
and offer to brainstorm instead of forcing a single recommendation.
- If missing evidence is the real blocker, make the smallest read-only check
the recommended action and generate a prompt for that check.
Prompt Levels
The three prompt depths — short copy/paste, full operator prompt, granular steps —
are in references/prompt-levels.md. The default is the short prompt; read this
only when the user asks to expand or make it granular.
Output Format
Recommended action: <one sentence>
Why now: <one evidence-backed sentence>
Quick prompt: <2-4 runnable sentences>
Say "expand prompt" for the full operator version or "make it granular" for exact steps and commands.
Show the route, score, evidence list, confidence, or alternatives only when the
user asks for rationale or when the unresolved tie rule requires them. When the
recommendation is an evidence-gathering step, state that in Why now without
loading the expanded prompt.
Boundaries
- Do not mutate files, repos, deployments, accounts, messages, or live systems
while recommending.
- Do not load the expanded or granular prompt by default.
- Do not repeat a broad audit when one current execution lane can be selected.
- Do not invent paths, URLs, skill availability, status, metrics, owners, or
completion evidence.
- Do not recommend vague actions such as "keep working", "improve the app", or
"do more research". Name a command, artifact, decision, edit, or verification
result.
- Do not hide a blocker. If authority or a decisive fact is missing, make its
resolution the next action.
Routing
- Need multi-lane coordination across specialists -> use
suede-agent-teams.
- Need help picking which single skill fits a request -> read this pack's
router (
suede-workflow-skills) or ask directly.
- Need idea exploration before selecting a move -> brainstorm directly with
the user instead of forcing a single recommendation.
- Need execution -> use the specialist named in the generated prompt.
1---2name: suede-recommend-next-action3description: Next-action selector for the Suede pack: inspects current repo, terminal, plan, or handoff state read-only and returns one recommended next move plus a short, self-contained copy/paste prompt for it. Use when the user asks 'what's next', 'what should I do next', 'recommend the next move', 'give me the prompt', 'expand prompt', or 'make it granular', especially after a review, audit, plan, or stalled task. NOT FOR: executing the recommended action without the user's separate authorization, or coordinating a multi-lane build across specialists (use suede-agent-teams).4---56# Suede Recommend Next Action78Recommend one action and package it as a short runnable prompt. Inspect9current state read-only; do not execute the recommended action unless the10user separately authorizes execution. Keep the full operator contract hidden11until the user asks to expand it.1213## Recommendation Workflow14151. Resolve the target and the user's actual done outcome from the current16 request, conversation, handoff, plan, repo, or live surface.172. Check only the evidence needed to distinguish the next move. Prefer, in18 order: current terminal/repo/live state, current source documents, current19 plans or handoffs, then older memory. Run the reads, don't assume them:20 `git -C <target-repo> status --short --branch` for dirty files and21 ahead/behind, `git -C <target-repo> log --oneline -5` for what actually22 landed, a direct read of the named plan/STATE/handoff file at its exact23 path, and — when a live surface is in scope — a fetch of the URL itself24 (`curl -sS -o /dev/null -w '%{http_code}' <url>`) instead of trusting the25 last recorded deploy. Skip any read that cannot change which candidate wins.263. Generate 2-4 candidate actions internally. Exclude work already verified as27 complete, adjacent cleanup, and actions outside the user's authorized scope.284. Score each candidate from 0-2 on every criterion below. Recommend the29 highest total.3031| Criterion | 2 points | 1 point | 0 points |32|---|---|---|---|33| Goal alignment | Directly produces the user's done signal | Required prerequisite | Merely adjacent |34| Unblocking | Unlocks a core path or at least two downstream steps | Unlocks one step | Unlocks nothing known |35| Evidence | Confirmed by current source | Confirmable with one read-only check | Depends on an assumption |36| Urgency | Active failure, deadline, security risk, or release gate | Needed for the active milestone | No current pressure |37| Leverage | Fits one focused session and prevents rework or creates a reusable result | Bounded work with moderate payoff | Unscoped, multi-day, or low-payoff work |38395. Break ties by preferring a required prerequisite, then current-evidence40 verification, then the more reversible action. If the top two remain within41 one point and target ambiguity would change the answer, run at most three42 additional read-only checks. If still tied, show both choices and state the43 single fact that decides between them.446. Turn the recommendation into a 2-4 sentence quick prompt. Keep the scoring45 and full operator contract internal unless the user asks to compare choices,46 `expand prompt`, or `make it granular`.4748## Routing Rules4950- If a repo or task already has its own plan, progress doc, issue tracker, or51 project board, do not create a second one. Treat its recorded next step as52 one candidate, verify it against current source, and recommend the winner —53 don't replace the existing tracker.54- If the user needs options explored before a commitment can be made, say so55 and offer to brainstorm instead of forcing a single recommendation.56- If missing evidence is the real blocker, make the smallest read-only check57 the recommended action and generate a prompt for that check.5859## Prompt Levels6061The three prompt depths — short copy/paste, full operator prompt, granular steps —62are in `references/prompt-levels.md`. The default is the short prompt; read this63only when the user asks to expand or make it granular.6465## Output Format6667```text68Recommended action: <one sentence>69Why now: <one evidence-backed sentence>7071Quick prompt: <2-4 runnable sentences>7273Say "expand prompt" for the full operator version or "make it granular" for exact steps and commands.74```7576Show the route, score, evidence list, confidence, or alternatives only when the77user asks for rationale or when the unresolved tie rule requires them. When the78recommendation is an evidence-gathering step, state that in `Why now` without79loading the expanded prompt.8081## Boundaries8283- Do not mutate files, repos, deployments, accounts, messages, or live systems84 while recommending.85- Do not load the expanded or granular prompt by default.86- Do not repeat a broad audit when one current execution lane can be selected.87- Do not invent paths, URLs, skill availability, status, metrics, owners, or88 completion evidence.89- Do not recommend vague actions such as "keep working", "improve the app", or90 "do more research". Name a command, artifact, decision, edit, or verification91 result.92- Do not hide a blocker. If authority or a decisive fact is missing, make its93 resolution the next action.9495## Routing9697- Need multi-lane coordination across specialists -> use `suede-agent-teams`.98- Need help picking which single skill fits a request -> read this pack's99 router (`suede-workflow-skills`) or ask directly.100- Need idea exploration before selecting a move -> brainstorm directly with101 the user instead of forcing a single recommendation.102- Need execution -> use the specialist named in the generated prompt.
tuyv