refine(skills): reconcile flowchart + EXTREMELY-IMPORTANT with the exception rule; writing-skills carve-out

Staff-review findings (4-reviewer panel):
- The skill_flow digraph still routed "yes, even 1%" straight to
  invoke with no exception branch — and this stack's own evidence says
  agents follow flowcharts literally. The flow now passes through
  "Skill's own description exempts this request?" with no/any-doubt →
  invoke.
- The <EXTREMELY-IMPORTANT> block ("you cannot rationalize your way
  out of this") read unconditional; one parenthetical defers to The
  Rule's single carve-out without weakening the block.
- Trimmed the redundant "the description defines the skill's scope"
  clause from The Rule paragraph.
- writing-skills' "descriptions must not carry process" doctrine would
  have had a future editor strip the brainstorming exception and
  silently regress the cost evals; it now distinguishes negative
  triggering conditions (scope — allowed and, per the routing rule,
  required at the description) from workflow summaries (still
  forbidden).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

skills/brainstorming/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: brainstorming
-description: "You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation."
+description: "You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation. The one exception: a request that leaves zero design decisions open needs no design - implement it directly without invoking this skill (e.g. 'add a basic checkbox, nothing fancy' where the context leaves nothing to choose). Decisions ARE open - so invoke - if the change adds a file or dependency, touches a schema, API contract, or persisted data (even when the user stated the outcome), deletes or disables working functionality (even when the deletion is exactly what was asked), touches security posture at all (auth, sessions, permissions, CORS, crypto - even with the exact value stated), alters user-visible behavior beyond the stated change, has more than one plausible reading, or the user frames it as a feature or project to think through."
 ---
 
 # Brainstorming Ideas Into Designs
@@ -10,12 +10,22 @@ Help turn ideas into fully formed designs and specs through natural collaborativ
 Start by understanding the current project context, then ask questions one at a time to refine the idea. Once you understand what you're building, present the design and get user approval.
 
 <HARD-GATE>
-Do NOT invoke any implementation skill, write any code, scaffold any project, or take any implementation action until you have presented a design and the user has approved it. This applies to EVERY project regardless of perceived simplicity.
+Do NOT invoke any implementation skill, write any code, scaffold any project, or take any implementation action until you have presented a design and the user has approved it. This applies to EVERY project regardless of perceived simplicity, with exactly one exception.
+
+Exception — nothing to design: when the exception in this skill's description applies (zero open design decisions; its tripwire list puts the gate back on), implement directly. TDD and verification-before-completion still apply. Brainstorming exists to surface decisions; when there are none, the user's request IS the design. Any doubt: the gate holds.
 </HARD-GATE>
 
 ## Anti-Pattern: "This Is Too Simple To Need A Design"
 
-Every project goes through this process. A todo list, a single-function utility, a config change — all of them. "Simple" projects are where unexamined assumptions cause the most wasted work. The design can be short (a few sentences for truly simple projects), but you MUST present it and get approval.
+Anything with open decisions goes through this process. A todo list, a single-function utility, a data migration — "simple" projects are where unexamined assumptions cause the most wasted work. The design can be short (a few sentences for truly simple projects), but if anything remains to decide, you MUST present it and get approval. Do not confuse this with the nothing-to-design exception above: "this seems simple, I'll skip the design" is a rationalization whenever decisions exist.
+
+| Excuse | Reality |
+|--------|---------|
+| "The codebase has an established pattern, so nothing is open" | A pattern answers HOW, not WHETHER or WHAT. Those decisions are still open unless the user made them. |
+| "I can infer the obvious choice" | If there is a choice to infer, a decision is open. Invoke. |
+| "The user said keep it simple / nothing fancy" | A hedge describes the solution's size, not the request's completeness. Check what remains undecided, not the tone. |
+| "Asking would waste the user's time" | One design question costs seconds; an unexamined assumption costs a rewrite. |
+| "The user already made that decision — they told me to delete it" | A requested deletion still has consequences the user may not have weighed (working feature, no usage data, alternatives). Surface them first; the tripwire applies to requested deletions. |
 
 ## Checklist
 

skills/subagent-driven-development/SKILL.md

@@ -11,6 +11,8 @@ Execute plan by dispatching fresh subagent per task, with two-stage review after
 
 **Core principle:** Fresh subagent per task + two-stage review (spec then quality) = high quality, fast iteration
 
+**Proportionality:** Review fanout scales with the change. When the entire plan is one trivial, fully-specified mechanical change — a log statement, a typo fix, a constant bump with no security or behavioral consequences — implement it directly (or with a single implementer subagent), verify per superpowers:verification-before-completion (run the relevant command, confirm output), commit, and skip all review subagents, including the final reviewer: three review dispatches cost more than a one-line diff. Trivial is a property of the diff — it changes no logic, no control flow, and nothing security-relevant — not of the plan's self-description. Any doubt means not trivial: run the full pipeline. Within a multi-task plan, never skip reviews, regardless of task size.
+
 **Continuous execution:** Do not pause to check in with your human partner between tasks. Execute all tasks from the plan without stopping. The only reasons to stop are: BLOCKED status you cannot resolve, ambiguity that genuinely prevents progress, or all tasks complete. "Should I continue?" prompts and progress summaries waste their time — they asked you to execute the plan, so execute it.
 
 ## When to Use
@@ -61,11 +63,16 @@ digraph process {
     }
 
     "Read plan, extract all tasks with full text, note context, create todos" [shape=box];
+    "Entire plan = one trivial, fully-specified mechanical change? (any doubt = no)" [shape=diamond];
+    "Implement directly, verify, commit (no review fanout)" [shape=box];
     "More tasks remain?" [shape=diamond];
     "Dispatch final code reviewer subagent for entire implementation" [shape=box];
     "Use superpowers:finishing-a-development-branch" [shape=box style=filled fillcolor=lightgreen];
 
-    "Read plan, extract all tasks with full text, note context, create todos" -> "Dispatch implementer subagent (./implementer-prompt.md)";
+    "Read plan, extract all tasks with full text, note context, create todos" -> "Entire plan = one trivial, fully-specified mechanical change? (any doubt = no)";
+    "Entire plan = one trivial, fully-specified mechanical change? (any doubt = no)" -> "Implement directly, verify, commit (no review fanout)" [label="yes — see Proportionality"];
+    "Implement directly, verify, commit (no review fanout)" -> "Use superpowers:finishing-a-development-branch";
+    "Entire plan = one trivial, fully-specified mechanical change? (any doubt = no)" -> "Dispatch implementer subagent (./implementer-prompt.md)" [label="no"];
     "Dispatch implementer subagent (./implementer-prompt.md)" -> "Implementer subagent asks questions?";
     "Implementer subagent asks questions?" -> "Answer questions, provide context" [label="yes"];
     "Answer questions, provide context" -> "Dispatch implementer subagent (./implementer-prompt.md)";
@@ -86,6 +93,10 @@ digraph process {
 }
 ```
 
+## Spec Context
+
+If the plan's header cites a spec (`**Spec:** <path>`), read it once during plan extraction. Plans reference requirements rather than restating them — when a task cites a spec section, paste that section's text into the implementer and spec-reviewer prompts along with the task text. Implementer subagents never read the spec file themselves; the spec reviewer may additionally read it at the cited path (its prompt says so).
+
 ## Model Selection
 
 Use the least powerful model that can handle each role to conserve cost and increase speed.
@@ -237,7 +248,7 @@ Done!
 
 **Never:**
 - Start implementation on main/master branch without explicit user consent
-- Skip reviews (spec compliance OR code quality)
+- Skip reviews — sole exception: a plan that is entirely one trivial change (see Proportionality)
 - Proceed with unfixed issues
 - Dispatch multiple implementation subagents in parallel (conflicts)
 - Make subagent read plan file (provide full text instead)

skills/subagent-driven-development/implementer-prompt.md

@@ -12,6 +12,8 @@ Subagent (general-purpose):
 
     [FULL TEXT of task from plan - paste it here, don't make subagent read file]
 
+    [If the task cites spec sections, paste the cited sections' text here too]
+
     ## Context
 
     [Scene-setting: where this fits, dependencies, architectural context]

skills/subagent-driven-development/spec-reviewer-prompt.md

@@ -12,7 +12,7 @@ Subagent (general-purpose):
 
     ## What Was Requested
 
-    [FULL TEXT of task requirements]
+    [FULL TEXT of task requirements, including the text of any spec sections the task cites]
 
     ## What Implementer Claims They Built
 
@@ -28,7 +28,7 @@ Subagent (general-purpose):
     git diff [BASE_SHA]..[HEAD_SHA]
     ```
 
-    Only read files in this diff. Do not crawl the broader codebase.
+    Only read files in this diff. Do not crawl the broader codebase. (One exception: if the requirements cite a spec document, you may read that spec at its cited path.)
 
     ## Read-Only Review
 

skills/using-superpowers/SKILL.md

@@ -12,7 +12,7 @@ If you think there is even a 1% chance a skill might apply to what you are doing
 
 IF A SKILL APPLIES TO YOUR TASK, YOU DO NOT HAVE A CHOICE. YOU MUST USE IT.
 
-This is not negotiable. This is not optional. You cannot rationalize your way out of this.
+This is not negotiable. This is not optional. You cannot rationalize your way out of this. (The single carve-out: a skill whose own description says it does not apply — see The Rule.)
 </EXTREMELY-IMPORTANT>
 
 ## Instruction Priority
@@ -49,6 +49,8 @@ Skills speak in actions ("dispatch a subagent", "create a todo", "read a file")
 
 **Invoke relevant or requested skills BEFORE any response or action.** Even a 1% chance a skill might apply means that you should invoke the skill to check. If an invoked skill turns out to be wrong for the situation, you don't need to use it.
 
+**Documented exceptions in a skill's own description are authoritative.** When a description itself says the skill does not apply to a request (e.g. brainstorming's nothing-to-design exception), not invoking it is compliance, not rationalization. Any doubt about whether the exception's conditions hold means invoke. Only the skill's description can define such an exception; you cannot infer one.
+
 ```dot
 digraph skill_flow {
     "User message received" [shape=doublecircle];
@@ -69,7 +71,10 @@ digraph skill_flow {
     "Invoke brainstorming skill" -> "Might any skill apply?";
 
     "User message received" -> "Might any skill apply?";
-    "Might any skill apply?" -> "Invoke the skill" [label="yes, even 1%"];
+    "Might any skill apply?" -> "Skill's own description exempts this request?" [label="yes, even 1%"];
+    "Skill's own description exempts this request?" [shape=diamond];
+    "Skill's own description exempts this request?" -> "Invoke the skill" [label="no / any doubt"];
+    "Skill's own description exempts this request?" -> "Respond (including clarifications)" [label="yes, clearly"];
     "Might any skill apply?" -> "Respond (including clarifications)" [label="definitely not"];
     "Invoke the skill" -> "Announce: 'Using [skill] to [purpose]'";
     "Announce: 'Using [skill] to [purpose]'" -> "Has checklist?";
@@ -118,4 +123,4 @@ The skill itself tells you which.
 
 ## User Instructions
 
-Instructions say WHAT, not HOW. "Add X" or "Fix Y" doesn't mean skip workflows.
+Instructions say WHAT, not HOW. "Add X" or "Fix Y" doesn't mean skip workflows — unless a skill's own description exempts the request (see The Rule above).

skills/writing-skills/SKILL.md

@@ -151,6 +151,8 @@ Concrete results
 
 The description should ONLY describe triggering conditions. Do NOT summarize the skill's process or workflow in the description.
 
+(Negative triggering conditions are still triggering conditions: a description MAY state when the skill does NOT apply — including its tripwires — and per using-superpowers' Rule such description-level exceptions are authoritative, so they must live here, not only in the body. That is scope, not workflow.)
+
 **Why this matters:** Testing revealed that when a description summarizes the skill's workflow, an agent may follow the description instead of reading the full skill content. A description saying "code review between tasks" caused an agent to do ONE review, even though the skill's flowchart clearly showed TWO reviews (spec compliance then code quality).
 
 When the description was changed to just "Use when executing implementation plans with independent tasks" (no workflow summary), the agent correctly read the flowchart and followed the two-stage review process.