Before heavy deliberation, classify the decision as cheap or costly to undo; decide two-way doors fast and stage one-way doors to preserve options.
SkillScore79Maintained
On-demandOn-demand: invoked explicitly — never occupies your agent's context until called.
◆Product Management pack
Last verified 8/14/2026
What it changes
Passed 19 of 24 test cases with the skill, and 7 of 24 without it.
Without skill29%
With skill79%
Checks it passed that the model alone missed
Recommends pilot as the process depth.
Recommends decide-now as the process depth.
Recommends full deliberation as the process depth.
and 8 more in the full report
12 fixed7 passed either way5 still failing0 broke
Pass-rate lift
+50 pp
Tokens
-11%
Agent turns
0%
Response time
-39%
Model gemini-3.6-flashMeasured 8/14/2026v119 of 24 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 12 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 12
Prompt
Our software team wants to introduce an automated code formatter into our pull request CI check pipeline. Evaluate this tool decision using a structured key-value output.
What was checked, without and with the skill
Checked
Without skill
With skill
Classifies adding a linter to CI checks as Type 2.
Missed
Passed
Recommends decide-now as the process depth.
Missed
Passed
case-14 · gemini-3.6-flash · 8/14/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md50 linessingle file
Reversibility
Core rule: match process depth to undo cost. Most decisions are cheaper to reverse than they look; irreversible ones deserve deliberation and staged commitment.
When to Use
Uncertain how much analysis a decision deserves (tech, process, product, org)
Tempted to committee a low-blast-radius choice, or to rush a high-lock-in one
Can redesign the move (pilot, flag, abstraction, time-box) to lower undo cost
High-stakes choice where acting vs waiting have asymmetric recovery profiles
When NOT to Use
Already classified this session—decide at matched depth; do not re-label forever
Trivial two-way calls (names, local refactors) where deciding is cheaper than classifying
Externally forced move with no optionality (hard deadline, contract, regulation)
Correctness gates (security, data integrity) that need the right answer, not speed theater
Procedure
Name the decision and undo path. State what would be committed and the concrete reverse move (rollback, migrate back, revoke, re-hire, re-contract).
Score reversibility. Assess technical effort, time, money, reputation, dependents, and learning lost if reversed. Classify:
Type 2: undo in days, low cost → decide fast
Type 1.5: undo in weeks, moderate cost → light structure + monitor
Type 1: months or not realistically undoable → deliberate
Asymmetric downside / recovery. For Type 1 or 1.5:
Not acting: what permanently closes (window, exclusivity, path lock)
Rule: recoverable acting downside + permanent inaction loss → staged commit over indefinite delay; catastrophic or third-party harm → refuse or redesign first
Option-preserving redesign. Prefer pilots, feature flags, interfaces, versioning, time-boxed vendor terms, or strangler slices that convert Type 1 surface into Type 2 experiments. Deliberate only the residual irreversible core.
Match process and commit. Type 2: pick a reasonable option, ship, monitor. Type 1: document assumptions, argue the opposing case, surface to owner if stakes require it. Stop once class and commitment depth are set—do not re-analyze without new undo-cost evidence.