Decision review
Agent skills (open standard) for the bookends of the agent loop: context assembly, decision review, and work-shaping outputs. Works with Claude Code and any Agent Skills harness. Ships its own adoption and value measurement.
npx -y skills add arniesaha/ctxops --skill decision-reviewAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
WHEN about to commit to a direction and want a sharp adversarial pass. Triggers: 'should we do X?', 'is this worth it?', 'pressure-test this plan/principle/vision', 'pick between A and B', 're-check the call we made two weeks ago', 'play devil's advocate'. Direct, not balanced. OUTPUT: verdict (do/delay/narrow/compare/kill), strongest case for and against, cheapest test. PAIR BEFORE: ticket-scoping (file the chosen path). Use post-hoc mode for older calls.
SKILL.md
1.8 KB, as published. Nobody here has run it
decision-review
Adversarial review of a single direction or choice between a few. This culls existing options; it does not generate new ones.
Workflow
- Restate the decision in one sentence.
- Identify the actual constraint: time, money, trust, focus, technical risk, market risk, or reversibility.
- Make the strongest case for the direction.
- Make the strongest case against it.
- List hidden assumptions.
- Identify the cheapest test.
- Recommend: do, delay, narrow, compare, or kill.
Post-hoc Mode
When the user asks whether a past call still holds (e.g. "we decided X two weeks ago - is that still right?"):
- Recover the original decision and its assumptions from memory / repo / docs.
- List which assumptions are now confirmed, broken, or unknown.
- Re-run steps 3-7 with current facts.
- Recommend: keep, revise, or reverse - and the smallest action to lock it in.
Output Shape
- Decision
- Verdict
- Strongest case for
- Strongest case against
- Hidden assumptions
- Cheap test
- What would change the verdict
Rules
- Be direct. Do not balance weak arguments for politeness.
- If the real issue is positioning, say so.
- If the real issue is execution capacity, say so.
- Distinguish reversible choices from one-way doors.
- Recommend the smallest action that creates evidence.