agentsclimarketplace

Decision review

Skill arniesaha/ctxops/skills/decision-review

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.From its SKILL.md

Install
npx -y skills add arniesaha/ctxops --skill decision-review

Assembled 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.

SKILL.md

1.8 KB, 311 tokens by cl100k_base, 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

  1. Restate the decision in one sentence.
  2. Identify the actual constraint: time, money, trust, focus, technical risk, market risk, or reversibility.
  3. Make the strongest case for the direction.
  4. Make the strongest case against it.
  5. List hidden assumptions.
  6. Identify the cheapest test.
  7. 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?"):

  1. Recover the original decision and its assumptions from memory / repo / docs.
  2. List which assumptions are now confirmed, broken, or unknown.
  3. Re-run steps 3-7 with current facts.
  4. 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.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most review quality skills give in 311 tokens

Counted across 1,273 of the 2,403 authors here whose files we hold, read 2026-09-06

  • Ask one question at a timein 63 of 1273, across 62 files
  • Provide a recommended answer for each questionin 47 of 1273, across 45 files
  • Rank findings by severityin 44 of 1273
  • Use parameterized queries for database accessin 38 of 1273, across 20 files
  • Validate all user input with schemasin 33 of 1273, across 15 files
  • Store secrets in environment variablesin 32 of 1273, across 14 files
  • Explore the codebase to answer questionsin 31 of 1273, across 29 files
  • Store tokens in httpOnly cookiesin 30 of 1273, across 12 files
  • Implement rate limiting on API endpointsin 30 of 1273, across 12 files
  • Sanitize user-provided HTMLin 29 of 1273, across 11 files
  • Return generic error messages to usersin 28 of 1273, across 10 files
  • Cite file and line for every findingin 28 of 1273, across 25 files

Said here and by no other author read

  • Restate the decision in one sentence
  • Identify the actual constraint
  • Make the strongest case for the direction
  • List hidden assumptions
  • Identify the cheapest test
  • Recommend do delay narrow compare or kill

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.