Skip to main content
skill CX Codex

review · insilico-org, reviewer — Claude Code skill: plan reviews and installation

This Claude Code skill checks PLSI plan predictions against follow-up results and revises decisions. It runs when a review is due or new results arrive.

MIT ★ 93 updated 2026-11-15

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add Insilico-org/plsi --skill review -a claude-code
Open on GitHub

What review does

The skill compares results with predictions in active PLSI plans, checks adherence and side effects, then proposes continuing, changing, or stopping a plan. It summarizes prediction calibration and marks outcomes as untested when low adherence means the prediction was not properly assessed.

After an adverse event, it screens the plan again; a serious finding can lead to a proposal to stop the action. PLSI Nostradamus drafts any replacement plan, and a decision is recorded only after PLSI relays the user's choice. The PLSI workflow and the plsi command must be available.

What it helps with

  • compare follow-up results with plan predictions
  • separate untested predictions from misses caused by low adherence
  • factor side effects into a plan review
  • summarize prediction calibration and decide what happens next

Example prompts for the agent

  • Run the PLSI plan review and collect any missing follow-up results.
  • Here are the results since the plan started. Compare them with its predictions and propose a decision.
  • The weekly check-in found a side effect. Review the plan.

How to install review

1Skills CLI (Vercel)

npx skills add Insilico-org/plsi --skill review -a claude-code

2Manually: put the files in place

~/.claude/skills/review/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/review/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about review

How do I install review in Claude Code?

Run npx skills add Insilico-org/plsi --skill review -a claude-code. The skill file is at ~/.claude/skills/review/SKILL.md.

What does the review skill do?

It evaluates PLSI predictions against follow-up results, checks adherence and side effects, then drafts a decision to continue, modify, or stop a plan.

What does review need to run?

The PLSI workflow and the plsi command must be available. For a plan change, PLSI Nostradamus drafts the replacement, and the decision is recorded after PLSI relays the user's choice.

Source text

SKILL.md · MIT
---
name: review
description: Use as PLSI Reviewer when PLSI asks for a review - predictions are due (weekly check-in, review date reached) or the user brings follow-up results for an adopted plan; collects adherence and side effects, scores predictions, revises the plan and reports calibration.
---

# PLSI review

## When to use

- The "PLSI check-in" routine found due or awaiting predictions.
- The user sends follow-up results, or a plan reached its review date.
- PLSI's mid-plan check (weekly check-in or a record card) reported low adherence or a side effect: run steps
  2-10 without waiting for the review date.
- An insight PLSI forwards (digest, research note, Mothership): check it against the active plans' predictions and
  actions only (`plsi plan list`), skip step 2, and return `continue` or a `modify` proposal.

## Steps

1. See what is due and what the user has not told yet; each active plan's `plan.json` is in the request's `files`
   (step 4 screens it; missing: say so in a `result`):

   ```bash
   plsi due --instance <instance>
   plsi plan list --instance <instance>
   ```

2. **Adherence and side effects first.** Unless the request already carries them for the whole window, send ONE
   `question` handoff to PLSI per review with, for each active plan: missing measurements; per action the count of
   doses/sessions done of those planned since adoption and the longest gap; any side effect or adverse event since adoption
   (what, when it started, still present, stopped the action?). Wait for the `answer`. PLSI passes the relayed answers to
   `processor/intake`; do not list them again in your `result`.

3. The new results reach you through PLSI after PLSI Data Processor recorded them and re-projected every map the plan uses. Check
   that the state of each map its predictions name (`map_id`) is current (otherwise say so in a `result`; PLSI has
   PLSI Data Processor re-project):

   ```bash
   plsi state show --instance <instance> --map <map_id>
   ```

4. **Adverse event: re-screen before scoring.** Add each reported event as a finding on the action it may belong to
   (`caution`, or `block` when serious or when the action must not continue), then screen the adopted plan again:

   ```bash
   plsi screen --instance <instance> --file plan.json --findings findings.json
   ```

   A `block` outcome forces the proposal to `stop` (or a `modify` that drops the action); state the event plainly.

5. Score:

   ```bash
   plsi score --instance <instance>
   ```

6. **Decide with adherence.** Low adherence = clearly fewer doses/sessions done than the prediction assumed (plan
   `method`; about four in five of those planned if none stated); quote the counts ("9 of 12"), not a share.
   - A miss with low adherence is reported as **not tested**, not as a failure; propose `continue` or `modify`
     (simpler schedule, later window), never `stop` for lack of effect.
   - A hit with low adherence is reported with that caveat.
   - A miss with adequate adherence is a failure of the prediction; apply the `revision_rule`.

7. Summarize calibration in bullets: scored and missed counts, observed within-interval fraction vs the nominal level, mean absolute error, beat-persistence rate and direction accuracy, per coordinate and overall; list not-tested predictions separately.

8. **Draft the decision** per plan: Continue / Modify / Stop / Complete against the plan's `revision_rule`, with each
   prediction's expected value, interval and observed value, adherence and side effects. Before proposing `modify`,
   ask PLSI in a `result` to have PLSI Nostradamus draft the replacement PlanInput as its own file, screened and
   checked (`nostradamus/plan` step 3), with `nostradamus/trajectory` on it (current course vs revised plan); you
   author no plan. Use its files for the decision. List every new caution from step 4 (one line each);
   PLSI shows them above the plan's card, and the user's Continue or Modify proceeds on them. `complete` is allowed
   only after the review date.

9. Send ONE `result`: scores, adherence, side effects, calibration and one decision question per plan (its cautions
   listed above it) and, for `modify`, the replacement's start date; list `trajectory.json` in `files` for a `modify`.
   PLSI shows it with `visualizer/dashboard` (scope "plan review").

10. After PLSI's `answer`, write `review.json` (for `modify`, the full replacement under `"replacement"`), apply it and
    send a `result` with the new plan status, the voided predictions and, for `modify`, the `replacement_plan_id` and
    the user's start date (PLSI has Nostradamus adopt it) with Nostradamus's `trajectory.json` unchanged in `files`, or
    plainly what failed. After `stop`, name `nostradamus/trajectory` as follow-up only if a dashboard needs it:

   ```json
   {"decision": "continue", "rationale": "p1 within interval; 12 of 12 sessions done; no adverse effects reported"}
   ```

   ```bash
   plsi plan review --instance <instance> --plan <plan_id> --file review.json
   ```

## Rules

- Report misses and wrong predictions as plainly as hits; never reword a miss as a success, and never call an
  untested plan a failure.
- Only measurements taken and recorded after adoption, inside the window, count; do not backdate.
- Any adverse event is reported, re-screened and named in the decision, even when the user wants to continue.
- A scored outcome or reported reaction that is a red flag gets a `red_flag:` line (`orchestrator/urgent`) in your
  step's one `question` or `result`; propose pausing the action as a revision.
- `stop` and `modify` void predictions whose window has not opened; say so.
- Never record a decision without the user's choice relayed in PLSI's `answer`.

© Insilico-org · MIT · Insilico-org/plsi

Similar skills

All skills for Code review and refactoring →

review by other authors comes first.

review garrytan review is a Claude Code skill that checks local changes, a branch, or a PR before merge. It examines the diff and writes a review report. CX Codex +1 514installs review official anthropics review is a Claude Code skill that checks incoming agreements against a company playbook and routes them to the right review skills. It runs when a contract is submitted for review. CX Codex +1 778installs review JuliusBrussee Runs an adversarial senior review of the spec before any code is written. Builds a skeptic and tries to refute the plan instead of rubber-stamping it. CX Codex +1 811installs review parcadei review runs parallel specialized subagents to evaluate code quality, architecture, and impact, then synthesizes a final merge verdict. CX Codex +1 523installs review jsmastery-pro review audits completed features against your original plan, system architecture, and production readiness. Flags discrepancies in a structured report without making code edits. CX Codex +1 1,000installs w-review-plan blockmatic-icebox The w-review-plan Claude Code skill checks a plan’s goals, assumptions, tasks, risks, and references. It compares the plan with project code and docs. CX Codex +1 649installs w-review blockmatic-icebox w-review — a skill for Claude Code checks changes for evidenced defects and risks. Run it on a diff, branch, PR, or working tree without asking it to edit code. CX Codex +1 647installs review-walkthrough clhbid The review-walkthrough Claude Code skill guides a reviewer through a pull request and explains the code as they go. It gathers agreed findings into one GitHub review at the end. CX Codex +1 536installs code-review-checklist davila7 code-review-checklist — a skill that walks a reviewer through context, functionality, quality, security, performance and tests. Useful on pull requests and audits. CX Codex +1 365installs dfyx-code-security-review reason-machines The dfyx-code-security-review skill performs white-box static analysis of code, tracing data flows and checking security controls, configuration, and business logic. Use it for a deep project audit. CX Codex +1 342installs eastsword-dfyx-code-security-review reason-machines The eastsword-dfyx-code-security-review skill runs white-box security audits by tracking data flows and spotting authorization or injection flaws. It suits projects preparing code for production. CX Codex +1 331installs

From the same set85

The whole set →
feedback This Claude Code skill builds a report about using PLSI and can email it to the PLSI team. It activates on feedback requests, after setup, and during the weekly feedback routine. CX Codex +1 ★ 93repo stars add-map The add-map Claude Code skill adds a PLSI map for a measured quantity that installed maps do not cover. It activates when a bot reports a map gap or a user asks to track a new quantity. CX Codex +1 ★ 93repo stars patient This Claude Code skill routes a physician’s work on one patient to the appropriate workers. It handles incoming files, visit preparation, notes, evidence reviews and plan options. CX Codex +1 ★ 93repo stars ward The ward Claude Code skill manages individual patient bots in a PLSI team. It creates one when a physician starts work on a roster patient, or removes it after the patient leaves the roster. CX Codex +1 ★ 93repo stars physicians This Claude Code skill finds physicians by specialty and location, then ranks them against a PLSI request. It can also prepare deidentified registry entries for longevity physicians and methods. CX Codex +1 ★ 93repo stars pandaomics Skill for Claude Code queries PandaOmics tools via PLSI when open target evaluation is finished. Connects commercial scoring, grant records, and expert lists using the user's personal token. CX Codex +1 ★ 93repo stars stress This Claude Code skill builds a stress-support plan from current wellbeing context. It screens for crisis signs and reasons to involve a clinician first. CX Codex +1 ★ 93repo stars google-health This Claude Code skill connects Google Health and imports wearable metrics. It runs when PLSI is asked to link an account or fetch a date range. CX Codex +1 ★ 93repo stars

Project sponsors

Companies that keep this analytics open