Ct Status Diff logo

Ct Status Diff

Community
agentii-ai
ct-status-diff

Weekly clinical-trial status diff — the 11-category change report over the stored weekly snapshots (spec 055 FR-B03). Surfaces exactly what changed on the trial registry for your coverage: New / Suspended / Withdrawn / Terminated / Recruiting / Recruitment-Complete / Completed / Ahead / Delayed / Upsized / Downsized, every row carrying previous and new values, with risk flags on Terminated and Downsized and re-timing flags on Ahead and Delayed. The stored-previous-value discipline makes each week's diff reproducible.

Overview

Publisheragentii-ai
Repositoryagentii-investment-intelligence
Skill namect-status-diff
Stars
207
Forks
16
Bundled files
2
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by agentii-ai on GitHub. Read the source before you install it.

Installation

Install the Ct Status Diff AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/agentii-ai/agentii-investment-intelligence/tree/main/marketplace-beachhead/plugins/bio-pharm/skills/agentii/ct-status-diff
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/agentii-ai/agentii-investment-intelligence.git /tmp/agentii-investment-intelligence
mkdir -p .claude/skills
cp -r /tmp/agentii-investment-intelligence/marketplace-beachhead/plugins/bio-pharm/skills/agentii/ct-status-diff .claude/skills/ct-status-diff
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Ct Status Diff in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Ct Status Diff on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Ct Status Diff is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Methodology inspired by publicly taught clinical-trial monitoring frameworks; all text is an original paraphrase.

Defaults

ParameterDefault ValueRationale
windowlatest two snapshotsThe diff is always between consecutive stored states
categoriesall 11Complete change report; filter on request
risk_flagsonTerminated / Downsized are surfaced first
gap_statementonMissing snapshot weeks are stated, never inferred

Preflight

Run canonical pre-flight per contracts/preflight.md. Include the X-Agentii-Trace header on every tool call per contracts/x-agentii-trace-header.md — carry the _run_id from your first tool result and name yourself (and your parent, if you were spawned). Confirm the snapshot coverage via get_ct_status_changes before framing any readout.

Triggers

  • "What changed on clinicaltrials.gov for my coverage this week?"
  • "Which of [ticker]'s trials moved this week?"
  • "Any trial delays or accelerations in my watchlist?"
  • "Flag every terminated or downsized trial since last week."
  • "Did any recruitment complete for [ticker]?"
  • "Show the previous and new primary-completion dates for [drug]'s program."
  • "Which trials were upsized this week?"
  • "Is [trial]'s enrollment collapsing?"
  • "Summarize the week's trial-registry changes for the sector."
  • "What should I re-check ahead of [readout] based on registry moves?"
  • "Compare this week's diff to the month-ago diff."

Production Grounding

  • The diff is a stored-state comparison: every row pairs a NEW value with the PREVIOUS value from the prior snapshot — the previous-value column is the discipline; a row without both is a defect.
  • The 11-category taxonomy: New / Suspended / Withdrawn / Terminated / Recruiting / Recruitment-Complete / Completed / Ahead / Delayed / Upsized / Downsized.
  • Risk signals: Terminated and Downsized (enrollment collapse is the earliest visible distress). Re-timing alerts: Ahead / Delayed primary-completion moves.
  • Recruitment-Complete means the readout clock has started — treat it as a catalyst-date confirmation.
  • Gap windows: if snapshots are not consecutive archive writes, the gap is stated on the rows — a change is never attributed across a missing week.
  • Determinism: identical snapshots yield byte-identical diffs; never invent an intermediate state.
  • Badge discipline: [FACT] registry rows, [DEDUCTED] interpretations, [VIEW] positioning, with the summary table.

Data Source Priority

  1. get_ct_status_changes — the stored-weekly-snapshot diff (pipeline.ct_status_snapshot).
  2. Trial context: search_clinical_trials / get_clinical_trial for design and endpoints.
  3. Company context: search_companies / get_company_profile.
  4. Historical grounding: search_investment_cases (event_type=termination/delay/safety) + search_by_analogue.
  5. Knowledge: search_knowledge_entries for trial-judgment patterns.

Methodology

Retrieval Scope

structured_only

Retrieval Strategy

  1. Pull the weekly diff via get_ct_status_changes (ticker-filtered for single names, sector-wide for watchlists).
  2. Rank rows: risk signals first, then re-timing, then recruiting/completed, then new.
  3. For each risk-signal row, pull the trial's design via get_clinical_trial and state what changed and what it implies.
  4. Ground termination/delay reads in search_investment_cases / search_by_analogue (sectors=med); cite /v/ records.
  5. Attach the gap-window statement verbatim wherever the tool reports one.

Temporal Scope

See frontmatter temporal_scope block. Historical diff series (month-over-month) available on request.

Tool Allowlist

See frontmatter allowed_tools.

Protocol

  1. Snapshot-diff pull
  2. Risk/re-timing triage
  3. Per-signal trial context
  4. Historical grounding
  5. Weekly change report + watch flags

Modes

  • Watchlist (default): one diff report across the basket, sorted risk-first.
  • Single ticker: per-trial change ledger with trial context.
  • Signal scan: restrict to risk signals (Terminated/Downsized) or re-timing (Ahead/Delayed).

Tool Fallbacks

FailureFallback
get_ct_status_changes empty (<2 snapshots)State the coverage gap: the diff needs two consecutive snapshot cycles; use search_clinical_trials metadata as a degraded view
Trial not in snapshotsFlag as registry-coverage gap; do not fabricate a previous value
Knowledge tools emptyProceed with structured diff only; annotate knowledge coverage_gap

Output File

{ticker}/{YYYY-MM-DD_HHMM}_ct-status-diff_{affix}.md (watchlist: watchlist/{YYYY-MM-DD_HHMM}_ct-status-diff_{affix}.md)

Output Structure

  1. Executive Summary — the week in trial-registry changes, 2-3 sentences
  2. Risk Signals — Terminated / Downsized rows with previous/new values and trial context
  3. Re-Timing Alerts — Ahead / Delayed rows with date deltas
  4. Flow Changes — New / Recruiting / Recruitment-Complete / Completed / Suspended / Withdrawn rows
  5. Gap Statement — snapshot windows with missing weeks stated
  6. Watch Flags — what to re-check before the next readout
  7. Coverage Gaps — missing snapshots, unregistered trials, degraded modes

Error Handling

ErrorFallback
Fewer than 2 snapshotscoverage_gap with the two-cycle requirement; degraded metadata view only
Empty diffState it plainly — a clean week is a valid result; never pad
Ticker not in med universeResolve via company match; surface the classification gap

Memory Load

See contracts/memory-load.md.

Snapshot

See contracts/snapshot-synthesis.md.

Final Summary (TUI)

Include ### Key Citations block with 0-10 clickable /v/ URLs.

References

  • contracts/citation-and-memory.md
  • contracts/output-frontmatter-schema.md
  • contracts/memory-load.md
  • contracts/snapshot-synthesis.md
  • contracts/preflight.md
  • references/knowledge-frameworks.md

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Ct Status Diff AI skill do?

Weekly clinical-trial status diff — the 11-category change report over the stored weekly snapshots (spec 055 FR-B03). Surfaces exactly what changed on the trial registry for your coverage: New / Suspended / Withdrawn / Terminated / Recruiting / Recruitment-Complete / Completed / Ahead / Delayed / Upsized / Downsized, every row carrying previous and new values, with risk flags on Terminated and Downsized and re-timing flags on Ahead and Delayed. The stored-previous-value discipline makes each week's diff reproducible.

Why use Ct Status Diff on TypingMind?

Because you install it once and use it with any model. Ct Status Diff is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Ct Status Diff in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/agentii-ai/agentii-investment-intelligence/tree/main/marketplace-beachhead/plugins/bio-pharm/skills/agentii/ct-status-diff. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Ct Status Diff?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Ct Status Diff?

As many as you like. As long as a model supports skills, you can use Ct Status Diff with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Ct Status Diff AI skill free?

Yes. It is published on GitHub by agentii-ai under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇