Skip to content
CAI
Software that uses CAICheck a score

anthropics/knowledge-work-plugins

45.9

Weak · 16 November 2026

8k

lines of production code

Python

with JavaScript

5

measurements over time

CAI band scale
CAI trend line
CAI lens gauges

What this system is

Features

New partner plugins: Apollo and Brand Voice

Two new partner-built plugins are now available. The Apollo plugin (v0.1.0) adds three sales skills—lead enrichment, ICP-based prospecting, and sequence loading—via an HTTP MCP server at mcp.apollo.io. The Brand Voice plugin (v1.1.0) by Tribe AI discovers brand materials and enforces voice across enterprise platforms, connecting to Notion, Atlassian Confluence, Box, Figma, Gong, and Granola via HTTP MCP servers.

partner-built · high confidence

Removals

Removal of clinical-trial-protocol skill and associated assets

The clinical-trial-protocol skill, along with its supporting reference documents (initialization, research, foundation, intervention, and operations steps) and the FDA clinical protocol template, has been removed from the bio-research/skills directory. This eliminates the ability to generate and manage clinical trial protocols for medical devices or drugs within this plugin.

bio-research/skills · high confidence

Behavioural changes

Improved dashboard security and restructured productivity skills

The productivity dashboard now escapes file-derived content before rendering it via innerHTML, preventing potential cross-site scripting issues when displaying task titles, notes, and memory file names. Additionally, the system has migrated from a 'commands' to a 'skills' structure, renaming and relocating skill definitions (such as start, update, and memory-management) to the new skills directory, with updated descriptions and path references to reflect the new organization.

productivity/skills · high confidence

New shared behavioral guidelines for the Small Business plugin

The small-business/shared area now includes a suite of new reference documents that define plugin-wide behavioral rules and connector-specific implementation details. These files establish how skills should handle data integrity (distinguishing absent data from zero), manage cross-skill data seams, enforce connector neutrality, and format outputs (including currency, locale, and document preferences). They also provide specific traps and correct API call shapes for connectors like Gmail, Gusto, QuickBooks, HubSpot, and Salesforce, ensuring consistent and accurate behavior across the plugin.

small-business/shared · high confidence

Replace bare excepts with specific Exception handling in environment checks

The environment validation scripts in bio-research now catch only Exception instead of using bare except clauses. This change prevents the accidental suppression of system-exiting errors (such as KeyboardInterrupt or SystemExit) during resource and network checks, ensuring that critical interruptions are not silently ignored.

python · high confidence

Written by cca.canine.dev from the codebase's own history, inside the signed delivery this page is composed from.

How this codebase got here

This is the PUBLIC form of this artifact. Findings are listed in full, but the details of SECURITY findings — which rule fired, in which file, on which line, and how to fix it — are deliberately withheld, and any secret-scanner results are excluded entirely. Where detail is absent here it was REMOVED FOR PUBLICATION; it is not missing from the analysis. The complete artifact is available from the repository owner.

Score

  • CAI 45 → 46 (+0.5)
  • Rubric changed (rubric-2026.11.2 → rubric-2026.11.4) — scores are not directly comparable.

Lenses

  • Code Health 55 → 49 (-5.8)
  • Architecture 96 → 96 (+0.0)
  • Maturity 81 → 82 (+0.6)
  • Readiness 32 → 32 (+0.0)
  • Security 100 → 100 (+0.0)
  • Accessibility 41 → 46 (+4.8)

Resolved (14)

  • Duplicated block (13 lines × 2) (bio-research/skills/scvi-tools/scripts/validate_adata.py)
  • Duplicated block (19–20 lines × 2) (bio-research/skills/nextflow-development/scripts/check_environment.py)
  • Duplicated block (22 lines × 2) (bio-research/skills/scvi-tools/scripts/cluster_embed.py)
  • Duplicated block (5 lines × 2) (bio-research/skills/scvi-tools/scripts/cluster_embed.py)
  • Duplicated block (7–8 lines × 2) (bio-research/skills/scvi-tools/scripts/model_utils.py)
  • Duplicated block (8 lines × 2) (bio-research/skills/scvi-tools/scripts/model_utils.py)
  • Duplicated block (9 lines × 2) (bio-research/skills/nextflow-development/scripts/manage_genomes.py)
  • High: security finding (details withheld)
  • High: security finding (details withheld)
  • High: security finding (details withheld)
  • High: security finding (details withheld)
  • Near-duplicate member pair (25 shared lines) (bio-research/skills/nextflow-development/scripts/utils/ncbi_utils.py)
  • No tests found
  • Off-boarding risk: anonymized user #1

New (4)

  • Edited copy of a member (19 corresponding lines) (bio-research/skills/instrument-data-to-allotrope/scripts/export_parser.py)
  • Edited copy of a member (23 corresponding lines) (bio-research/skills/scvi-tools/scripts/train_model.py)
  • Edited copy of a member (50 corresponding lines) (bio-research/skills/nextflow-development/scripts/utils/ncbi_utils.py)
  • High: security finding (details withheld)

Changes since last survey

  • 16 commits — 16 feature/other, 0 fixes

By area

  • (repo) — 6 commits
  • .claude-plugin/marketplace.json — 6 commits
  • small-business/.mcp.json — 2 commits
  • .github/workflows — 1 commit
  • small-business/skills — 1 commit

Notable commits

  • change: Close every pull request opened by a non-member
  • change: Merge pull request #1428 from anthropics/mhegazy/bump-security-guidance-2.0.18
  • change: Merge pull request #1431 from anthropics/mhegazy/bump-security-guidance-2.0.19
  • change: Merge pull request #1439 from anthropics/close-external-prs
  • change: Merge pull request #1440 from anthropics/mhegazy/bump-security-guidance-2.0.20
  • change: Merge pull request #1445 from anthropics/bump/qodo
  • change: Merge pull request #1448 from anthropics/bump/blackrock-advisor-center-plugin
  • change: bump(blackrock-advisor-center-plugin): 591c7589 → 736344f8
  • change: bump(qodo): b8c21854 → 80240e3f
  • change: bump(security-guidance): 41f619d6 → c07c748f
  • change: bump(security-guidance): c07c748f → dceb15d5
  • change: bump(security-guidance): dceb15d5 → f75f5b25
  • change: bump(unity): ba48956a → 81b6079e (#1425)
  • change: small-business: finish the airwallex rename and bump to 1.35.2 (#1430)
  • change: small-business: point Atlassian at v2 and rename the key (#1438)
  • change: small-business: rename airwallex-agentos server key to airwallex (#1295)

Architecture

  • Unchanged — 0 containers · 1 contexts · 0 edges

Written by cca.canine.dev from the codebase's own history, inside the signed delivery this page is composed from.

Survey your own repository

anthropics/knowledge-work-plugins was measured the same way every project in this corpus was: the same rubric, at a pinned commit, with the result published in full. Point a surveyor at a repository you know and see whether you agree with it.

About this page

  • The score is its most recent published measurement, taken on 16 November 2026 at a pinned commit. It is not a live figure and does not change until the project is measured again.
  • Measured at commit e91a134584eb798bac7fb0379358006a2b63b965 — the exact code this score is about.
  • Scored under rubric-2026.11.4 — the same rubric and the same method as every other entry in this index.
  • Measured by Canine Code Analyzer (cca.canine.dev) using cca measure-2026.11.73+preprod-52de90b74216.