Best Productivity Skills for Claude Code
Skills for task planning, verification, memory, and workflow automation. Evaluated on six dimensions — the full scorecard with written rationale is on every detail page.
The best productivity skills for Claude Code, ranked by six-dimension evaluation: academy-guide (9.6/10), threejs-world-generation (9.6/10), linkedin-reply-handler (9.5/10), ponytail-audit (9.5/10), jira (9.5/10). Every score has published rationale. How we score →
Install the top 3 in one line
curl -fsSL https://skill123.me/install/academy-guide.sh | bash
curl -fsSL https://skill123.me/install/threejs-world-generation.sh | bash
curl -fsSL https://skill123.me/install/linkedin-reply-handler.sh | bash
Verified evaluation, one-line install. Or tell your agent: install the productivity skill from skill123.me.
Stop and check this skill before finishing any reply to a question about how to use Claude or a C…
Anthropic-authored Claude Academy recommendation skill; exemplary trigger design, hallucination guards, and untrusted-catalog handling with no security concerns.
Build deterministic, editable, free-viewpoint Three.js worlds from text or structured briefs. Use…
Outstanding orchestration skill: explicit When-Not, fidelity tiers, bounded refinement loops, quality gates and check-based verification; only minor oddity is the agents/openai.yaml interface file.
Draft a reply to one LinkedIn comment from its URL, or sweep a whole thread from just the post UR…
Best-in-batch execution design: single-comment and whole-thread sweep modes, correct 2-level parentComment flattening with per-entry double-check, transparent filter summary, batch approval, sequential publishing with 429 stop rule, and sweep-wide prompt-injection defenses. Fetching is no-cookie public Apify only.
Whole-repo audit for over-engineering. Like ponytail-review, but scans the entire codebase instea…
Read, search, draft, create, or update Jira work. Use only with explicit Jira or Atlassian contex…
After you give a substantive answer or draft that the user may act on — advice or recommendations…
Exemplary behavioral skill: exhaustive What/When/When-Not trigger description, precise output contract, rich boundary rules, zero security surface; only minor verbosity in exclusion cases.
Use when configuring Django to store static and media files on AWS S3 with django-storages. Invok…
Outstanding narrowly-scoped specialist: correct Django 4.2-6.0 STORAGES guidance, an 8-item grep-based audit checklist for existing configs, env-only credentials, and mocked-S3 test strategy; only lacks an explicit When-Not boundary.
Interview the user for the raw material their posts are made of. Builds a lasting Story Bank of r…
Conversational Story Bank builder with two modes (broad bank, focused post spine), resumable thin-section tracking, one-question-at-a-time discipline, explicit off-limits memory, and hard never-invent rules. No scripts, no network; even warns that the personal bank file should be gitignored.
Create and edit JSON Canvas files (.canvas) with nodes, edges, groups, and connections. Use when …
Outstanding generator skill: four concrete workflows each ending in a validation step, an 8-point checklist, layout guidance, and offloaded examples; only weakness is absent When-Not boundary.
Use when building Django web applications or REST APIs with Django REST Framework. Invoke when wo…
Excellent Django/DRF specialist: six-step workflow with migration and endpoint verification before auth, complete model-serializer-viewset-test example, five load-when references; only missing an explicit When-Not trigger boundary.
Score comparison
How the top 10 compare across the six evaluation dimensions (0–10). Full written rationale for every score is on each skill's page.
| Skill | Overall | Trigger | Structure | Workflow | Content | Engineering | Security |
|---|---|---|---|---|---|---|---|
| academy-guide | 9.6 | 9.5 | 9.3 | 9.2 | 10.0 | 10.0 | 10.0 |
| threejs-world-generation | 9.6 | 10.0 | 9.3 | 9.2 | 9.0 | 10.0 | 10.0 |
| linkedin-reply-handler | 9.5 | 9.5 | 9.3 | 9.6 | 10.0 | 9.0 | 9.5 |
| ponytail-audit | 9.5 | 9.0 | 9.5 | 9.5 | 9.5 | 9.0 | 10.0 |
| jira | 9.5 | 9.5 | 9.0 | 9.5 | 9.5 | 9.0 | 10.0 |
| discernment-nudge | 9.4 | 9.5 | 9.3 | 8.8 | 9.0 | 10.0 | 10.0 |
| django-storages-s3 | 9.4 | 8.5 | 9.3 | 9.2 | 10.0 | 10.0 | 10.0 |
| linkedin-interviewer | 9.4 | 9.0 | 9.3 | 9.2 | 10.0 | 9.0 | 10.0 |
| json-canvas | 9.3 | 7.0 | 10.0 | 9.6 | 10.0 | 10.0 | 10.0 |
| django-expert | 9.3 | 8.5 | 9.3 | 8.8 | 10.0 | 10.0 | 10.0 |
FAQ
What is a Claude Code productivity skill?
A package that teaches your agent a working discipline — planning before execution, verifying before claiming done, structuring multi-step tasks.
What does verification-before-completion do?
It stops your agent from saying "done" without evidence. One of the highest-leverage habits you can install — most AI mistakes happen in the gap between claimed and actual completion.
Are these skills hard to set up?
No — one-line install, no external accounts, no API keys. They're pure methodology encoded as instructions.
Every skill here was scored on the same six-dimension rubric — the full scorecard with written rationale is on each skill's page. see all Productivity skills.