modular skills for AI agents

Recent window: last 5.3 months (2026-04-30 → 2026-10-09), compared with the prior 5.3 months.

horizontal · 244 members · Data as of 2026-10-11

These products provide specialized, plug-and-play skills and capability libraries to enhance autonomous AI agents across niche domain tasks such as technical writing, presentation design, and reverse engineering. They are built for developers, prompt engineers, and AI practitioners looking to expand model competencies without building custom tooling from scratch. Unlike full-stack autonomous agent platforms, this cluster focuses on granular, task-specific modules and evaluation benchmarks designed to plug into existing agent frameworks.

Metrics

Stage: crowded
Recent count: 212
Prior count: 19
Total count: 244
Momentum: 300.00
Momentum (normalized): 1.00
Attention: 0.49
Crowding: 0.89
Low crowding: 0.11
Concentration: 0.84
Low concentration: 0.16
Opportunity: 0.44

Source split

github: 150 (0.71)
hn: 31 (0.15)
ph: 19 (0.09)
yc: 12 (0.06)

Dominant source: github · Divergence: 0.65

Similar niches

developer tools for coding agents (0.71)
tools and environments for coding agents (0.67)
ai agent development and runtime tools (0.66)
autonomous AI agent development tools (0.65)
agent frameworks and reinforcement learning (0.63)
ai agent skills and developer utilities (0.63)
developer infrastructure for AI agents (0.61)
AI agent infrastructure and operations (0.61)

Monthly trajectory

Pulled from real Hacker News comment threads on this niche's launches.

Most asked for

Ability to create skills/plugins for existing coding agents to generate lessons similarly (1)
Raised on Chestnut
Add /s4h command for skill discovery (1)
Raised on skills-for-humanity
Add embedded lab links to try concepts immediately (1)
Raised on AgentSwarms
Add more PlusCal examples as reference material (1)
Raised on TLA+ Workbench skill for coding agents (compat. with Vercel skills CLI)
Add prefix to all skills (s4h- or sfh-) (1)
Raised on skills-for-humanity
Add token cost per run and cost-benefit analysis to reports (1)
Raised on Agent-skills-eval
Add token count consumed per skill and detailed aggregate stats (1)
Raised on Agent-skills-eval
API token that uses Pro subscription pool instead of separate billing (1)
Raised on Quibbler

Concerns raised

'Software factory' terminology misleading for autonomous agents (1)
Raised on Benchmark your eng team's AI agent maturity in 5 minutes
Adding more prompting instructions isn't a real fix for AI errors (1)
Raised on QUALITY.md
After-message change does not establish causation (1)
Raised on A replayable A2A jury for tracing how agents influence decisions
AI struggles to understand test failures vs timeouts in e2e tests (1)
Raised on Showboat and Rodney, so agents can demo what they've built
AI-generated content is repetitive and hard to read (1)
Raised on AgentSwarms
Anthropic API key required in addition to Pro subscription (1)
Raised on Quibbler
Appears to be work-in-progress/incomplete (1)
Raised on Quibbler
Author credibility and whether work was AI-generated (1)
Raised on I RL-trained an agent that trains models with RL (for ~$1.3k)

Compared to

Claude Code (3)
Raised on Skill-up, Panel, Teaching AI agents to write better GraphQL
Codex (2)
Raised on Skill-up, Agent-skills-eval
AGENTS.md / CLAUDE.md files (1)
Raised on QUALITY.md
Airtable (1)
Raised on Panel
Anthropic (1)
Raised on A replayable A2A jury for tracing how agents influence decisions
Anthropic's MCP (Model Context Protocol) (1)
Raised on SkillGraph
AsciiDoc (1)
Raised on Showboat and Rodney, so agents can demo what they've built
AWS Bedrock (1)
Raised on Quibbler

Members

Name	Source	Upvotes ▲	Launched
TLA+ Workbench skill for coding agents (compat. with Vercel skills CLI)	HN	41	2026-02-22
agentic-dev-kit	GITHUB	42	2026-10-02
tubeai-skills	GITHUB	42	2026-09-24
easyplot	GITHUB	42	2026-09-23
novel-agent-studio	GITHUB	43	2026-09-09
r-doc	GITHUB	44	2026-09-14
thinkwithblack-skill	GITHUB	46	2026-10-09
fomo-cc	GITHUB	48	2026-09-29
skillscout	GITHUB	51	2026-09-30
Panel	HN	53	2026-09-15
stop-describing-ui	GITHUB	53	2026-10-11
Agent Draw: An agent draws while you talk, built on TLDraw	HN	53	2026-07-06
consultant	GITHUB	53	2026-09-14
skills	GITHUB	67	2026-10-08
philosopher-OKF	GITHUB	78	2026-10-08
awesome-embodied-agents	GITHUB	79	2026-10-11
Agent-skills-eval	HN	79	2026-05-07
lyric-writing-skills	GITHUB	83	2026-09-17
qisi-video-remix	GITHUB	85	2026-09-11
Showboat and Rodney, so agents can demo what they've built	HN	91	2026-02-10
cida	GITHUB	94	2026-09-19
REx-skill	GITHUB	96	2026-09-23
SureForge	GITHUB	100	2026-09-09
I RL-trained an agent that trains models with RL (for ~$1.3k)	HN	107	2026-07-14
system-design-trainer	GITHUB	110	2026-09-28
skills	GITHUB	112	2026-09-27
Quibbler	HN	114	2025-10-31
music-composition-skills	GITHUB	117	2026-09-17
system1-agents	GITHUB	120	2026-09-22
project-manager-skill	GITHUB	123	2026-09-30
bug-bounty-triage	GITHUB	124	2026-10-09
Agent Skills Leaderboard	HN	135	2026-01-20
ste-zh	GITHUB	145	2026-10-05
wenzi-xhs-agent-skills	GITHUB	152	2026-09-30
skills	GITHUB	160	2026-09-19
podcast-to-article	GITHUB	163	2026-10-07
Comma	GITHUB	171	2026-09-30
Cognition's SWE-2	PH	189	2026-09-13
skillbox	GITHUB	222	2026-09-17
luobo-ppt	GITHUB	260	2026-10-08
zh-tech-writing	GITHUB	302	2026-09-24
replica-skill	GITHUB	796	2026-10-03
yomiyasu	GITHUB	1371	2026-09-30
jianying-headless	GITHUB	1458	2026-09-15