Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/gleanwork/claude-plugins/skill-creation-guidenpx skills add gleanwork/claude-plugins --skill skill-creation-guidegit clone --depth 1 https://github.com/gleanwork/claude-pluginsWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00136 | $0.01169 |
| Opus 5 | $0.00068 | $0.00584 |
| Sonnet 5 | $0.00027 | $0.00234 |
| Haiku 4.5 | $0.00014 | $0.00117 |
Grade A, and why
skill-creation-guide scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
1 near-identical copy found in the catalogue:
- skill-creation-guide — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Creation Guide
Help the user author effective agent skills — single SKILL.md files (in the
open Agent Skills format) that auto-trigger by context and provide specialized
guidance. The format is shared across hosts (Claude Code, Cursor, and others);
only the install location differs.
This skill covers three things: deciding whether a skill is worth creating, discovering candidates from the user's work, and generating a well-formed skill.
BE SKEPTICAL
Not every idea makes a good skill. Evaluate before creating:
Recurrence — Will this be used repeatedly?
- ✅ Weekly or more → create
- ⚠️ Monthly → reconsider, may not be worth it
- ❌ One-time → skip
Automation — Can it actually be automated?
- ✅ Clear, repeatable process → create
- ⚠️ Needs significant judgment each time → reconsider
- ❌ Too context-dependent, each case unique → skip
Value — Is the cumulative time saved significant?
- ✅ Meaningful savings per use → create
- ❌ Slower to invoke than doing manually → skip
Duplication — Does it already exist?
- ✅ Novel, unaddressed need → create
- ⚠️ Similar to an existing skill → enhance that instead
- ❌ Already covered → skip
Don't create skills for one-time events, tasks that differ fundamentally each time, sub-30-second manual tasks, or things the user will forget exist.
Workflow A — Discover opportunities
When the user asks what they should automate, analyze their work patterns first.
Requires the Glean MCP tools. If they aren't visible, ask the user to set up
Glean by prompting the harness (for example, Set up Glean for me).
- Gather context with Glean:
memory(roles, responsibilities, active projects),user_activity(past ~2 weeks), andsearchfor process docs ("runbook OR checklist OR process owner:me"). - Spawn the
work-pattern-analyzeragent to identify repeated queries, frequent contexts, workflow sequences, and manual processes — and to vet each candidate against the recurrence/value tests above. - Present vetted recommendations grouped by cumulative value, and show the rejected candidates with reasons. A few high-quality candidates beat many weak ones — "no automatable patterns" is a valid outcome.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 120 lines · 136 tokens per session scan A 5722a8039076
skill-creation-guide is a skill published in the GitHub repository gleanwork/claude-plugins (25 stars, last pushed 12d ago), licensed MIT. It adds 136 tokens to every session and 1,169 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
mcporter
List, auth, and call MCP servers/tools from the terminal.
agent-messaging
Send and receive cryptographically signed messages between AI agents using the Agent Messaging Protocol (AMP). Use when the user asks to "send a message to an agent", "check agent inbox", "message another agent", "reply to a message", "notify an agent", or any inter-agent communication task.
📝 任务完成后归档
重要提醒: 每次完成复杂调试或开发任务后，主动执行此流程！ 将学到的经验归档为 skill，供以后参考。不要等用户提醒。.
oracle
Best practices for using the oracle CLI (prompt + file bundling, engines, sessions, and file attachment patterns).
agent-mode
Unified tool for managing agent LLM modes (add, remove, update, list, switch).
agento11y-prod-setup
Sets up production evaluation and guardrails for a DEPLOYED AI agent in Grafana Agent Observability, grounded in the agent's own code and its real ingested traffic. The judgment layer on top of the agento11y skill: it reads the agent's source (system prompt, tools, entrypoint) AND samples its live traffic via gcx…