write-skill
Author a new agent skill in this repo following progressive-disclosure, trigger-rich-description, and script-over-prose principles. Use when the user asks to "write a skill", "add a skill", "create a new skill", or scaffold a SKILL.md. Targets the `npx skills` layout (top-level `skills/<name>/SKILL.md`).
What this skill does
# write-skill
Scaffold a new skill under `skills/<name>/` that is short, trigger-rich, and self-contained.
## Steps
1. **Clarify the skill** — ask the user, in one round:
- What capability does it provide? (one sentence)
- What concrete user phrases or contexts should trigger it?
- Are there contexts where it should *not* trigger? (negative triggers)
- Does it need executable scripts, or are instructions enough?
- Is it cross-agent (Claude Code + Codex + Cursor) or Claude-Code-only?
2. **Pick a name** — kebab-case, verb-or-noun, unique within `skills/`. Check with `ls skills/`.
3. **Draft `skills/<name>/SKILL.md`** using the template below. Cap at ~100 lines.
4. **Add scripts only if deterministic** — see "When to add scripts".
5. **Update `README.md`** — add a one-line entry under "## Skills" pointing to the new SKILL.md.
6. **Verify** with the checklist at the bottom. Do not commit unless asked.
## SKILL.md template
```md
---
name: <kebab-case-name>
description: <Sentence 1: what it does, third person.> Use when <explicit triggers: phrases, file types, contexts>. Do NOT use <negative triggers, if topic is broad>.
---
# <name>
<One-line purpose.>
## Quick start
<Smallest working example — command or invocation.>
## Steps
1. <Numbered, imperative.>
2. <…>
## Notes
- <Hard rules: "never do X", "always Y".>
- <Argument handling, if any.>
```
## Description rules (the highest-leverage part)
The description is the *only* thing the agent sees when picking skills. Get it right.
- Max ~1024 chars; aim for 1–3 sentences.
- Third person, present tense.
- Sentence 1: concrete capability ("Search an Obsidian vault…", not "Helps with notes").
- Sentence 2: `Use when …` — list real trigger phrases, file types, or contexts.
- If the topic is broad (macOS, git, "review"), add `Do NOT use …` to suppress false positives. See `m-cli/SKILL.md` for a strong example.
- No marketing words ("powerful", "comprehensive"). No emojis.
## When to add scripts
Add a `scripts/` subdirectory when:
- The operation is deterministic (a query, a formatter, an API call shape).
- The agent would otherwise regenerate the same code each invocation.
- Errors need explicit handling that prose can't enforce.
Then SKILL.md becomes a *menu of script invocations* with one example per command (see `youtube-transcript/` and `obsidian-vault-search/` in this repo, or agent-stuff's `web-browser`).
## When to split files
If SKILL.md would exceed ~100 lines, split:
```
skills/<name>/
SKILL.md # entry: triggers, quick start, steps
REFERENCE.md # detailed rules, long lists, edge cases
EXAMPLES.md # worked examples
scripts/ # deterministic helpers
```
Link one level deep from SKILL.md (`See [REFERENCE.md](REFERENCE.md)`). Don't nest further — the agent loads files lazily and deep chains defeat that.
## Cross-agent portability
This repo is consumed via `npx skills`, which targets multiple agents.
- `allowed-tools:` in frontmatter is Claude-Code-only. Other agents ignore it. Use it when you want to constrain Claude, but don't rely on it for correctness.
- Hooks and `context: fork` are Claude-only — note in the description if a skill requires them.
- If the skill is platform-specific (macOS, local sqlite, a specific CLI), say so in sentence 1 of the description.
## Review checklist
- [ ] Name is kebab-case and unique in `skills/`.
- [ ] Description has explicit `Use when …` triggers.
- [ ] Description has `Do NOT use …` if the topic is broad.
- [ ] SKILL.md is ≤100 lines (else split into REFERENCE.md).
- [ ] No time-sensitive claims ("as of 2025…").
- [ ] Concrete examples, not abstractions.
- [ ] Scripts colocated under `scripts/` and invoked by SKILL.md, not duplicated as prose.
- [ ] `README.md` updated with a one-line entry.
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.