菜单
Use when creating new skills, editing existing skills, or verifying skills work before deployment
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
SQLite migration rules for the Ghost codebase. MUST READ before writing or modifying any file in migrations/. Covers: table recreation patterns, column ordering, CHECK constraint changes, NOT NULL safety, and the validation checklist. A faulty migration that ships breaks the production daemon on startup with no recovery path short of manual DB surgery — these rules are non-negotiable.
Read when you need to browse, traverse, or query the knowledge system beyond basic knowledge_search — graph traversal, tag exploration, orphan detection, reference browsing, topic listing, or direct SQL access.
Import and update external content in the knowledge base — git repos, web crawls, documents (PDF, DOCX), and books (EPUB). Use when the OPERATOR wants persistent, searchable reference material from a git repository, website, document, or book, or when existing references may be stale and need refreshing.
Ghost's Lua scripting layer internals. MUST READ before modifying anything in src/scripting/, prompts/stdlib/, prompts/agents/*/agent.lua, or agent hook logic. Covers: ScriptHost VM lifecycle, sandbox, host globals, ctx bindings, nudge library, template module, custom tools, type stubs, and the PreTurnState contract.
Use when reading or changing GHOST configuration (providers, models, timing, compaction, services, any config.toml key), adding or switching LLM providers, answering questions about GHOST's own features or capabilities, a CLI tool is missing or "not found", services need starting/stopping/debugging, updating GHOST to a newer version, managing the Nix shell environment, or troubleshooting GHOST setup.
Triage and fix issues reported via Ghost's /feedback command. MUST READ when the user points you to a feedback folder, mentions a feedback report, or asks you to investigate a bug that happened during a GHOST session. Covers: retrieving feedback from remote servers, reading transcripts and debug request dumps, root-cause categorization, and the fix workflow.
| name | writing-skills |
| description | Use when creating new skills, editing existing skills, or verifying skills work before deployment |
| available | coding |
Writing skills IS Test-Driven Development applied to process documentation.
Skills live in the workspace skills/ directory as agentskills.io files.
You write test cases (pressure scenarios with agents), watch them fail (baseline behavior), write the skill (documentation), watch tests pass (agents comply), and refactor (close loopholes).
Core principle: If you didn't watch an agent fail without the skill, you don't know if the skill teaches the right thing.
A skill is a reference guide for proven techniques, patterns, or tools. Skills help future GHOST instances find and apply effective approaches.
Skills are: Reusable techniques, patterns, tools, reference guides
Skills are NOT: Narratives about how you solved a problem once
| TDD Concept | Skill Creation |
|---|---|
| Test case | Pressure scenario with agent |
| Production code | Skill document (skill.md) |
| Test fails (RED) | Agent violates rule without skill (baseline) |
| Test passes (GREEN) | Agent complies with skill present |
| Refactor | Close loopholes while maintaining compliance |
| Write test first | Run baseline scenario BEFORE writing skill |
| Watch it fail | Document exact rationalizations agent uses |
| Minimal code | Write skill addressing those specific violations |
| Watch it pass | Verify agent now complies |
| Refactor cycle | Find new rationalizations, plug, re-verify |
The entire skill creation process follows RED-GREEN-REFACTOR.
Create when:
Don't create for:
Concrete method with steps to follow (condition-based-waiting, root-cause-tracing)
Way of thinking about problems (flatten-with-flags, test-invariants)
API docs, syntax guides, tool documentation
skills/
skill-name/
skill.md # Main reference (required)
supporting-file.* # Only if needed
Flat namespace - all skills in one searchable namespace
Separate files for:
Keep inline:
Frontmatter (YAML):
name and descriptionname: Use letters, numbers, and hyphens only (no parentheses, special chars)description: Third-person, describes ONLY when to use (NOT what it does)
---
name: Skill-Name-With-Hyphens
description: Use when [specific triggering conditions and symptoms]
---
# Skill Name
## Overview
What is this? Core principle in 1-2 sentences.
## When to Use
[Small inline flowchart IF decision non-obvious]
Bullet list with SYMPTOMS and use cases When NOT to use
## Core Pattern (for techniques/patterns)
Before/after code comparison
## Quick Reference
Table or bullets for scanning common operations
## Implementation
Inline code for simple patterns Link to file for heavy reference or reusable tools
## Common Mistakes
What goes wrong + fixes
## Real-World Impact (optional)
Concrete results
Critical for discovery: Future GHOST instances need to FIND your skill
Purpose: GHOST reads description to decide which skills to load for a given task. Make it answer: "Should I read this skill right now?"
Format: Start with "Use when..." to focus on triggering conditions
CRITICAL: Description = When to Use, NOT What the Skill Does
The description should ONLY describe triggering conditions. Do NOT summarize the skill's process or workflow in the description.
Why this matters: Testing revealed that when a description summarizes the skill's workflow, the agent may follow the description instead of reading the full skill content. A description saying "code review between tasks" caused the agent to do ONE review, even though the skill's flowchart clearly showed TWO reviews (spec compliance then code quality).
When the description was changed to just "Use when executing implementation plans with independent tasks" (no workflow summary), the agent correctly read the flowchart and followed the two-stage review process.
The trap: Descriptions that summarize workflow create a shortcut the agent will take. The skill body becomes documentation the agent skips.
# BAD: Summarizes workflow - agent may follow this instead of reading skill
description: Use when executing plans - dispatches agent per task with code review between tasks
# BAD: Too much process detail
description: Use for TDD - write test first, watch it fail, write minimal code, refactor
# GOOD: Just triggering conditions, no workflow summary
description: Use when executing implementation plans with independent tasks in the current session
# GOOD: Triggering conditions only
description: Use when implementing any feature or bugfix, before writing implementation code
Content:
# BAD: Too abstract, vague, doesn't include when to use
description: For async testing
# BAD: First person
description: I can help you with async tests when they're flaky
# BAD: Mentions technology but skill isn't specific to it
description: Use when tests use setTimeout/sleep and are flaky
# GOOD: Starts with "Use when", describes problem, no workflow
description: Use when tests have race conditions, timing dependencies, or pass/fail inconsistently
# GOOD: Technology-specific skill with explicit trigger
description: Use when using React Router and handling authentication redirects
Use words the agent would search for:
Use active voice, verb-first:
creating-skills not skill-creationcondition-based-waiting not async-test-helpersGerunds (-ing) work well for processes:
creating-skills, testing-skills, debugging-with-logsProblem: Frequently-referenced skills load into EVERY conversation. Every token counts.
Target word counts:
Techniques:
Move details to tool help:
# BAD: Document all flags in skill.md
search-conversations supports --text, --both, --after DATE, --before DATE, --limit N
# GOOD: Reference --help
search-conversations supports multiple modes and filters. Run --help for details.
Use cross-references:
# BAD: Repeat workflow details
When searching, start agent with template... [20 lines of repeated instructions]
# GOOD: Reference other skill
Always use agents (50-100x context savings). **REQUIRED:** Read the other skill's
`skill.md` for workflow.
Compress examples:
# BAD: Verbose example (42 words)
the OPERATOR: "How did we handle authentication errors in React Router before?" You:
I'll search past conversations for React Router authentication patterns. [Start agent
with search query: "React Router authentication error handling 401"]
# GOOD: Minimal example (20 words)
OPERATOR: "How did we handle auth errors in React Router?" You: Searching... [Start
agent, synthesis]
Eliminate redundancy:
When writing documentation that references other skills:
Use skill name only, with explicit requirement markers:
**REQUIRED:** Read the \tdd` skill`**REQUIRED BACKGROUND:** You MUST understand the test-driven-development skillSee skills/testing/test-driven-development (unclear if required)Use flowcharts ONLY for:
Never use flowcharts for:
One excellent example beats many mediocre ones
Choose most relevant language:
Good example:
Don't:
You're good at porting - one great example is enough.
defense-in-depth/
skill.md # Everything inline
When: All content fits, no heavy reference needed
condition-based-waiting/
skill.md # Overview + patterns
example.ts # Working helpers to adapt
When: Tool is reusable code, not just narrative
pptx/
skill.md # Overview + workflows
pptxgenjs.md # 600 lines API reference
ooxml.md # 500 lines XML structure
scripts/ # Executable tools
When: Reference material too large for inline
NO SKILL WITHOUT A FAILING TEST FIRST
This applies to NEW skills AND EDITS to existing skills.
Write skill before testing? Delete it. Start over. Edit skill without testing? Same violation.
No exceptions:
Different skill types need different test approaches:
Test with:
Success criteria: Agent follows rule under maximum pressure
Test with:
Success criteria: Agent successfully applies technique to new scenario
Test with:
Success criteria: Agent correctly identifies when/how to apply pattern
Test with:
Success criteria: Agent finds and correctly applies reference information
| Excuse | Reality |
|---|---|
| "Skill is obviously clear" | Clear to you does not mean clear to other agents. Test it. |
| "It's just a reference" | References can have gaps, unclear sections. Test retrieval. |
| "Testing is overkill" | Untested skills have issues. Always. 15 min testing saves hours. |
| "I'll test if problems emerge" | Problems = agents can't use skill. Test BEFORE deploying. |
| "Too tedious to test" | Testing is less tedious than debugging bad skill in production. |
| "I'm confident it's good" | Overconfidence guarantees issues. Test anyway. |
| "Academic review is enough" | Reading does not equal using. Test application scenarios. |
| "No time to test" | Deploying untested skill wastes more time fixing it later. |
All of these mean: Test before deploying. No exceptions.
Skills that enforce discipline (like TDD) need to resist rationalization. Agents are smart and will find loopholes when under pressure.
Don't just state the rule - forbid specific workarounds:
Bad:
Write code before test? Delete it.
Good:
Write code before test? Delete it. Start over.
**No exceptions:**
- Don't keep it as "reference"
- Don't "adapt" it while writing tests
- Don't look at it
- Delete means delete
Add foundational principle early:
**Violating the letter of the rules is violating the spirit of the rules.**
This cuts off entire class of "I'm following the spirit" rationalizations.
Capture rationalizations from baseline testing. Every excuse agents make goes in the table:
| Excuse | Reality |
| -------------------------------- | ----------------------------------------------------------------------- |
| "Too simple to test" | Simple code breaks. Test takes 30 seconds. |
| "I'll test after" | Tests passing immediately prove nothing. |
| "Tests after achieve same goals" | Tests-after = "what does this do?" Tests-first = "what should this do?" |
Make it easy for agents to self-check when rationalizing:
## Red Flags - STOP and Start Over
- Code before test
- "I already manually tested it"
- "Tests after achieve the same purpose"
- "It's about spirit not ritual"
- "This is different because..."
**All of these mean: Delete code. Start over with TDD.**
Follow the TDD cycle:
Run pressure scenario with agent WITHOUT the skill. Document exact behavior:
This is "watch the test fail" - you must see what agents naturally do before writing the skill.
Write skill that addresses those specific rationalizations. Don't add extra content for hypothetical cases.
Run same scenarios WITH skill. Agent should now comply.
Agent found new rationalization? Add explicit counter. Re-test until bulletproof.
"In session 2025-10-03, we found empty projectDir caused..." Why bad: Too specific, not reusable
example-js.js, example-py.py, example-go.go Why bad: Mediocre quality, maintenance burden
step1 [label="import fs"];
step2 [label="read file"];
Why bad: Can't copy-paste, hard to read
helper1, helper2, step3, pattern4 Why bad: Labels should have semantic meaning
After writing ANY skill, you MUST STOP and complete the deployment process.
Do NOT:
The deployment checklist below is MANDATORY for EACH skill.
Deploying untested skills = deploying untested code. It's a violation of quality standards.
IMPORTANT: Use todo(action: "plan", ...) to create todos for EACH checklist item
below.
RED Phase - Write Failing Test:
GREEN Phase - Write Minimal Skill:
REFACTOR Phase - Close Loopholes:
Quality Checks:
Deployment:
How future GHOST finds your skill:
Optimize for this flow - put searchable terms early and often.
best-practices.md extra — Conciseness,
structure, progressive disclosure, evaluation-driven developmentpersuasion-principles.md extra — Psychology of
effective skill design (authority, commitment, scarcity)testing-skills-with-subagents.md extra —
Pressure scenarios, rationalization tables, bulletproofingCreating skills IS TDD for process documentation.
Same Iron Law: No skill without failing test first. Same cycle: RED (baseline), GREEN (write skill), REFACTOR (close loopholes). Same benefits: Better quality, fewer surprises, bulletproof results.
If you follow TDD for code, follow it for skills. It's the same discipline applied to documentation.