Skip to main content
rule CX Codex

skill-conventions — Claude Code rule: what it does, how to install

skill-conventions defines standards for workflow skills: separates human invocation from auto-triggers, governs state writes, and keeps the skill router in sync.

MIT ★ 2,966 updated 2026-09-29

Install into Cursor · Manually: put the files in place All methods and platforms ↓
.cursor/rules/skill-conventions.mdc
Open on GitHub

What skill-conventions does

This rule enforces design standards for agent skills. Every skill must declare its intent: either human-run via user-invocable: true for deliberate side-effect rituals, or auto-triggered based on a tight prompt description. If you cannot explain in one sentence when an action should fire on its own, it must stay human-run.

State changes are restricted to three explicit modes: content-addressed add with upsert, targeted update by identified key, and sequential append for trails or handoff logs. A skill that duplicates its own output upon re-running is treated as broken.

Skills move through three states: draft, promoted, and deprecated. Promoting a skill requires registering it in skills/skill-router/SKILL.md and running the deslop skill-file check to ensure instructions stay under one screen without duplicate lines.

What it helps with

  • Stop agent skills from auto-triggering on unrelated user prompts
  • Prevent duplicated entries when a skill runs more than once
  • Classify skills into deliberate human rituals versus automated actions
  • Keep the repository skill router synchronized during updates

Example prompts for the agent

  • Audit this new skill against skill-conventions before promoting it
  • Refine this skill description so the agent triggers it only for database migrations
  • Choose the right write semantics for this session-handoff skill

How to install skill-conventions

Manually: put the files in place

.cursor/rules/skill-conventions.mdc

Frontmatter: description, globs, alwaysApply

Step by step, with commands for each platform: Cursor rules: .mdc files, four modes and what replaced .cursorrules

Questions about skill-conventions

How to install skill-conventions in Claude Code?

Register the catalog with /plugin marketplace add rohitg00/pro-workflow, then install it by running /plugin install pro-workflow@pro-workflow. Alternatively, place the rule file directly at .claude/rules/skill-conventions.md.

What does skill-conventions do?

It guides skill authoring by enforcing trigger modes, safe duplicate-free write semantics, and documentation updates across the router index.

When should a skill use user-invocable: true?

Use this flag whenever an action produces side effects, acts as a deliberate session ritual, or lacks a single sentence describing exactly when it should run automatically.

Source text

skill-conventions.mdc · MIT
---
description: Conventions every pro-workflow skill follows - invocation intent, write semantics, buckets, and sync. A skill that gets these wrong misfires, duplicates state, or hides from the people who need it.
globs:
alwaysApply: true
---

# Skill Conventions

## Invocation intent - declare one

Every skill is either human-run or auto-triggered. Getting this wrong is the
most common failure: a deliberate skill that auto-fires interrupts, an
auto-skill with a vague description never fires.

- **Human-run** - deliberate, side-effectful, or a session ritual. Set
  `user-invocable: true`. The user reaches for it on purpose; it should not
  fire from a stray phrase. Examples: `wrap-up`, `safe-mode`, `agent-teams`,
  `plan-interrogate`, `auto-setup`, `tdd`, `domain-modeling`.
- **Auto-triggered** - the agent should reach for it from the prompt. No
  `user-invocable` flag; instead the description must be precise enough to
  fire on the right task and stay silent otherwise. A description that is
  vague under-fires; one that over-claims interrupts. Examples: `deslop`,
  `module-map`, `replay-learnings`, `bug-capture`, `wiki-query`.

Pick the mode from what the skill does, not from habit. If you cannot say in
one sentence when it should fire on its own, it is human-run. The full
per-skill classification lives in [`skills/skill-router/SKILL.md`](../skills/skill-router/SKILL.md).

## Write semantics - add vs update vs append

A skill that changes stored state (learnings, wiki pages, handoffs, issues)
must be explicit about which operation it performs, and must be safe to run
twice.

- **add** - create a new record. Derive its identity from content, not a fresh
  random id, so re-running the same input does not duplicate. If a record with
  that identity exists, reinforce or update it instead of adding a twin.
- **update** - modify an existing record addressed by its identity. Never
  blind-overwrite a record you did not locate first.
- **append** - add to an ordered log or list (a session handoff, a research
  trail) where every entry is meant to persist in sequence. Appends accrete;
  they never replace.

Rule of thumb: re-importable or re-derivable input uses content-addressed
`add` with upsert. One-off events use `append`. Corrections to an existing
fact use `update`. A skill that re-runs and duplicates its own output is
broken, not chatty.

## Buckets

Keep the promoted set clean. A skill is either shipped or it is not.

- **Promoted** - listed in the router, ready to use, carries a clear
  invocation intent. Only promoted skills appear in `skill-router`.
- **Draft** - work in progress, not yet in the router. Do not promote until
  it has a stable invocation intent and passes `deslop` skill-file mode.
- **Deprecated** - superseded; leave a one-line pointer to the replacement and
  drop it from the router.

## Sync obligations

- **Router** - adding, renaming, removing, or re-scoping a promoted skill
  updates `skills/skill-router/SKILL.md` in the same change.
- **Description** - the description is the auto-trigger surface. When behavior
  changes, re-tune it so it still fires on the right prompt.
- **Quality** - run `deslop` skill-file mode before promoting: no stale lines,
  no bloat past one screen, no dead sentences, no instruction stated twice, a
  clear anchor concept, and a declared invocation intent.

© Rohit Ghumare · MIT · rohitg00/pro-workflow

Similar IDE rules

All IDE rules for Agent setup: memory, context, orchestration →

From the same set83

The whole set →
domain-modeling domain-modeling builds the project's shared vocabulary and context boundaries before code gets written, so the agent stops paraphrasing domain terms. Leaves a CONTEXT.md glossary behind. CX Codex +1 ★ 2,966repo stars llm-gate llm-gate configures prompt and agent hooks in Claude Code to validate commit messages, stop dangerous terminal commands, and catch secret leaks before execution. CX Codex +1 ★ 2,966repo stars cost-tracker The cost-tracker skill helps you review Claude Code session costs, set budget checkpoints, and spot expensive work patterns. Use it when planning work across sessions. CX Codex +1 ★ 2,966repo stars reviewer reviewer — a subagent that reviews code line by line, reading actual files and citing every finding with exact quotes. Use before committing, during PR review, or after major changes. CX Codex ★ 2,966repo stars plan-interrogate The plan-interrogate skill probes a plan before implementation by mapping its decisions and asking about them one at a time. Use it to clarify unresolved design choices. CX Codex +1 ★ 2,966repo stars bug-capture bug-capture is a Claude Code skill that turns reported defects into GitHub issues using the project’s own terms. It activates after a conversational bug report, a QA pass, or a request to file an issue. CX Codex +1 ★ 2,966repo stars context-optimizer context-optimizer controls token consumption and frees context in Claude Code. Use it when agent sessions slow down, forget instructions, or approach budget limits. CX Codex +1 ★ 2,966repo stars deslop deslop trims unnecessary code from the current branch diff and checks SKILL.md files. Run it before committing or reviewing a skill for release. CX Codex +1 ★ 2,966repo stars

Project sponsors

Companies that keep this analytics open