aspiers/ai-config / .agents/skills/ids
ids
VerifiedCorrects output that refers to entities by bare identifier, restating it with a human-readable label beside every ID, and keeps that rule for the rest of the conversation. Use when the user invokes `/ids` or `$ids`, or complains that bead IDs, PR numbers, commit SHAs, or ticket keys were given without titles.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 1.8 KB |
SKILL.md
View on GitHub---
name: ids
description: >-
Corrects output that refers to entities by bare identifier, restating it
with a human-readable label beside every ID, and keeps that rule for the
rest of the conversation. Use when the user invokes `/ids` or `$ids`, or
complains that bead IDs, PR numbers, commit SHAs, or ticket keys were given
without titles.
---
# Label every ID
You referred to one or more entities (beads issues, GitHub issues, pull
requests, commits, tickets, files, jobs, etc.) by bare identifier alone. Bare
IDs are opaque to humans: `ai-config-a1b2c3` or `#4271` conveys nothing
without a lookup.
Restate what you just said, giving every entity reference a short
human-readable label alongside its ID. Look up the title if you don't already
have it. Examples of the required form:
- `ai-config-a1b2c3 (prefix parallel subagent labels with the bead ID)`
- `PR #4271 (fix race in worktree cleanup)`
- `fea0177 (feat(beads): prefix parallel subagent labels with the bead ID)`
Keep the label short: a title or a few-word summary, not a paragraph. The ID
stays, because it is what commands take as arguments; the label is what makes
the sentence legible.
**This applies for the rest of this conversation, not just to the message you
are correcting.** Every subsequent mention of an entity, in prose, in lists,
in summaries, in handoffs, must carry its label. The first mention in a
message always needs one; repeated mentions in the same immediate context may
use the bare ID once the label is established.
**Do not treat this invocation as a signal to record a new memory or amend
existing guidance.** Most likely the guidance already exists and the failure
was not following it. Adding more instructions on top of instructions you
already had does not fix that. Just fix the output and keep it fixed.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| planning-and-task-breakdownaddyosmani/agent-skillsBreaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large to start, when you need to estimate scope, or when parallel work is possible. | Stars: 119k | Updated | Claude CodeCodex | Verified | Install |
| screenpipethedotmack/claude-memSearch screen and audio history recorded by Screenpipe and optionally save selected context into claude-mem. Use when the user asks to recall desktop activity, a meeting, or something seen in another app through Screenpipe. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |
| contact-widgetnexu-io/open-designSelf-contained floating chat widget with welcome screen, social links, meeting button, and message input. Single HTML file, zero dependencies. | Stars: 108k | Updated | Claude CodeCodex | Verified | Install |
| meeting-notesnexu-io/open-designMeeting notes page — title bar with attendees, agenda checklist, decisions block, action items table with owners + dates, and a "next meeting" footer. Use when the brief mentions "meeting notes", "minutes", "1:1 notes", "all-hands recap", or "会议纪要". | Stars: 108k | Updated | Claude CodeCodex | Verified | Install |