Ejecuta cualquier Skill en Manus
con un clic

Ejecuta cualquier Skill en Manus con un clic

np-labeling

Estrellas3

Forks0

Actualizado27 de abril de 2026 a las 21:45

Use when the agent needs to add or remove labels on an existing `np` (nitpicking) issue (often across multiple issues at once), or inspect the workspace's label vocabulary for drift or to ground a new label key. Triggers on prompts like "add foo:bar to all issues about X", "remove the kind:bug label from FOO-a3bxr", "what labels are in use", "tag these issues with sprint:2026-w17". Does not cover label-based filtering of the ready queue (use `np-finding-work`) or label-based filtering during issue lookup (use `np-reading-issues`).

Instalación

Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.

Ejecutar en Manus

Fuente

pinkhop

pinkhop/nitpicking

Abrir repositorio de GitHub Ver repositorios del creador

Descarga

Ejecutar en Manus

Ocupaciones relacionadasSOC

Basado en la clasificación ocupacional SOC

Desarrolladores de softwareOcupaciones informáticas y matemáticas·SOC 15-1252

SKILL.md

readonly

Más de este repositorio

mismo repositorio

np-commenting

pinkhop/nitpicking

Use when the agent needs to add a comment to an `np` (nitpicking) issue — to record reasoning, capture an investigation finding, leave a handoff note, document a trade-off considered, or annotate any issue (including closed ones). Triggers on prompts like "add a comment to FOO-a3bxr saying ...", "leave a note on the issue", "record that we tried X", "comment on FOO-12345 that ...". Comments do not require a claim.

2026-04-273

np-creating-issues

pinkhop/nitpicking

Use when the agent needs to file a new `np` (nitpicking) issue — an incidental discovery while working on something else, a child task or sub-epic when decomposing a parent epic, a deferred follow-up, or any new task or epic the user asks to be created. Triggers on prompts like "create an issue for ...", "file a follow-up", "decompose this epic into ...", "add a child task under FOO-c4npt".

2026-04-273

np-finding-work

pinkhop/nitpicking

Use when the agent needs to pick up the next ready issue from the `np` (nitpicking) tracker, claim a specific issue by ID, browse the ready queue, or filter ready work by label or role (e.g., "claim the next ready bug", "pick up the next task in area:auth", "claim FOO-a3bxr"). Does not cover reading the claimed issue's content or finishing work.

2026-04-273

np-finishing-work

pinkhop/nitpicking

Use when the agent has a claimed `np` (nitpicking) issue and needs to close it as complete, release the claim without changing the issue's state, or defer the issue for later. Triggers on prompts like "close the issue", "mark it done", "release the claim", "defer this for now". Does not cover reopening or undeferring (escape-hatch via `np-help-discipline`); commenting is handled separately by `np-commenting`.

2026-04-273

np-help-discipline

pinkhop/nitpicking

Use when about to invoke an `np` (nitpicking) command, subcommand, or flag that has not been verified in the current session, or when unsure whether a flag or subcommand exists. Also use as the escape hatch for any `np` activity not covered by another skill (e.g., `np issue reopen`, `np issue undefer`, `np epic close-completed`, `np admin backup`, `np agent name`, `np json update`).

2026-04-273

np-managing-relationships

pinkhop/nitpicking

Use when the agent needs to express, remove, or list a dependency or informational link between two `np` (nitpicking) issues — adding `blocked_by` because one issue cannot proceed until another finishes, adding `refs` for a "see also" pointer, removing a relationship that no longer applies, or listing the workspace's relationships at a glance. Triggers on prompts like "mark FOO-a3bxr as blocked by FOO-c4npt", "FOO-12345 references FOO-67890", "remove the blocker", "show me the blocking chains".

2026-04-273

name

np-labeling

description

np-labeling

Overview

Labels are key:value metadata attached to issues. They make backlog-scanning faster, enable filtering and routing, and can capture lightweight workflow markers. This skill covers modifying labels on existing issues and inspecting the workspace vocabulary.

Author identity and claim

Adding or removing a label is a mutation. It requires the active claim ID for the issue, and --author is implicit through the claim:

$ np label add kind:bug --claim <CID>
$ np label remove kind:bug --claim <CID>

If the agent does not already hold a claim, claim the issue first (see np-finding-work), then label, then transition (see np-finishing-work). For a labeling-only task, releasing the claim immediately after with np issue release --claim <CID> keeps the issue's state unchanged.

The claim ID is a bearer credential. Never paste it into a comment, commit message, or shared log.

np label list-all is read-only and needs no claim or author flag.

Adding a label

$ np label add kind:bug --claim a4dace30e46eb1ec14019c79a59c6b27
$ np label add area:auth --claim a4dace30e46eb1ec14019c79a59c6b27

A label is a single key:value argument. Add multiple labels with multiple invocations.

Removing a label

np label remove takes the key, not the full key:value:

$ np label remove kind --claim a4dace30e46eb1ec14019c79a59c6b27

That removes whatever value was stored under kind on this issue. If the exact remove syntax is unfamiliar, run np label remove --help to confirm.

Applying a label across multiple issues

The user often asks for labeling across a set ("add task-group:auth-overhaul to all issues about auth"). Find the issues first (np-reading-issues), then for each one: claim, label, release.

# 1. Find the targets (np-reading-issues)
$ np list --label area:auth --state open --json

# 2. For each target ID:
$ np claim FOO-a3bxr --author blue-seal-echo
# capture the returned claim ID
$ np label add task-group:auth-overhaul --claim <CID>
$ np issue release --claim <CID>

Be deliberate about scope. Confirm with the user before sweeping a label across many issues.

Inspecting the workspace vocabulary

Before introducing a new key, see what is already in use:

$ np label list-all
KEY       POPULAR VALUES
area      auth (12), cli (8), storage (5)
kind      bug (19), feature (11), docs (8)
risk      low (10), med (4), high (2)

This is also the best drift detector. If both kind:bug and kind:Bug show up, the convention has split.

Naming conventions

Defer to project rules and persistent memory for label naming standards (key vocabulary, value formatting). The user often documents these in CLAUDE.md, a workspace conventions issue, or saved memory.

If no guidance is present, default to lowercase, hyphenated keys and values:

kind:bug, kind:feature, kind:enhancement
area:auth, area:billing-api
task-group:auth-overhaul, sprint:2026-w17

A key must be 1–64 ASCII printable bytes; the first character must be an ASCII letter or underscore. Values are also ASCII printable, no whitespace.

What this skill does not cover

Filtering the ready queue by label (np ready --label …, np claim ready --label …) — use np-finding-work.
Filtering issue lookups by label (np list --label …, np issue search --label …) — use np-reading-issues.
Attaching labels at issue-creation time — use np-creating-issues (the labels field on np json create).

Common mistakes

Passing key:value to np label remove. Remove takes the key only.
Forgetting --claim on add or remove. Both require an active claim on the issue.
Inventing a new key when one exists. Run np label list-all first; reuse existing keys to keep filtering reliable.
Casing drift. kind:Bug and kind:bug are different labels. Stick to one convention per workspace.