New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Ad Task

by CorridorTech in CorridorTech/PoseCap

Draft a new task tracking file at doc/tasks/NNNN-<short-slug.md, using a checkbox-toggle + append-only-Notes format optimized for LLM editing.

Apache-2.0Auto-check: notesProduct & Project Management

Install Ad Task

skills CLI
$ npx skills add CorridorTech/PoseCap --skill ad-task -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install CorridorTech/PoseCap ad-task --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/CorridorTech/PoseCap.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/ad-task .claude/skills/ad-task && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
ad-task
GitHub stars
224
Token cost
~1.5k tokens
SKILL.md length
607 words
Files
1
Skills in repo
15
Repo updated
First seen
Licence
Apache-2.0

At a glance

Draft a new task tracking file at doc/tasks/NNNN-<short-slug.md, using a checkbox-toggle + append-only-Notes format optimized for LLM editing.

  • Works in 4 steps: Determine NNNN and slug → Interview to fill → Write the file → …
  • The user wants to create
  • SKILL.md covers Step 1 — Determine NNNN and slug, Step 2 — Interview to fill, Interview UX and Step 3 — Write the file, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Ad Task is an agent skill from CorridorTech/PoseCap. Draft a new task tracking file at doc/tasks/NNNN-<short-slug.md, using a checkbox-toggle + append-only-Notes format optimized for LLM editing. Use when the user wants to create, draft, scaffold, or open a task, ticket, work item, or backlog entry tracked in the repo. Status starts at proposed; the file is the source of truth, not a board.

Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Product & Project Management, covering Task management. The licence is Apache-2.0.

When your agent uses it

  • The user wants to create
  • Backlog entry tracked in the repo

Example prompts

  • “/ad-task”

Requirements

  • Pre-approved tools (allowed-tools): Read, Write, Glob, Bash

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Determine NNNN and slug
  2. Interview to fill
  3. Write the file
  4. Editing guidance for later turns

What it can do on your machine

Read from SKILL.md and the folder at commit 626701b. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read
    • Write
    • Glob
    • Bash

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Ad Task loads about 1.5k tokens when it runs. Until then it costs about 87 tokens; SKILL.md has 607 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~87
When it runs · the whole SKILL.md, loaded when a task matches
~1.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Read, Write, Glob, Bash

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from CorridorTech/PoseCap at commit 626701b, republished under its Apache-2.0 licence (© CorridorTech). 607 words, ~1,493 tokens.

Download SKILL.mdSave it as .claude/skills/ad-task/SKILL.md (or your agent's skills folder).
name
ad-task
description
Draft a new task tracking file at doc/tasks/NNNN-<short-slug>.md, using a checkbox-toggle + append-only-Notes format optimized for LLM editing. Use when the user wants to create, draft, scaffold, or open a task, ticket, work item, or backlog entry tracked in the repo. Status starts at proposed; the file is the source of truth, not a board.
allowed-tools
Read, Write, Glob, Bash
summary
Draft a new task at `doc/tasks/NNNN-<slug>.md`.

/ad-task

Drafts doc/tasks/<NNNN>-<short-slug>.md for one tracked task. Format chosen so status changes via single checkbox toggles and Notes is append-only — cheap, reviewable, idempotent edits.

Step 1 — Determine NNNN and slug

List doc/tasks/. NNNN = next available 4-digit number after the highest existing (mirrors the ADR convention). If doc/tasks/ does not exist, create it; start at 0001. Slug: kebab-case, ≤6 words, derived from the user's task title.

Step 2 — Interview to fill

Ask one question per missing field, in this order:

  • Context: why this task exists, what problem it solves, any assumption being tested.
  • Acceptance Criteria: measurable conditions. Each is a checkbox; pass/fail must be observable, not aspirational ("loads in under 2s", not "fast enough").
  • Plan: concrete sequential steps with file paths where applicable. Each is a checkbox.
  • Owner: ask.
  • Execution: AFK when the task is specified enough for an agent to execute with bounded context and disjoint write scope; HITL when it needs human judgment, taste, external access, or frequent back-and-forth.
  • Spec ref: ask; leave blank when no spec drives this task. When a feature spec exists at doc/specs/NNNN-<slug>.md, link it here so the spec's Related → Tasks list reciprocates.
  • Board ref: ask; leave blank if solo work.

Status starts at proposed. Created: today, ISO format. Notes: empty (filled during execution). Definition of Done section: copy verbatim from the template.

Do not invent values. When the user does not know something, leave <TODO> and ask. Stop after writing the file — do not start work.

Interview UX

When the host exposes AskUserQuestion, use it for multi-choice prompts (status, owner selection, Spec-ref pick from existing doc/specs/) and for confirmation gates with non-trivial branching. Inline text questions are the fallback only when the host lacks a structured-prompt primitive (Codex). Single card per multi-choice gate beats chained text questions.

Step 3 — Write the file

Path: doc/tasks/<NNNN>-<short-slug>.md. Use the template below.

Step 4 — Editing guidance for later turns

When the user later works on the task, edit the file by:

  • Toggling checkboxes (- [ ] → - [x]).
  • Appending to Notes (date each entry, ### YYYY-MM-DD).
  • Never rewriting existing sections.

Status flips to done only when every Acceptance Criterion and every Definition of Done item is checked.

A checkbox is checked only after everything it names has actually happened — never in anticipation. Split a bundled step (e.g. "open PR; merge on CI green") into separate items when its parts complete at different moments; a checked box claiming an unfinished step is a false record.

Show full SKILL.md (206 more words)Show less

Template — doc/tasks/NNNN-<slug>.md

markdown
# Task `<NNNN>`: `<short imperative title>`

**Status:** `<proposed | in-progress | blocked | done>`
**Created:** `<YYYY-MM-DD>`
**Owner:** `<name or role>`
**Execution:** `<AFK | HITL>`
**Spec ref:** `<doc/specs/NNNN-<slug>.md or SPEC-NNNN — blank when no spec drives this task>`
**Board ref:** `<external ticket URL or ID — blank for solo work>`

## Context

`<Why this task exists. What problem it solves. Any assumption being tested.>`

## Acceptance Criteria

Verifiable conditions. Each as a checkbox so progress is point-editable.

- [ ] `<criterion 1>`
- [ ] `<criterion 2>`
- [ ] `<criterion 3>`

## Plan

Concrete sequential steps. Each as a checkbox. Reference file paths where applicable.

- [ ] `<step 1: action with file path if applicable>`
- [ ] `<step 2>`
- [ ] `<step 3>`

## Notes

Append-only log. Date each entry. Never rewrite past entries.

### `<YYYY-MM-DD>`

`<observation, decision, blocker, learning>`

## Definition of Done

All Acceptance Criteria checked, plus:

- [ ] Local tests pass (or N/A documented in Notes)
- [ ] Code review completed (human or fresh-context reviewer per WORKFLOW §10)
- [ ] No orphan `TODO`/`FIXME` introduced
- [ ] Status updated to `done` and Notes log closes the task

Output contract

A single new file at doc/tasks/<NNNN>-<short-slug>.md. Status proposed. Notes empty. No existing tasks modified. No invented values.

Task files are decision-record artifacts and are exempt from the no-dates rule (Documentation Discipline §2): the **Created:** field anchors the task in time and the append-only Notes log is dated per entry by design. The remaining Documentation Discipline rules (WORKFLOW.md §2) apply at write time:

  • No emoji anywhere in the file.
  • Context is the business-context-first section — why this task exists and what would break without it before Acceptance Criteria.
  • One scope: one task per file. If the user's request implies multiple deliverables, ask which to write first; the others become follow-up tasks.
  • No speculation. Acceptance criteria must be measurable; do not list aspirational items ("loads in under 2s", not "fast enough").
  • Notes is append-only and dated per entry — that is the auditability primitive, not a violation of Rule 2.

Next

  • Implement. Toggle Acceptance Criteria checkboxes and append to Notes as work lands.
  • /ad-review main..HEAD (or current scope) before merge — the task DoD requires a fresh-context §10 review.
  • Flip Status to done once every Acceptance Criterion and Definition-of-Done item is checked.
  • If the task implements a spec, the spec's Related → Tasks list should reciprocate the link.

© CorridorTech, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/ad-task of CorridorTech/PoseCap.

Open the folder on GitHubat commit 626701b

Compare with similar skills

Ad Task next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Ad Task compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Ad Task this skillCorridorTech/PoseCap224—~1.5kAutomated safety check: NotesApache-2.0
Ad Taskalexandremendoncaalvaro/CorridorKey-Runtime7551 repos~1.3kAutomated safety check: PassCustom licence
Backlog Groomingforcedotcom/salesforcedx-vscode1k—~1.5kAutomated safety check: PassBSD-3-Clause
Kanban Mdantopolskiy/kanban-md223—~4kAutomated safety check: PassMIT
Herdr BoardnelsonPires5/herdr-board170—~4.6kAutomated safety check: PassNone
Triagejoa23/linear-cli144—~699Automated safety check: PassMIT

Similar skills

  • Ad Task

    alexandremendoncaalvaro/CorridorKey-Runtime

    Draft a new task tracking file at doc/tasks/NNNN-<short-slug.md, using a checkbox-toggle + append-only-Notes format optimized for LLM editing.

    755 GitHub starsUsed in 1 repo~1.3k tokens
    Product & Project ManagementAuto-check passed

  • Backlog Grooming

    forcedotcom/salesforcedx-vscode

    Triage the team's open GUS backlog — propose closing done-but-open work items (with code/test citations), flag under-specified items for grilling, catch wrong-epic / orphan / unpointed / dead-link…

    1k GitHub stars~1.5k tokensUpdated today
    Product & Project ManagementAuto-check passed

  • Kanban Md

    antopolskiy/kanban-md

    Manage project tasks using kanban-md, a file-based kanban board CLI.

    223 GitHub stars~4k tokensUpdated 2 days ago
    Productivity & AutomationAuto-check passed

  • Herdr Board

    nelsonPires5/herdr-board

    Interact with the herdr-board kanban from inside an agent run or an interactive session.

    170 GitHub stars~4.6k tokensUpdated yesterday
    Productivity & AutomationAuto-check passed

  • Triage

    joa23/linear-cli

    Triage and prioritize Linear backlog issues using the linear CLI.

    144 GitHub stars~699 tokensUpdated 24 days ago
    Product & Project ManagementAuto-check passed

  • Tidy

    croffasia/itsaplan

    Simplifies and refines code for clarity, consistency, and maintainability while preserving all functionality.

    903 GitHub stars~2.8k tokensUpdated today
    Product & Project ManagementAuto-check passed

More from CorridorTech/PoseCap

All 15 skills in this repo

  • Ad Adr

    CorridorTech/PoseCap

    Draft a new ADR (Architecture Decision Record) at doc/adr/NNNN-<short-title.md, using Michael Nygard's Context/Decision/Consequences/Alternatives pattern.

    224 GitHub stars~1k tokensUpdated yesterday
    Auto-check: notes

  • Ad Architecture

    CorridorTech/PoseCap

    Generate ARCHITECTURE.md at the repo root by scanning the code first, pre-filling layers/patterns/observability/deployment from observed signals, then asking only the genuine gaps.

    224 GitHub stars~1.5k tokensUpdated yesterday
    Auto-check: notes

  • Ad Archive

    CorridorTech/PoseCap

    Hard-delete completed plan files (tasks Status:done, specs Status:shipped, PRDs Status:superseded, ADRs Status:superseded or deprecated) via git rm, leaving git history as the only ledger.

    224 GitHub stars~1.9k tokensUpdated yesterday
    Auto-check: notes

  • Ad Drift

    CorridorTech/PoseCap

    Read-only drift audit — compare AGENTS.md, ARCHITECTURE.md, ADR statuses, feature specs in doc/specs/, and documentation discipline against what the code actually does.

    224 GitHub stars~1.8k tokensUpdated yesterday
    Auto-check: notes

  • Ad Hooks

    CorridorTech/PoseCap

    Scaffold deterministic quality gates per WORKFLOW.md §11 — pre-commit (lint, format, secret-scan), pre-push (build, unit, integration).

    224 GitHub stars~2.4k tokensUpdated yesterday
    Auto-check: notes

  • Ad Next

    CorridorTech/PoseCap

    Survey the project's state across the six-layer artifact stack and recommend prioritized next actions, modeled on flutter doctor.

    224 GitHub stars~3.3k tokensUpdated yesterday
    Auto-check: notes

Categories

Questions about Ad Task

What does Ad Task do?

Draft a new task tracking file at doc/tasks/NNNN-<short-slug.md, using a checkbox-toggle + append-only-Notes format optimized for LLM editing. Ad Task is an agent skill from CorridorTech/PoseCap.md, using a checkbox-toggle + append-only-Notes format optimized for LLM editing.

When should I use Ad Task?

Ad Task fits situations like: the user wants to create; backlog entry tracked in the repo.

How do I install Ad Task in Claude Code?

Run `npx skills add CorridorTech/PoseCap --skill ad-task -a claude-code`. Or copy the skill folder (.claude/skills/ad-task in CorridorTech/PoseCap) into .claude/skills/ad-task in your project. Claude Code loads it when a task matches its description.

How do I install Ad Task in Codex?

Run `npx skills add CorridorTech/PoseCap --skill ad-task -a codex`. Or copy the skill folder (.claude/skills/ad-task in CorridorTech/PoseCap) into .agents/skills/ad-task in your project. Codex loads it when a task matches its description.

Can I use Ad Task in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add CorridorTech/PoseCap --skill ad-task -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ad-task, .gemini/skills/ad-task, .github/skills/ad-task and .opencode/skills/ad-task in your project.

What does Ad Task need to run?

SKILL.md names no scripts, command-line tools or credentials: Ad Task is instructions for the agent only. Its frontmatter pre-approves these tools: Read, Write, Glob, Bash.

Does Ad Task access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Ad Task safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Ad Task use?

Ad Task is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Ad Task use?

About 1.5k tokens (SKILL.md is roughly 6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Ad Task?

Skills that share tags, products or a category with Ad Task: Ad Task (alexandremendoncaalvaro/CorridorKey-Runtime, 755 stars), Backlog Grooming (forcedotcom/salesforcedx-vscode, 1k stars), Kanban Md (antopolskiy/kanban-md, 223 stars) and Herdr Board (nelsonPires5/herdr-board, 170 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Ad Task?

CorridorTech (a GitHub organization) maintains it in CorridorTech/PoseCap, which has 224 GitHub stars. The repository holds 15 skills in this directory. The repository was last updated on October 7, 2026.

Source: CorridorTech/PoseCap on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.