do-work

Task queue - add requests or process pending work

Safety Notice

This listing is imported from skills.sh public index metadata. Review upstream SKILL.md and repository scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "do-work" with this command: npx skills add bladnman/do-work/bladnman-do-work-do-work

Do-Work Skill

A unified entry point for task capture and processing.

Actions:

  • do: Capture new tasks/requests → creates UR folder (verbatim input) + REQ files (queue items), always paired, then verifies coverage
  • work: Process pending requests → plans (with plan verification), explores, builds, tests
  • verify: Evaluate captured REQs against original input → coverage check with auto-fix (also runs automatically after capture)
  • cleanup: Consolidate archive → moves loose REQs into UR folders, closes completed URs

Core concept: The do action always produces both a UR folder (preserving the original input) and REQ files (the queue items). Each REQ links back to its UR via user_request frontmatter. This pairing is mandatory for all requests — simple or complex.

Capture ≠ Execute. The do action captures requests. The work action executes them. These are strictly separate operations. After the do action finishes writing files and reporting back, STOP. Do not start processing the queue, do not begin implementation, do not "helpfully" transition into the work action. The user decides when to execute — always. The only exception is if the user explicitly says something like "add this and then run it" or "capture this and start working" in the same invocation.

Routing Decision

Step 1: Parse the Input

Examine what follows "do work":

Check these patterns in order — first match wins:

PriorityPatternExampleRoute
1Empty or bare invocationdo work→ Ask: "Start the work loop?"
2Action verbs onlydo work run, do work go, do work start→ work
3Verify keywordsdo work verify, do work check, do work evaluate→ verify
4Cleanup keywordsdo work cleanup, do work tidy, do work consolidate→ cleanup
5Version keywordsdo work version, do work update, do work check for updates→ version
6Changelog keywordsdo work changelog, do work release notes, do work what's new, do work what's changed, do work updates, do work history→ version
7Descriptive contentdo work add dark mode, do work [meeting notes]→ do

Step 2: Preserve Payload

Critical rule: Never lose the user's content.

Single-word rule: A single word is either a known keyword or ambiguous — it is never "descriptive content."

  • Matches a keyword in the routing table (e.g., "version", "verify", "cleanup") → route to that action directly.
  • Doesn't match any keyword (e.g., "refactor", "optimize") → ambiguous. Ask: "Do you want to add '{word}' as a new request, or did you mean something else?"

Only route to do when the input is clearly descriptive — multiple words, a sentence, a feature request, etc.

If routing is genuinely unclear AND multi-word content was provided:

  • Default to do (adding a task)
  • Hold onto $ARGUMENTS
  • If truly ambiguous, ask: "Add this as a request, or start the work loop?"
  • User replies with just "add" or "work" → proceed with original content

Action Verbs (→ Work)

These signal "process the queue": run, go, start, begin, work, process, execute, build, continue, resume

Verify Verbs (→ Verify)

These signal "check request quality": verify, check, evaluate, review requests, review reqs, audit

Note: "check" routes to verify ONLY when used alone or with a target (e.g., "do work check UR-003"). When followed by descriptive content it routes to do (e.g., "do work check if the button works" → do).

Cleanup Verbs (→ Cleanup)

These signal "consolidate the archive": cleanup, clean up, tidy, consolidate, organize archive, fix archive

Changelog Verbs (→ Version)

These signal "show release notes": changelog, release notes, what's new, what's changed, updates, history

Note: "updates" (plural) routes to changelog display. "update" (singular) routes to update check. Both are handled by the version action.

Content Signals (→ Do)

These signal "add a new task":

  • Descriptive text beyond a single verb
  • Feature requests, bug reports, ideas
  • Screenshots or context
  • "add", "create", "I need", "we should"

Examples

Routes to Work

  • do work → "Ready to process the queue?" (confirmation)
  • do work run → Starts work action immediately
  • do work go → Starts work action immediately

Routes to Verify

  • do work verify → Evaluates most recent UR's REQs
  • do work verify UR-003 → Evaluates specific UR
  • do work check REQ-018 → Evaluates the UR that REQ-018 belongs to
  • do work evaluate → Evaluates most recent UR's REQs
  • do work review requests → Evaluates most recent UR's REQs

Routes to Cleanup

  • do work cleanup → Consolidates archive, closes completed URs
  • do work tidy → Same as cleanup
  • do work consolidate → Same as cleanup

Routes to Changelog (via Version)

  • do work changelog → Displays changelog (newest at bottom)
  • do work release notes → Same as changelog
  • do work what's new → Same as changelog
  • do work updates → Same as changelog
  • do work history → Same as changelog

Routes to Do

  • do work add dark mode → Creates REQ file + UR folder
  • do work the button is broken → Creates REQ file + UR folder
  • do work [400 words] → Creates REQ files + UR folder with full verbatim input

Payload Preservation Rules

When clarification is needed but content was provided:

  1. Do not lose $ARGUMENTS - keep the full payload in context
  2. Ask a simple question: "Add this as a request, or start the work loop?"
  3. Accept minimal replies: User says just "add" or "work"
  4. Proceed with original content: Apply the chosen action to the stored arguments
  5. Never ask the user to re-paste content

This enables a two-phase commit pattern:

  1. Capture intent payload
  2. Confirm action

Action References

Follow the detailed instructions in:

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

General

Interior Fullplan

# 室内设计·全案方案自动生成器

Archived SourceRecently Updated
General

kb-archiver

智能本地知识库归档系统 v1.1.0。支持 AI 智能分类、批量归档、全文搜索、统计报告。 自动将文件分类归档到本地知识库,提取全文索引支持秒级搜索。 小文件存本地、大文件可对接云存储。支持 Excel/Word/PPT/PDF/TXT 等格式。 当用户需要:归档文件、建立知识库、全文检索文档内容、管理大量工作文档、批量处理文件夹时使用。 关键词:知识库、归档、文件管理、全文搜索、文档索引、批量归档、AI分类

Archived SourceRecently Updated
General

honest-agent

强制诚实系统:防止AI撒谎、虚构、言行不一。核心功能:(1) 承诺自动追踪(写入honest-commitments.json)(2) 回复前诚实校验拦截 (3) 媒体并行识别(大模型+OCR择优)(4) 诚实审计日志 (5) 安全独立存储。触发词:诚实、撒谎、虚构、承诺、图片识别、媒体处理、我承诺、我会帮你。

Archived SourceRecently Updated
General

long-term-plan

长期计划推进技能。用于管理需要持续数天/数周的任务,采用滚动节点式规划(每3-5天为一个阶段,阶段结束时复盘并规划下一阶段)。支持自动日期计算、每日同步、复盘统计、多任务管理、极简指令。当用户说"开一个长期计划"、"今天计划任务"、"阶段复盘"、"滚动下一阶段"、"列出所有计划"时使用。

Archived SourceRecently Updated