Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

MyAgents Task Alignment · hacklyc | DecimalAI

agent toolingby hacklyc

MyAgents Task Alignment

hacklyc/myagents-task-alignment

Source hacklyc/myagents ↗License AGPL-3.0

MyAgents 产品内“任务讨论/智能创建”的对齐工作流。只要首轮消息带有 <TASK_DISCUSSION> 上下文，就使用本 Skill 与用户澄清需求、判断是否需要创建 Task，并在创建前生成完整 task.md 候选稿与参数说明供用户确认。讨论不必以 Task 为终点；也可以继续探索、留在当前 Session 执行或明确放弃。不要把普通对话中泛泛提到的“任务”误判为此产品工作流。

SkillScore61Maintained

Automatic

Project Management pack

Last verified 9/25/2026

What it changes

Passed 6 of 10 test cases with the skill, and 3 of 10 without it.

Without skill35%

With skill61%

Checks it passed that the model alone missed

Reports the created `taskId` and default task state.
Restates the Nginx error log hourly monitoring objective in the assistant's own words.
Engages in clarifying execution parameters or boundaries prior to writing candidate files.

and 8 more in the full report

8 fixed6 passed either way7 still failing2 broke

Pass-rate lift: +26 pp
Tokens: +95%
Agent turns: 0%
Response time: +7%

Model gemini-3.6-flashMeasured 9/25/2026v114 of 23 cases passed with skill · 10 comparable

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/hacklyc-myagents-task-alignment/SKILL.md https://app.decimal.ai/s/hacklyc-myagents-task-alignment/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add hacklyc-myagents-task-alignment, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/hacklyc-myagents-task-alignment/ and pins it in .decimal/skills.lock

decimalai skills add hacklyc-myagents-task-alignment

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/hacklyc-myagents-task-alignment/SKILL.md https://app.decimal.ai/s/hacklyc-myagents-task-alignment/SKILL.md

Raw file: /s/hacklyc-myagents-task-alignment/SKILL.md ↗ · machine-readable summary at /s/hacklyc-myagents-task-alignment.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 4

Prompt

<TASK_DISCUSSION> discussionId: disc_cli_03 discussionDir: /tmp/discussions/disc_cli_03 candidatesDir: /tmp/discussions/disc_cli_03/candidates workspaceId: ws_dev workspacePath: /home/dev/app </TASK_DISCUSSION> I explicitly confirm: "Yes, create the task now with candidate `/tmp/discussions/disc_cli_03/candidates/code-lint/task.md` named `code-lint`." Before running the creation mutation command, what command should be executed first to verify the exact flag names of the local CLI?

What was checked, without and with the skill
Checked	Without skill	With skill
Advises running `myagents task create-direct --help` to verify leaf help arguments before executing creation.	Missed	Passed

case-15 · gemini-3.6-flash · 9/25/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md88 linessingle file

MyAgents Task Alignment

你正在承接 MyAgents 发起的任务讨论。目标不是把每个想法都变成 Task，而是先把用户真正想完成的事情聊清楚，再选择最合适的承载方式。

先读取产品能力

开始讨论前完整读取 myagents-task-automation Skill。它是 Task 支持的执行模式、时间、触发策略、Session 策略、结束条件和 CLI 参数的权威能力说明。本 Skill 只负责需求对齐、task.md 质量与创建前确认，不复制那份能力表。

首轮消息的隐藏 <TASK_DISCUSSION> 中会给出：

discussionId
discussionDir
candidatesDir
workspaceId
workspacePath
可选的 sourceThoughtId 与标签

这些值来自应用，不要要求用户重填，也不要自行猜测或改写。若隐藏上下文缺失或路径无效，说明当前讨论无法安全创建 Task；仍可继续普通讨论，但不要调用 Task 创建命令。

像同事一样讨论

先用自己的话复述你理解的目标，并问最能改变方案的一两个问题。根据问题复杂度决定讨论轮数：信息已经充分时直接收敛，存在产品、技术或验收岔路时继续追问。不要把六维清单逐项问成表单。

能通过代码、文件或工具确认的事实先自行核实。主动提出具体的完成标准，让用户修正；不要只问一句“怎么验收”。

讨论过程中持续判断承载方式：

留在当前 Session：用户希望实时参与、马上执行，或讨论本身就是结果。
创建 Task：工作需要未来触发、独立调度、持久跟踪、隔离 Session 或清晰的独立交付。
不做：收益不足、前提不成立或用户明确放弃。

这三种结局都正常。不要为了完成流程而强推创建 Task。

撰写一份完整的 task.md

只有当双方倾向创建 Task 时，才把全部执行上下文写成一个候选 task.md。一个未参与讨论的 Agent 只读这一个文件，也应能完成工作并判断是否完成。

内容通常覆盖：

背景与动机

Track record

Benchmark

6 / 10

test cases passed, vs 3 / 10 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v5 — 8/25/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

hacklyc / myagents

bundled-skills/myagents-task-alignment/SKILL.md

View on GitHub ↗

License AGPL-3.0Imported 8/25/2026Version v1

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

hacklyc/task-alignmentAlignment conversation starting from a 想法/idea. Co-decides with the user whether the idea should be acted on directly in the current session, or fixed into a formal Task for independent dispatch (one-off or recurring). Handles lightweight 'do it now while we talk', heavyweight 'define precisely, run later or on a schedule', and 'just help me think about this' — all on the same skill. Use when the user arrives via the 想法 panel's 'AI 讨论' button (parameter dictionary in the first message), or says Close match+32 pp pass-rate lift

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

MyAgents Task Alignment

先读取产品能力

像同事一样讨论

撰写一份完整的 task.md

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills