Ready to supercharge your AI agents?

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

Get Started Free →

CC Task State · doccker | DecimalAI

agent toolingby doccker

CC Task State

doccker/cc-task-state

Source doccker/cc-use-exp ↗License NOASSERTION

任务状态沉淀与恢复工作流，适用于补记进展、记录未开始需求、标记被打断或阻塞、整理恢复入口与下一步场景；通过项目内 .codex/tasks/ 持久化任务状态。

SkillScore82Maintained

Automatic

Project Management pack

Last verified 8/14/2026

What it changes

Passed 18 of 22 test cases with the skill, and 9 of 22 without it.

Without skill41%

With skill82%

Checks it passed that the model alone missed

Labels the operation as 更新任务
References task paths under .codex/tasks/
Classifies the tasks into 当前主线, 候选任务, or 插入任务

and 11 more in the full report

10 fixed8 passed either way3 still failing1 broke

Pass-rate lift: +41 pp
Tokens: +12%
Agent turns: 0%
Response time: -22%

Model gemini-3.6-flashMeasured 8/14/2026v118 of 22 cases passed with skill

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/doccker-cc-task-state/SKILL.md https://app.decimal.ai/s/doccker-cc-task-state/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add doccker-cc-task-state, 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/doccker-cc-task-state/ and pins it in .decimal/skills.lock

decimalai skills add doccker-cc-task-state

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

curl -fsSL --create-dirs -o .claude/skills/doccker-cc-task-state/SKILL.md https://app.decimal.ai/s/doccker-cc-task-state/SKILL.md

Raw file: /s/doccker-cc-task-state/SKILL.md ↗ · machine-readable summary at /s/doccker-cc-task-state.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 10

Prompt

关于‘多语言国际化支持’，组长明确要求‘先记一下，等主线收尾再做，现在千万别开始写代码’。请记录其任务状态。

What was checked, without and with the skill
Checked	Without skill	With skill
Assigns status 需求中 or 待开始 to the unstarted task	Missed	Passed
Does not assign status 进行中 to the unstarted task	Passed	Passed

case-10 · gemini-3.6-flash · 8/14/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md42 lines3 files

CC Task State

当用户明确要求记录当前进展、补记需求、说明“还没开始/先记一下/被 fix 打断/稍后继续”、整理恢复入口，或需要把自然语言进展沉淀为项目任务状态时，使用本技能。

不要用于：

直接实现完整 feature
代替 bug 修复或 debug
只做配置状态诊断

核心方式

先确认当前项目根目录的 .codex/tasks/ 与 .codex/tasks/archived/ 可用；目录缺失时优先初始化，不把“缺目录”直接当成“不可写”。
即使目录已存在，也必须先确认当前会话对项目根目录的写入动作可执行；不能因为“看起来已有骨架”就跳过项目内写入检查。
若项目内初始化或任务写入命中权限边界，优先走平台原生审批提示；只有项目目录在审批后仍确实不可写，才说明约束，并明确是否回退到 ~/.codex/tasks/ 继续持久化。
识别用户消息中的任务主体；一段话里有多个任务时，必须拆成多条任务状态，而不是混写成一条。
对每个任务判断状态：需求中、待开始、进行中、被打断、阻塞中、待恢复、已完成、已取消。
若当前已有主线任务，再出现短期插入的 fix 或调查，优先在主线任务的“中断记录”中补 checkpoint；只有范围独立、可能跨多轮的插入任务才单独建任务文件。
用户明确说“还没开始”“先别写代码”“等主线收尾再做”时，只能落为 需求中 或 待开始，不能误写成 进行中。
更新任务文件时，至少补齐“当前结论”“未开始 / 被打断 / 阻塞原因”“恢复入口”“下一步”中的相关字段，避免只写一句状态。
若任务已结束，更新状态后移动到 .codex/tasks/archived/；不要让已完成或已取消任务长期留在根目录。

协作约束

需要完整实现 feature 时，转交 new-feature
需要修 bug 或 debug 时，转交 fix
需要查看任务盘点或配置状态时，转交 cc-status
涉及接口新增、分页、筛选、详情或响应格式判断时，遵循 cc-api-contract-safety

输出要求

明确列出识别出的任务主体和对应状态
明确区分“当前主线”“候选任务”“插入任务”
若用户一句话包含多个任务，必须拆开说明，不合并成模糊总结
说明本次是“新建任务 / 更新任务 / 归档任务 / 只补 checkpoint”中的哪一种
若发生任务目录回退，必须明确说明是“目录缺失已初始化”“项目目录确实不可写”还是“当前会话受限导致写入被拦截”
若当前信息不足以判断状态，先说明缺口，不臆测已经开工

按需展开

Track record

Benchmark

18 / 22

test cases passed, vs 9 / 22 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 v4 — 8/3/2026

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

doccker / cc-use-exp

.codex/skills/cc-task-state/SKILL.md

View on GitHub ↗

License NOASSERTIONImported 8/3/2026Version v1Bundled 2 files

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

CC Task State

核心方式

协作约束

输出要求

按需展开

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills