implement-workitem
Skill2 starsChanged 45 days agoMITView on GitHub
Use ONLY when the user explicitly types `$implement-workitem <task-id>`. Do not trigger implicitly from generic phrasing.
In this repository51 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- accept-milestoneSkill
- bootstrap-projectSkill
- bootstrap-stackSkill
- consult-expertSkill
- design-milestoneSkill
- finalize-workitemSkill
- plan-milestoneSkill
- plan-workitemSkill
- repair-acceptanceSkill
- repair-discoverySkill
- repair-milestoneSkill
- repair-planSkill
- repair-workitemSkill
- run-milestoneSkill
- seal-milestoneSkill
- stabilize-milestoneSkill
- stack-guardSkill
- validate-discoverySkill
- validate-milestoneSkill
- validate-planSkill
- validate-workitemSkill
- accept-milestoneSkill
- amend-ssotSkill
- boilerplate-contextSkill
- bootstrap-designSkill
- bootstrap-projectSkill
- bootstrap-stackSkill
- consult-expertSkill
- design-milestoneSkill
- discover-productSkill
- finalize-workitemSkill
- implement-workitemSkill
- plan-milestoneSkill
- plan-workitemSkill
- repair-acceptanceSkill
- repair-discoverySkill
- repair-milestoneSkill
- repair-planSkill
- repair-workitemSkill
- research-packSkill
- review-docSkill
- run-milestoneSkill
- seal-milestoneSkill
- stabilize-milestoneSkill
- stack-guardSkill
- validate-discoverySkill
- validate-milestoneSkill
- validate-planSkill
- validate-workitemSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 8
Treat all frontmatter keys other than name and description (e.g., agent:, disable-model-invocation:, allowed-tools:, context:, …
- Distinctive: line 14
If the source path no longer exists, this wrapper is stale — see ADR-010.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Source of truth: .claude/skills/implement-workitem/SKILL.md. Read it and follow the workflow.
Treat all frontmatter keys other than name and description (e.g., agent:, disable-model-invocation:, allowed-tools:, context:, argument-hint:, model:, effort:) as Claude-only and ignore them — execute locally in Codex.
Slash command translation: 본문 안의 /implement-workitem 표기는 Claude 슬래시 커맨드다. Codex에서는 $implement-workitem으로 읽고 사용자에게 안내한다 (예: 본문 "다음 단계: /finalize-workitem T-001" → Codex 응답에서는 "다음 단계: $finalize-workitem T-001"). Codex CLI는 /를 빌트인 슬래시 커맨드에 쓰므로 명시적 치환이 필요.
Preserve all repo policies from AGENTS.md and docs/.
If the source path no longer exists, this wrapper is stale — see ADR-010.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.