workflow-done-definition
Skill1 starsChanged 6 months agoMITView on GitHub
What "done" means. Applied before reporting any task complete.
In this repository33 other files it gives its agents.
- skill-process-gotchasSkill
- workflow-cache-disciplineSkill
- workflow-codegraphSkill
- workflow-conductorSkill
- workflow-context-condenserSkill
- workflow-context-hygieneSkill
- workflow-criticSkill
- workflow-deadline-disciplineSkill
- workflow-deep-researchSkill
- workflow-edit-formatSkill
- workflow-effort-routingSkill
- workflow-escalateSkill
- workflow-execute-from-planSkill
- workflow-filesystem-offloadSkill
- workflow-learn-frameworkSkill
- workflow-long-running-processesSkill
- workflow-lspSkill
- workflow-memory-curationSkill
- workflow-plan-contractSkill
- workflow-plan-firstSkill
- workflow-planSkill
- workflow-quality-barSkill
- workflow-repomapSkill
- workflow-retrieve-before-actSkill
- workflow-spec-drivenSkill
- workflow-stuck-detect-resetSkill
- workflow-stuckSkill
- workflow-subagent-isolationSkill
- workflow-subtask-loopSkill
- workflow-task-finishSkill
- workflow-task-startSkill
- workflow-tool-selectionSkill
- workflow-verify-enhancedSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 11
Every item in the task's definition-of-done checklist (from workflow-plan-first) is met.
- Distinctive: line 19
Only then report done, with: what was built, the verify result, and how to run it.
- Distinctive: line 20
If any of the above is not true, the task is NOT done — keep going or invoke stuck-detect-reset.
≈ “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
<!-- TRIGGERS WHEN: What "done" means. -->"Done" is defined by verification, never by the model's opinion.
Before reporting done:
- Every item in the task's definition-of-done checklist (from workflow-plan-first) is met.
- mcp-verify is GREEN (
mcp_hermes_max_verify_verify— lint + types + tests). If the project has no tests, that itself is a gap — write at least one test that exercises the main path, then verify. - For anything with a runtime (server, CLI, script): it was actually RUN once and produced the expected output (see workflow-long-running-processes for how to test a server).
- The knowledge-graph has the key decisions recorded
(
mcp_hermes_max_knowledge_graph_record_entity); a skill was distilled if the task was novel. - Only then report done, with: what was built, the verify result, and how to run it. If any of the above is not true, the task is NOT done — keep going or invoke stuck-detect-reset.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
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.