verifying-task-output
Skill1 starsChanged 5 months agoMITView on GitHub
Use after a dispatched task returns, to verify the output before marking it done.
In this repository6 other files it gives its agents.
- capability-routingSkill
- dispatching-agentsSkill
- mission-trackingSkill
- reviewing-plansSkill
- writing-agentsSkill
- writing-plansSkill
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
- Distinctive: line 8
Verify in two stages, in order:
- Very specific: line 18
When you mark a task done, append a row to the mission's ## Metrics section (creating the section if it is absent) with the task id, the …
≈ “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
Verifying Task Output
Verify in two stages, in order:
- Spec review (spec-reviewer agent): does the output do exactly what the task asked, nothing missing or extra? If not, send the task back to its agent with the gaps.
- Code-quality review (code-quality-reviewer agent): only after spec review passes. If it raises issues, send them back.
Mark the task done only when both pass. If an agent cannot resolve a blocker, mark the
task blocked and surface it to the user.
When you mark a task done, append a row to the mission's ## Metrics section (creating the
section if it is absent) with the task id, the agent that ran it, and your best estimate of
the tokens used and the wall-clock duration in minutes. Leave a cell blank if you cannot
estimate it. /report reads these rows.
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.