technical-assessment-loop
Skill7 starsChanged 6 months agoMITView on GitHub
Use when running checkpoints that compare plan, implementation evidence, risk, metrics, review findings, or readiness before continuing.
In this repository8 other files it gives its agents.
- AGENTS.mdAGENTS.md
- conops-builderSkill
- decision-analysisSkill
- integration-plannerSkill
- requirements-auditorSkill
- requirements-distillerSkill
- validation-plannerSkill
- verification-plannerSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
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
Use this skill at checkpoints to decide whether evidence supports continuing, changing course, or closing.
- Distinctive: line 18
Do not close work because tests passed if validation or user intent is still unproven.
- Very specific: line 23
Start with references/source-grounding.md, then inspect Section 6.7 pages extraction/pages/page_165.md through extraction/pages/page_171.md …
≈ “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
Technical Assessment Loop
Use this skill at checkpoints to decide whether evidence supports continuing, changing course, or closing.
Workflow
- Restate objective, current plan, and current system state.
- Inventory evidence: changed files, tests, inspections, review findings, artifacts, user feedback, and unresolved assumptions.
- Compare evidence against requirements, integration state, verification, validation, and risk.
- Identify drift: scope creep, weak evidence, stale assumptions, hidden dependencies, or validation gaps.
- Decide one action: continue, rework, split scope, escalate, pause for input, or close.
- Record the decision, evidence, residual risk, and next checkpoint trigger.
- Do not close work because tests passed if validation or user intent is still unproven.
- Output a checkpoint note: objective, evidence, gaps, risk, decision, next action.
Source grounding
Start with references/source-grounding.md, then inspect Section 6.7 pages extraction/pages/page_165.md through extraction/pages/page_171.md before making technical-assessment claims.
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.