workflow-assessment
Skill1 starsChanged 53 days agoMITView on GitHub
Assess project and task complexity, risk, impact, size, maintainability, coordination, existing assets, and target stage to select LIGHTWEIGHT, STANDARD, or STRICT. Use for AUTO mode, new tasks, scope changes, or risk-driven escalation and de-escalation.
In this repository21 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- adaptive-testingSkill
- architecture-decisionSkill
- artifact-validationSkill
- change-impactSkill
- clarification-gateSkill
- code-reviewSkill
- component-planningSkill
- failure-diagnosisSkill
- failure-escalationSkill
- framework-checkpointSkill
- framework-resumeSkill
- gap-analysisSkill
- implement-componentSkill
- integration-gateSkill
- minimum-pathSkill
- project-intakeSkill
- quality-gateSkill
- reverse-engineeringSkill
- stage-gateSkill
- traceabilitySkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 3 are distinctive, and 1 is 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.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 14
Run when Workflow Mode is AUTO, at initial planning, when a task is introduced, or when new evidence changes complexity, risk, impact, or …
- Distinctive: line 34
Check Process Budget: added ceremony must reduce relevant risk or support the target.
- Distinctive: line 63
Use Clarification Gate when accepting risk, cost, scope, or reduced rigor requires user authority.
- Distinctive: line 67
Stop when both levels and required evidence are recorded, when clarification blocks classification, or when Intake/validation must precede …
≈ “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
Workflow Assessment
Purpose
Choose proportionate engineering rigor while distinguishing the Project Workflow Level from the current Task Workflow Level.
Trigger
Run when Workflow Mode is AUTO, at initial planning, when a task is introduced, or when new evidence changes complexity, risk, impact, or scope.
Inputs
- User target, Project Configuration, Execution Mode, and existing State.
- Complexity, technical uncertainty, risk, impact, Project Size, and Task Size.
- Maintainability horizon, Team/Agent Count, coordination boundaries, existing assets, and Target Stage.
- Security, safety, compliance, data, deployment, compatibility, and cost constraints.
Prerequisites
- Complete enough Intake to avoid scoring an unknown project as simple.
- Identify mandatory organizational or regulatory checks that no level may waive.
Procedure
- Assess each factor as low, medium, or high with evidence and uncertainty.
- Determine the Project Workflow Level as the long-lived baseline for overall system risk and maintenance needs.
- Determine the Task Workflow Level independently from the task's affected scope and actual risk.
- Compare the task level with the project baseline; document every escalation or de-escalation.
- Check Process Budget: added ceremony must reduce relevant risk or support the target.
- Define the required Artifact, review, testing, traceability, and Gate depth for the chosen task level.
- Record reassessment triggers such as cross-module impact, security discovery, Contract change, or reduced scope.
Decision Rules
LIGHTWEIGHT: bounded low-risk change, small blast radius, established design, and short/simple coordination; still require build/equivalent check, relevant tests, verification, quick review, and Checkpoint.STANDARD: normal multi-step or multi-module work needing explicit dependencies, design, review, testing, and integration evidence.STRICT: high security/safety/compliance risk, major architecture/data impact, broad compatibility or deployment impact, large coordination surface, or long-lived/high-reliability system.- A Task may be
LIGHTWEIGHTinside aSTRICTproject only when isolation and low risk are evidenced. - A Task may exceed the Project Level when its risk demands it.
- Uncertainty with high possible impact raises rigor; it does not justify optimistic classification.
Outputs
- Project Workflow Level and rationale.
- Task Workflow Level and rationale.
- Factor assessment, uncertainty, escalation/de-escalation reason, and reassessment triggers.
- Required evidence and Gate depth for the current task.
Failure Cases
- Risk or target is too ambiguous to classify.
- Mandatory standards conflict with the requested level.
- The task boundary is not defined.
- Available assets have unknown validity.
Escalation
Use Clarification Gate when accepting risk, cost, scope, or reduced rigor requires user authority. Escalate immediately when discovered security, architecture, data, or cross-component impact exceeds the current level.
Stop Conditions
Stop when both levels and required evidence are recorded, when clarification blocks classification, or when Intake/validation must precede a reliable decision. Do not generate lifecycle work merely because a higher level exists.
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.

