minimum-path
Skill1 starsChanged 53 days agoMITView on GitHub
Convert a validated Gap Set and Artifact dependencies into the Minimum Necessary Path to a target. Use to prune satisfied work, order required nodes, expose blockers, place Gates, and avoid running the full lifecycle automatically.
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
- project-intakeSkill
- quality-gateSkill
- reverse-engineeringSkill
- stage-gateSkill
- traceabilitySkill
- workflow-assessmentSkill
The file
We split this skill into the rules it gives an agent
7 rules. About 0 are common, 7 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈7
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 14
Run after Gap Analysis, after a material decision or Change Impact, when workflow rigor changes, or when failure invalidates the current …
- Distinctive: line 32
Add required clarification, decision, validation, implementation, test, review, integration, and Gate nodes.
- Distinctive: line 35
Place integration points, revalidation boundaries, Checkpoints, and the final Stage Gate.
- Distinctive: line 42
Never add the entire lifecycle by default.
- Distinctive: line 43
Do not include work beyond Target Stage.
- Distinctive: line 64
Use Clarification Gate for target or authority choices, Architecture Decision for structural dependency choices, and Workflow Assessment …
- Distinctive: line 68
Stop when a minimal executable path and next action are recorded, or when a blocker prevents safe planning.
≈ “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
Minimum Necessary Path
Purpose
Produce the smallest dependency-correct, risk-appropriate path from current evidence to the requested target.
Trigger
Run after Gap Analysis, after a material decision or Change Impact, when workflow rigor changes, or when failure invalidates the current path.
Inputs
- Target Artifact/Stage and stop boundary.
- Gap Set, satisfied nodes, Artifact dependency graph, and current State.
- Project/Task Workflow Levels, risks, constraints, available Agents/Skills, and Process Budget.
Prerequisites
- Target and Definition of Done are sufficiently clear.
- Target-relevant Artifact dispositions and gaps are current.
Procedure
- Walk backward from the target through only mandatory Artifact dependencies.
- Prune nodes already satisfied by
VALID, sufficient, compatible revisions. - Replace broad regeneration with
SUPPLEMENTorREVALIDATEnodes when sufficient. - Add required clarification, decision, validation, implementation, test, review, integration, and Gate nodes.
- Order nodes by dependency; mark ready, blocked, satisfied, failed, and pruned states.
- Group independent ready nodes for possible parallel work only when write scopes do not overlap and Contracts are stable.
- Place integration points, revalidation boundaries, Checkpoints, and the final Stage Gate.
- Estimate process cost and remove optional work that does not reduce material risk or enable the target.
- Record replan triggers and the first next action.
Decision Rules
- Artifact dependencies, not Agent order, determine sequence.
- Never add the entire lifecycle by default.
- Do not include work beyond Target Stage.
- Existing valid evidence is reused; unknown evidence is validated before replacement.
- Parallel writes require non-overlapping scope, stable versioned Contracts, isolated workspaces, and an integration owner.
- Any node whose prerequisites are unmet remains blocked, not optimistically ready.
- The effective Task Workflow Level determines evidence depth, not the number of lifecycle stages executed.
Outputs
- Current Minimum Necessary Path with node IDs, purpose, dependencies, state, owner capability, required Skill/Gate, output, and DoD.
- Pruned-node rationale and accepted reusable evidence.
- Parallel groups, integration points, blockers, replan triggers, and next ready action.
Failure Cases
- Cyclic or missing dependencies prevent ordering.
- Target ambiguity changes the path materially.
- Required Contracts or ownership are unresolved.
- Process Budget conflicts with mandatory risk controls.
Escalation
Use Clarification Gate for target or authority choices, Architecture Decision for structural dependency choices, and Workflow Assessment when risk outgrows the current level. Report cycles or model defects for correction before execution.
Stop Conditions
Stop when a minimal executable path and next action are recorded, or when a blocker prevents safe planning. Do not start executing nodes merely because the plan 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.

