agentleFS
Sign inStart free
fzfcleefzfclee/consulting-skills/skills/constraint-analysis/SKILL.md

constraint-analysis

Skill6 starsChanged 4 months agoApache-2.0View on GitHub

Use when progress is limited by bottlenecks, scarce resources, binding constraints, dependencies, policy limits, capacity limits, decision rights, or one factor that controls throughput. Use when applying constraint analysis, bottleneck diagnosis, theory of constraints, limiting-factor review, or constraint removal planning.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 4 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill to identify the constraint that most limits progress and decide how to address it.

    line 9
  2. Very specific:

    If an input is missing, mark it as missing, state the assumption used, and add a validation action.

    line 28
  3. Very specific:

    Do not use when the issue is mainly unclear preference or option selection.

    line 32
  4. Distinctive:

    Do not treat every problem as a constraint.

    line 72
  5. Distinctive:

    Use evidence of throughput, delay, queue, rejection, or dependency to identify the binding constraint.

    line 73
  6. Distinctive:

    Avoid solving a non-binding issue just because it is visible.

    line 76

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Constraint Analysis

Use this skill to identify the constraint that most limits progress and decide how to address it.

Method Notes

  • A constraint is the factor that most limits the system's ability to reach the goal.
  • Many issues are annoyances; only a few are binding constraints.
  • The method should distinguish symptoms, bottlenecks, dependencies, policy constraints, resource constraints, and self-imposed constraints.
  • Removing a constraint may move the bottleneck elsewhere, so follow-up monitoring matters.

Required Inputs

Collect or infer these inputs before execution:

  • goal or desired throughput
  • current process, path, or action sequence
  • observed blockage or delay
  • resources, capacity, decision rights, dependencies, and policies
  • evidence of where work queues, stalls, or fails

If an input is missing, mark it as missing, state the assumption used, and add a validation action.

When Not To Use

Do not use when the issue is mainly unclear preference or option selection. Use decision-matrix or weighted-scorecard instead.

Step-by-Step Execution

StepRequired inputHow to executeOutput
Define the goalDesired outcome, throughput, or progress.State what the system is trying to achieve.Goal statement.
Map the flowProcess steps, dependencies, owners.List the sequence from start to desired outcome.Flow map.
Identify stall pointsEvidence of delays, queues, rework, rejection, missing approvals.Mark where progress slows or stops.Bottleneck candidates.
Classify constraintsResources, capability, policy, market, decision rights, information.Label each candidate constraint type.Constraint table.
Find the binding constraintEvidence, impact, dependency logic.Identify which constraint limits progress most right now.Binding constraint.
Choose responseConstraint type, control boundary.Decide whether to exploit, elevate, remove, redesign around, or monitor the constraint.Constraint action.
Predict next constraintFlow map, action.Anticipate where the bottleneck may move after intervention.Next-constraint watchlist.

Output Template

### 1. Goal And Flow
- Goal:
- Current flow:
- Desired throughput / progress:

### 2. Constraint Candidates
| Candidate constraint | Type | Evidence | Impact | Control boundary |
|---|---|---|---|---|
|  | resource / capacity / capability / policy / decision rights / information / market / self-imposed |  | high / medium / low | inside / influence / outside |

### 3. Binding Constraint
- Current binding constraint:
- Why this is the constraint:
- What is only a symptom:

### 4. Response Plan
| Action | Purpose | Owner / actor | Expected signal | Next constraint to watch |
|---|---|---|---|---|
|  | exploit / elevate / remove / redesign / monitor |  |  |  |

Quality Gate

  • Do not treat every problem as a constraint.
  • Use evidence of throughput, delay, queue, rejection, or dependency to identify the binding constraint.
  • Separate what is inside control from what only can be influenced.
  • Watch for the next bottleneck after the current one is addressed.
  • Avoid solving a non-binding issue just because it is visible.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free