agentleFS
yogsoth-aiyogsoth-ai/convergence/skills/constraint-identification/SKILL.md

constraint-identification

Skill2 starsChanged 6 months agoApache-2.0View on GitHub

Find blockers and showstoppers using TOC, TRIZ contradiction analysis, and Pre-mortem techniques.

The file

Files
SKILL.md

Constraint Identification

Purpose: Systematically discover what could prevent a candidate from being implemented. Uses Theory of Constraints to find bottlenecks, TRIZ to surface contradictions, and Pre-mortem to anticipate failures before they occur.

When to use:

  • A candidate looks promising but you need to stress-test its viability
  • Stakeholders want to know what could go wrong before committing
  • You need a structured inventory of blockers with severity and removability assessments

Budget

MetricTarget
Constraints identified>= 3 per candidate
Hard constraints classified>= 1
Removal paths designed>= 1 per removable constraint

State Ledger

KeyTypeDescription
candidateobjectThe candidate under assessment
constraints[]arrayAll identified constraints
hard_constraints[]arrayNon-negotiable blockers
soft_constraints[]arrayConstraints that can be worked around
assumptions[]arrayUnvalidated beliefs that may become constraints
removal_paths{}mapConstraint -> removal path mapping

Available Tactics

TacticWhen
constraint-drillingDefault — full constraint discovery, classification, and removal path design

Available SOPs

SOPPurpose
constraint-identification-sopDiscover constraints
constraint-classificationSort into hard/soft/assumptions
removability-assessmentScore how removable each constraint is
removal-pathDesign steps to remove a constraint

Execution Guidance

  1. Deploy constraint-identification-sop to discover all constraints using TOC, TRIZ, and Pre-mortem
  2. Feed discovered constraints to constraint-classification to sort them
  3. For each non-trivial constraint, run removability-assessment
  4. For constraints with removability score > 0.3, design removal-path
  5. Aggregate findings into state ledger

Output Format

constraint_analysis:
  candidate: <name>
  total_constraints: N
  hard_constraints:
    - {constraint, severity, rationale}
  soft_constraints:
    - {constraint, severity, workaround_sketch}
  assumptions:
    - {assumption, risk_if_false, validation_method}
  removal_paths:
    - {constraint, removability: 0.X, steps: [...], timeline, resources}
  showstopper_verdict: <yes/no>
  showstopper_reason: <if yes>

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.