agentleFS
QuirkybrainQuirkybrain/claude-code-swe-framework/.claude/skills/gap-analysis/SKILL.md

gap-analysis

Skill1 starsChanged 53 days agoMITView on GitHub

Compare validated existing Artifacts with a target Artifact or Target Stage and find missing, partial, unverified, stale, invalid, or incompatible dependencies. Use after Intake/validation and before computing the Minimum Necessary Path.

21 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 20 edited versions we read keep these.

  • 6

    Distinctive

    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
  1. Distinctive:

    Run after Project Intake, when a target changes, after Change Impact, on resume with repository drift, or when a Gate exposes missing …

    line 14
  2. Distinctive:

    Start at the target and enumerate only dependencies required for its declared scope and risk.

    line 29
  3. Distinctive:

    Do not add requirements, design, implementation, testing, or release work unrelated to the target.

    line 44
  4. Distinctive:

    If the target itself is ambiguous, stop at Clarification Gate before expanding the graph.

    line 45
  5. Distinctive:

    Use Artifact Validation for uncertain reusable nodes, Clarification Gate for material target ambiguity, and Change Impact when the gap …

    line 63
  6. Distinctive:

    Stop when all target-required dependencies are classified with evidence, or when clarification/validation blocks reliable analysis.

    line 67

“Common” is measured: kept by at least 6 in 10 of the 20 edited versions of this file we could read. “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

Gap Analysis

Purpose

Identify exactly what prevents the current Artifact graph from satisfying the user's target.

Trigger

Run after Project Intake, when a target changes, after Change Impact, on resume with repository drift, or when a Gate exposes missing evidence.

Inputs

  • Target Artifact or Target Stage and its Definition of Done.
  • Artifact Inventory, dependency graph, validation records, and current State.
  • Existing Asset evidence, Project Constraints, Workflow Level, and accepted assumptions/decisions.

Prerequisites

  • Normalize the target and stop boundary.
  • Validate target-relevant existing Artifacts enough to distinguish presence from usability.

Procedure

  1. Start at the target and enumerate only dependencies required for its declared scope and risk.
  2. Walk the Artifact dependency graph backward to source evidence.
  3. For each required node, compare required revision/quality with current status and evidence.
  4. Classify gaps as MISSING, PARTIAL, UNVERIFIED, STALE, INVALID, incompatible, or blocked by clarification.
  5. Explain why each gap blocks or weakens the target and which downstream nodes it affects.
  6. Recognize alternative evidence or reusable assets that may satisfy the dependency.
  7. Separate required gaps from optional improvements and later-stage work.
  8. Record ready gaps whose upstream dependencies are already satisfied.

Decision Rules

  • A VALID and sufficient Artifact is not a gap.
  • PARTIAL is a gap only for uncovered content required by the target.
  • UNVERIFIED and STALE normally require validation, not automatic regeneration.
  • INVALID requires repair or regeneration only if it lies on the target dependency path.
  • Do not add requirements, design, implementation, testing, or release work unrelated to the target.
  • If the target itself is ambiguous, stop at Clarification Gate before expanding the graph.

Outputs

  • Gap Set with node ID, type, state, required revision/quality, evidence, and blocking reason.
  • Satisfied/prunable dependency set.
  • Ready, blocked, optional, and out-of-scope nodes.
  • Dependency rationale suitable for Minimum Path computation.

Failure Cases

  • Dependency graph is absent or contradictory.
  • Artifact statuses lack revision-specific evidence.
  • Multiple target interpretations produce materially different gaps.
  • A required asset is inaccessible.

Escalation

Use Artifact Validation for uncertain reusable nodes, Clarification Gate for material target ambiguity, and Change Impact when the gap originates from an upstream change. Ask an architect only when dependency semantics cannot be established without a design decision.

Stop Conditions

Stop when all target-required dependencies are classified with evidence, or when clarification/validation blocks reliable analysis. Do not execute the gaps in this Skill.

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.