scope-creep-detector

Analyzes git diffs against a stated intent to detect scope creep, unrelated files, broad pull requests, changes that grew beyond a fix, dependency additions, public API renames, config or CI edits, oversized hunks, and formatting-only files. Use when the user asks whether a change grew beyond the fix, a PR is too broad, or what unrelated stuff they touched, and wants keep, split, or justify guidance. Operates locally and offline.

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

93%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a lean, executable, well-structured overview with real one-level-deep references and a clear multi-step workflow. The only gap is slightly lighter validation/feedback-loop detail for a tool that gates destructive split/staging decisions.

Suggestions

Add an explicit validation checkpoint before destructive actions — e.g., a 'Verify before acting' step that re-runs the classifier with --json dry-run or confirms the proposed split against the intent before any staging/revert.

Include a brief error-recovery loop: what to do when the script reports a parse error on a malformed diff or an unsupported manifest format.

Make the validation gating more prominent by mirroring the 'Validate → fix → only-then-proceed' pattern from the workflow-clarity anchors for the split/justify handoff.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — no padding about what git or a diff is, every section earns its place, and instructions are tight ('Prefer split when evidence is ambiguous').	5 / 5
Actionability	It provides copy-paste-ready, executable commands for every diff mode (working tree, staged, branch-base, stdin), flags like --json and --hunk-threshold, and a concrete keep/split/justify decision procedure with named criteria.	5 / 5
Workflow Clarity	The sequence (establish intent → run classifier → interpret JSON → recommend → write report) is clear with explicit checkpoints like 'Ask before applying any split, revert, staging, or commit', but validation/verification feedback loops are lighter than the destructive-operation guidance warrants.	4 / 5
Progressive Disclosure	The SKILL.md is a concise overview that signals a single one-level-deep reference (references/scope-signals.md) and a script (scripts/scope_creep.py), both of which are real bundle files; navigation is easy and content is appropriately split.	5 / 5
	Total	19 / 20 Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific, trigger-rich, and complete, clearly answering both what the skill does and when to invoke it with natural user phrasing. It is well-distinguished from neighboring review skills.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete detection actions — scope creep, unrelated files, broad PRs, dependency additions, API renames, config/CI edits, oversized hunks, formatting-only files — with comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	It explicitly answers both 'what' (analyzes git diffs to detect scope creep and the listed signals) and 'when' ('Use when the user asks whether a change grew beyond the fix, a PR is too broad...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	It includes natural phrases users actually say ('a change grew beyond the fix', 'a PR is too broad', 'what unrelated stuff they touched', 'keep, split, or justify') alongside technical terms, covering synonyms and intent-driven language.	5 / 5
Distinctiveness Conflict Risk	It targets a clear niche (git-diff scope analysis with keep/split/justify dispositions) with distinct triggers unlikely to collide with general code-review or commit-message skills.	5 / 5
	Total	20 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: Shubhamsaboo/awesome-llm-apps
Path: agent_skills/scope-creep-detector/SKILL.md
Commit: 813a55e

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.