speckit-analyze

Perform cross-artifact consistency analysis across spec.md, plan.md, and tasks.md. Use after task generation to identify gaps, duplications, and inconsistencies before implementation.

Quality

65%

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

Fix and improve this skill with Tessl

tessl review fix ./bundled/skills/speckit-analyze/SKILL.md

Quality

Content

67%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 content is a well-sequenced, highly actionable read-only analysis workflow with explicit validation and a structured report format. Its main weakness is mild redundancy that could be tightened to improve token efficiency.

Suggestions

Remove the duplicated $ARGUMENTS block (present in both 'User Input' and 'Context') and consolidate the read-only constraint so it is stated once.

Factor the severity heuristic and detection-pass definitions into a reference file (e.g. references/detection.md) referenced one level deep, which would improve progressive_disclosure and conciseness.

Add an explicit re-run/determinism note as a validation checkpoint after report generation to confirm stable IDs and counts before offering remediation.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and avoids over-explaining known concepts, but contains redundancy: $ARGUMENTS appears in both 'User Input' and 'Context', and the read-only constraint is restated in both 'Operating Constraints' and 'Analysis Guidelines', fitting the score-3 anchor.	3 / 5
Actionability	It provides a concrete executable prerequisite command, explicit path derivation, named detection passes with examples, a severity heuristic with worked examples, and a report template with a sample table row, matching the score-4 anchor with only minor gaps.	4 / 5
Workflow Clarity	A clear 8-step sequence is present with an explicit abort-on-missing-file validation checkpoint in step 1; because the skill is read-only the destructive-cap does not apply, but it lacks a validate-fix-retry feedback loop, so it stays at score 4 rather than 5.	4 / 5
Progressive Disclosure	No bundle files exist, and the body is organized into clearly headed sections with no nested references and appropriately inline content for a self-contained instruction skill, matching the score-4 anchor with minor organization gaps.	4 / 5
	Total	15 / 20 Passed

Description

62%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 and clearly conveys both purpose and workflow timing, but its trigger phrasing is procedural rather than natural user language and lacks synonym coverage. Strengthening natural-language triggers would lift completeness and trigger-term quality.

Suggestions

Add natural-language trigger phrases a user would actually say, e.g. 'Use when the user asks to review, audit, or check their spec/plan/tasks for gaps or inconsistencies.'

Include common synonyms (review, audit, check, validate) alongside 'analysis' to broaden trigger-term coverage.

Optionally surface the compatibility constraint ('Requires spec-kit project structure with .specify/ directory') inside the description so users can self-select the right skill.

Dimension	Reasoning	Score
Specificity	Names the domain (cross-artifact consistency across spec.md/plan.md/tasks.md) and concrete outputs (gaps, duplications, inconsistencies), but it is effectively one analytical action with listed outputs rather than several distinct actions, matching the score-3 anchor.	3 / 5
Completeness	It clearly states both what the skill does and when to use it ('Use after task generation ... before implementation'), but the 'when' is a procedural workflow-position trigger rather than natural user-utterance trigger phrases, so it does not reach the score-5 anchor.	4 / 5
Trigger Term Quality	Relevant keywords like 'spec.md', 'plan.md', 'tasks.md', 'gaps', 'duplications', and 'inconsistencies' appear, but common natural synonyms a user might say (review, audit, check, validate) are missing, fitting the score-3 anchor.	3 / 5
Distinctiveness Conflict Risk	Scoped to spec-kit's three specific artifacts with a read-only analysis scope, giving it a clear niche with minimal conflict risk, but it belongs to a family of related speckit-* skills with minor overlap risk, matching the score-4 anchor.	4 / 5
	Total	14 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: foryourhealth111-pixel/Vibe-Skills
Path: bundled/skills/speckit-analyze/SKILL.md
Commit: ddcaa2a

Reviewed: 10 days 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.