CtrlK
BlogDocsLog inGet started
Tessl Logo

speckit-analyze

Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.

75

1.47x
Quality

67%

Does it follow best practices?

Impact

90%

1.47x

Average score across 3 eval scenarios

SecuritybySnyk

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./.claude/skills/speckit-analyze/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Discovery

57%

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 identifies a clear and distinctive niche (cross-artifact consistency analysis for spec/plan/tasks files) but suffers from vague action language and lacks an explicit 'Use when...' clause. The technical phrasing ('non-destructive cross-artifact consistency') may not match how users naturally request this functionality.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user wants to verify consistency between spec.md, plan.md, and tasks.md, or after generating tasks from a plan.'

List specific concrete actions performed, e.g., 'Checks for missing requirements coverage, detects contradictions between spec and plan, validates task completeness against plan milestones.'

Include natural trigger terms users might say, such as 'review tasks', 'check plan alignment', 'validate spec coverage', or 'verify task completeness'.

DimensionReasoningScore

Specificity

It names the domain (cross-artifact consistency and quality analysis) and specifies the artifacts involved (spec.md, plan.md, tasks.md), but the actual concrete actions beyond 'analysis' are vague — it doesn't list what specific checks or outputs are produced.

2 / 3

Completeness

It answers 'what' (consistency and quality analysis across three artifacts) and partially implies 'when' ('after task generation'), but lacks an explicit 'Use when...' clause with trigger guidance for Claude to know when to select this skill.

2 / 3

Trigger Term Quality

Includes some relevant terms like 'spec.md', 'plan.md', 'tasks.md', 'consistency', and 'quality analysis', but misses natural user phrases like 'review tasks', 'check plan', 'validate spec', or 'verify alignment'. The phrase 'non-destructive cross-artifact consistency' is more technical jargon than natural language.

2 / 3

Distinctiveness Conflict Risk

The description targets a very specific niche — cross-artifact consistency checking across exactly spec.md, plan.md, and tasks.md after task generation — which is unlikely to conflict with other skills.

3 / 3

Total

9

/

12

Passed

Implementation

77%

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

This is a well-structured, highly actionable skill for cross-artifact consistency analysis with clear multi-step workflows, explicit validation gates, and concrete output formats. Its main weaknesses are the duplicated extension hook logic (pre/post) which inflates token count, and the monolithic structure that could benefit from splitting detailed sub-procedures into referenced files. The severity framework and coverage mapping approach are particularly strong.

Suggestions

Extract the duplicated extension hook checking logic (Steps 0 and 9) into a shared reference file or a single reusable procedure description referenced by both steps, reducing ~40 lines of near-identical content.

Consider splitting detection pass details (Step 4 A-F) into a separate DETECTION_PASSES.md reference file, keeping only a summary list in the main skill body to improve progressive disclosure.

DimensionReasoningScore

Conciseness

The skill is detailed and mostly necessary given the complexity of the multi-artifact analysis task, but there is significant repetition—the extension hook logic is duplicated nearly verbatim for pre- and post-hooks (Steps 0 and 9), and some sections like 'Operating Principles' restate constraints already covered in 'Operating Constraints'. The semantic model building instructions are appropriately detailed but could be tighter.

2 / 3

Actionability

The skill provides highly concrete, executable guidance: specific shell commands (check-prerequisites.sh with exact flags), explicit file paths, structured output format with exact Markdown table schemas, specific detection categories with examples of what to flag (e.g., 'fast, scalable, secure' as vague adjectives, 'TODO, TKTK, ???' as placeholders), and clear severity heuristics. The report format is copy-paste ready.

3 / 3

Workflow Clarity

The 9-step workflow is clearly sequenced with explicit validation checkpoints: Step 1 aborts if prerequisites are missing, Step 4 has structured detection passes, Step 5 assigns severity, and Step 7 provides conditional next actions based on severity levels. The read-only constraint is reinforced multiple times, and the remediation step (8) explicitly requires user approval before any changes, serving as a safety checkpoint.

3 / 3

Progressive Disclosure

The skill is a monolithic document (~200+ lines) with no references to external files for detailed sub-topics. The extension hook handling logic, detection pass details, and semantic model specifications could be split into referenced files. However, given no bundle files are provided, the content is reasonably well-organized with clear headers and subsections within the single file.

2 / 3

Total

10

/

12

Passed

Validation

81%

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

Validation9 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

9

/

11

Passed

Repository
mixpanel/mixpanel-headless
Reviewed

Table of Contents

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.