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.

78

1.47x
Quality

71%

Does it follow best practices?

Impact

90%

1.47x

Average score across 3 eval scenarios

SecuritybySnyk

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/speckit-analyze/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

81%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 highly actionable with a clear, validated workflow and well-organized sections, scoring strong on actionability and workflow clarity. The main weakness is conciseness: the extension-hook template is duplicated verbatim in two places, adding notable padding.

Suggestions

De-duplicate the extension-hook template: define the optional/mandatory hook output format once and reference it from both the Pre-Execution and Step 9 sections.

Remove the second `$ARGUMENTS` occurrence in the trailing Context section since it already appears under User Input.

Consider extracting the verbose hook-formatting spec into a bundled reference file to reduce inline length and improve progressive_disclosure.

DimensionReasoningScore

Conciseness

Mostly efficient and directive without explaining known concepts, but the extension-hook template block is duplicated verbatim across Pre-Execution Checks and Step 9 (~40 lines repeated) and $ARGUMENTS appears twice, which could be tightened.

3 / 5

Actionability

Provides fully concrete, executable guidance: a specific prerequisite command with flags, absolute-path derivation, shell-escape syntax examples, named detection categories with concrete illustrations (e.g. Next.js vs Vue), and an exact report table schema with stable ID prefixes.

5 / 5

Workflow Clarity

A clear 9-step sequence with explicit validation checkpoints (prerequisite JSON check, abort with error if files missing, 'MUST run only after /speckit.tasks') and a deterministic-results checklist; error handling appropriately aborts and instructs for this read-only analysis.

5 / 5

Progressive Disclosure

No bundle files exist; the skill is a self-contained ~250-line document organized into well-signaled sections (Pre-Execution, Goal, Execution Steps 1-9, Operating Principles) with good navigation, though the large duplicated hook block is a minor organization gap that could live in one place.

4 / 5

Total

17

/

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 clearly conveys what the skill does and is well-scoped to a distinct niche, but it lacks an explicit 'Use when...' trigger clause and natural trigger-term variations, capping completeness and trigger quality. Adding concrete trigger phrases would raise both dimensions.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use after /speckit.tasks when you want to validate consistency across spec.md, plan.md, and tasks.md before implementation.'

Include natural trigger terms users would say, such as 'spec analysis', 'check my tasks', or 'spec/plan/task consistency'.

Consider listing the specific analysis actions (duplication, ambiguity, coverage, constitution alignment) to strengthen specificity beyond 'consistency and quality analysis'.

DimensionReasoningScore

Specificity

Names the domain and several concrete actions ('consistency and quality analysis') across three explicitly named artifacts (spec.md, plan.md, tasks.md) with a 'non-destructive' modifier, comparable to 'lists several specific actions; minor gaps'.

4 / 5

Completeness

The 'what' is clear (cross-artifact consistency and quality analysis), but the 'when' is only weakly implied via 'after task generation' with no explicit 'Use when...' trigger clause, which caps completeness at 3 per the rubric guideline.

3 / 5

Trigger Term Quality

Includes relevant keywords (spec.md, plan.md, tasks.md, consistency, quality analysis) but misses common natural variations or synonyms a user might say ('analyze my spec', 'check my tasks'), matching 'some relevant keywords but missing common variations'.

3 / 5

Distinctiveness Conflict Risk

Scoped to a distinct niche (spec-kit's spec.md/plan.md/tasks.md trio after task generation) with clear triggers, giving minimal overlap risk with other skills.

5 / 5

Total

15

/

20

Passed

Validation

87%

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

Validation14 / 16 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

14

/

16

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.