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.

57

Quality

67%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

High

Do not use without reviewing

Fix and improve this skill with Tessl

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

Quality

Content

77%

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

The content is highly actionable and clearly sequenced with a real validation checkpoint, scoring well on actionability and workflow clarity. Conciseness and progressive disclosure are held to 2 by the duplicated extension-hook blocks and the monolithic structure lacking external references.

Suggestions

Deduplicate the extension-hook instructions: define the pre/after hook handling once and reference it from both Pre-Execution Checks and Step 9 to remove ~30 lines of redundancy.

Consolidate the two `$ARGUMENTS` blocks (User Input and Context) into a single user-input section to avoid repetition.

Extract the detailed hook output-format templates and detection-pass rules into a `references/` file and link to it, improving progressive disclosure and reducing the inline footprint.

DimensionReasoningScore

Conciseness

The body is mostly tight and assumes Claude's competence, but the extension-hook instructions are duplicated nearly verbatim in "Pre-Execution Checks" and Step 9 (~30 lines each), and `$ARGUMENTS` appears twice (User Input and Context); matches score 2 "Mostly efficient but includes some unnecessary explanation or could be tightened." Not a 3 due to the redundant hook blocks; not a 1 because most content is high-signal guidance rather than concept explanation.

2 / 3

Actionability

Quotes like "Run `.specify/scripts/powershell/check-prerequisites.ps1 -Json -RequireTasks -IncludeTasks`" and the fully specified report table, severity heuristics, and detection categories give copy-paste-ready, executable guidance; matches score 3 "Fully executable code/commands; specific examples." Not a 2 because commands and output structure are concrete rather than pseudocode.

3 / 3

Workflow Clarity

A clear 9-step sequence is presented with an explicit validation/abort checkpoint in Step 1 ("Abort with an error message if any required file is missing") and a checklist-style structure; matches score 3 "Clear sequence with explicit validation steps... checklists for complex processes." Not a 2 because validation and ordering are explicit; the read-only nature means no destructive feedback loop is required.

3 / 3

Progressive Disclosure

Sections are well-organized, but the ~245-line body is monolithic with no bundle-file references and large inline hook-instruction blocks that could live in a separate reference; matches score 2 "Some structure but... content that should be separate is inline." Not a 3 because it exceeds the simple-skill threshold and offers no one-level-deep external references; not a 1 because section organization is clear rather than a wall of text.

2 / 3

Total

10

/

12

Passed

Description

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 is specific about its artifact scope and clearly non-destructive, but it stops short of listing concrete analysis actions and omits an explicit "Use when..." trigger clause, capping completeness and trigger-term quality at 2. Distinctiveness is strong given the narrow spec-kit framing.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user wants to review spec/plan/task consistency before implementation, or mentions analyzing tasks.md, coverage gaps, or spec-kit artifacts."

Enumerate the concrete analysis actions (e.g., duplication, ambiguity, coverage gaps, constitution alignment) so the description conveys the full capability set.

Include common user-spoken phrasings like "check spec coverage" or "find inconsistencies in tasks" to improve trigger-term quality.

DimensionReasoningScore

Specificity

Quotes "cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md" name the domain and the analysis intent, but do not enumerate the concrete analysis actions (duplication, ambiguity, coverage gaps) found in the body; closest to score 2 anchor "Names domain and some actions, but not comprehensive." Not a 3 because no multiple specific concrete actions are listed; not a 1 because the artifacts and non-destructive action are explicit.

2 / 3

Completeness

The description answers "what" (analysis) and gives a timing cue ("after task generation"), but lacks a "Use when..." clause or equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 2. Not a 3 because "when" is only implied via timing; not a 1 because both what and a when-cue are present.

2 / 3

Trigger Term Quality

Phrases "spec.md, plan.md, and tasks.md" and "after task generation" supply relevant keywords, but no common user-spoken variations (e.g., "analyze tasks", "check spec coverage") or natural trigger phrasing appear; matches score 2 "Some relevant keywords but missing common variations." Not a 3 due to thin natural-term coverage; not a 1 because the artifact names are real triggers.

2 / 3

Distinctiveness Conflict Risk

The scope is tightly bound to spec-kit's three named artifacts and "after task generation," giving it a clear niche unlikely to trigger for unrelated skills; matches score 3 "Clear niche with distinct triggers; unlikely to conflict." Not a 2 because the artifact triplet is highly specific to this workflow.

3 / 3

Total

9

/

12

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
unoplatform/uno
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.