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.

52

Quality

58%

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

63%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 well-sequenced, highly actionable read-only analysis workflow with a concrete prerequisite command and defined output schema, but it pays a conciseness and progressive-disclosure penalty from a duplicated ~30-line hook block and a monolithic all-inline structure with no external references.

Suggestions

De-duplicate the extension-hook handling block: define it once and reference it from both Pre-Execution Checks and Step 9 to recover ~30 lines of token budget.

Extract the verbose hook command-templating rules into a referenced file (e.g. references/hooks.md) and link to it, improving progressive disclosure and conciseness simultaneously.

Add an explicit validate→fix→retry note for the analysis output (e.g. re-run prerequisite check if JSON parse fails, then re-emit report) to push workflow clarity toward a feedback-loop model.

DimensionReasoningScore

Conciseness

Quotes the near-verbatim duplication of the extension-hook handling block in both 'Pre-Execution Checks' and 'Step 9. Check for extension hooks' (~30 lines repeated), plus occasional over-explanation; the body is mostly efficient but could be tightened by factoring the hook block once, fitting 'mostly efficient but includes some unnecessary content' rather than the lean level 4.

3 / 5

Actionability

Quotes the concrete command '.specify/scripts/powershell/check-prerequisites.ps1 -Json -RequireTasks -IncludeTasks', the explicit output table schema with defined columns, and named detection passes with severity heuristics — mostly executable, copy-paste-ready guidance with only minor gaps, sitting at level 4 short of the fully-exhaustive level 5.

4 / 5

Workflow Clarity

Quotes the clearly sequenced nine execution steps and the abort checkpoint ('Abort with an error message if any required file is missing'); the sequence and most checkpoints are present, but there is no explicit validate→fix→retry feedback loop for the analysis output itself, so it lands at 'clear sequence with most checkpoints' rather than the feedback-loop level 5.

4 / 5

Progressive Disclosure

Quotes a single ~250-line monolithic body with no bundle files and no external references; section headers organize it well, but the large duplicated hook-handling content and bulk detail are inlined rather than split into referenced files, matching 'some structure but content that should be separate is inline.'

3 / 5

Total

14

/

20

Passed

Description

53%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 a narrow, well-scoped niche (cross-artifact spec-kit analysis) with named artifacts, but it lacks an explicit 'Use when...' trigger clause and relies on technical artifact names rather than natural user phrases, capping trigger quality and completeness at the mid-level.

Suggestions

Add an explicit trigger clause, e.g. 'Use when reviewing spec-kit artifacts for consistency after /speckit.tasks, or when the user asks to check spec/plan/tasks alignment.'

Expand the action list from the single 'analysis' verb to concrete actions like 'identifies inconsistencies, duplications, ambiguities, and coverage gaps' to raise specificity.

Include natural-language synonyms users might say (e.g. 'spec review', 'plan/tasks audit', 'spec drift') alongside the file-name triggers.

DimensionReasoningScore

Specificity

Quotes 'Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md' — names the domain and the analysis action but does not enumerate several specific concrete actions (it is essentially one analysis verb), matching the '1-2 concrete actions' anchor and falling short of the 'several specific actions' level 4.

3 / 5

Completeness

Quotes a clear 'what' ('cross-artifact consistency and quality analysis') with only a weakly implied 'when' ('after task generation') and no explicit 'Use when...' clause; per the judging guideline a missing explicit trigger clause caps completeness at 3.

3 / 5

Trigger Term Quality

Quotes 'spec.md, plan.md, and tasks.md' and 'after task generation' — relevant domain keywords are present, but these are spec-kit technical artifact names rather than natural user phrasings, and common variations/synonyms are missing, fitting the 'some relevant keywords but missing common variations' anchor.

3 / 5

Distinctiveness Conflict Risk

Quotes 'across spec.md, plan.md, and tasks.md after task generation' — a clear, narrow niche tied to three named spec-kit artifacts with low conflict risk, but other spec-kit analysis commands could plausibly overlap, so it sits at 'mostly distinct; minor overlap risk' rather than the fully-distinct level 5.

4 / 5

Total

13

/

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
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.