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.

70

1.47x
Quality

58%

Does it follow best practices?

Impact

90%

1.47x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

The canonical home for this skill is speckit-analyze in g14wx/staffSync

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 analysis procedure with concrete commands, severity rules, and report schemas, plus good guardrails (read-only, approval-gated remediation). Its weaknesses are redundancy — the hook protocol appears twice verbatim — and the absence of any reference files, leaving the long inline protocol where a one-level-deep reference should be.

Suggestions

Extract the duplicated extension-hook protocol (Pre-Execution Checks and Step 9) into a single shared section or references/hooks.md, cutting ~40 lines of verbatim duplication.

Remove the off-topic shell-quoting note ('For single quotes in args like "I'm Groot"...') or move it to a reference on running the prerequisite script, since it does not advance the analysis workflow.

Provide a concrete template for the overflow summary and the zero-issues success report so the compact-report and graceful-degradation steps are as copy-paste ready as the findings table.

DimensionReasoningScore

Conciseness

The body is mostly efficient operational directives, but the ~40-line extension-hook protocol is duplicated verbatim in 'Pre-Execution Checks' and again in 'Step 9', and an off-topic shell-quoting aside ('For single quotes in args like "I'm Groot"...') pads the workflow. This fits 'mostly efficient but includes some unnecessary explanation or could be tightened'; it is not verbose enough across the board for anchor 2's 'several padded sections'.

3 / 5

Actionability

Concrete, executable guidance dominates: an exact command ('Run .specify/scripts/bash/check-prerequisites.sh --json --require-tasks --include-tasks'), precise severity heuristics with examples, a fully specified findings-table schema with an example row, and explicit next-action command suggestions. It stops short of anchor 5 because some steps remain directive rather than copy-paste ready (e.g., 'aggregate remainder in overflow summary' and 'Report zero issues gracefully' lack concrete templates), keeping minor gaps.

4 / 5

Workflow Clarity

A clear numbered 1-9 sequence with explicit checkpoints: abort with an error message if prerequisite files are missing, severity-conditioned next actions, and a user-approval gate before any remediation. The skill is strictly read-only ('Do not modify any files'), so the missing-validation cap for destructive/batch operations does not apply; it misses anchor 5 mainly for lacking explicit feedback/re-validation loops after the report.

4 / 5

Progressive Disclosure

Section headers are clear, but there are no bundle files at all, and the duplicated extension-hook protocol is inline content that clearly belongs in a shared reference file (e.g., references/hooks.md) — matching 'some structure but content that should be separate is inline'. Structure is good enough to sit above anchor 2's 'minimal structure' but below anchor 4's 'most content appropriately placed' with well-signaled references.

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 is concrete and clearly scoped to spec-kit's three core artifacts, with low conflict risk. Its main weakness is the absence of an explicit 'Use when...' trigger clause and of natural trigger synonyms, leaving both completeness and trigger quality at the midpoint.

Suggestions

Add an explicit trigger clause, e.g., 'Use when the user wants to check spec/plan/tasks consistency, find gaps in task coverage, or review artifacts before implementation.'

Enumerate 2-3 concrete analysis capabilities in the description (e.g., flags duplicates, ambiguities, coverage gaps, and constitution violations) to raise specificity from 'one-two actions' to 'several specific actions'.

Include natural user phrasings and synonyms such as 'inconsistencies', 'spec drift', or 'cross-artifact review' so trigger matching catches how users actually ask for this.

DimensionReasoningScore

Specificity

The description names its domain ('cross-artifact ... across spec.md, plan.md, and tasks.md') and 1-2 concrete actions ('consistency and quality analysis'), matching the anchor for naming domain plus 1-2 actions. It does not list several specific actions (e.g., duplication detection, ambiguity flags, coverage mapping), so it falls short of anchor 4, but it is far more concrete than the generic 'names domain, minimal actions' of anchor 2.

3 / 5

Completeness

The 'what' is clear ('non-destructive cross-artifact consistency and quality analysis'), but the 'when' is only weakly implied via the sequencing phrase 'after task generation', which describes a prerequisite rather than explicit trigger guidance. Per the judging guidelines, a missing 'Use when...' clause or equivalent explicit trigger guidance caps completeness at 3.

3 / 5

Trigger Term Quality

Relevant keywords are present ('consistency', 'analysis', 'spec.md', 'plan.md', 'tasks.md'), but natural phrases a user would say ('find inconsistencies', 'spec drift', 'review my spec/plan/tasks') and synonyms are missing, matching the 'some relevant keywords but missing common variations' anchor. It is clearly above the one-or-two-generic-keywords level of anchor 2 and below the good-coverage level of anchor 4.

3 / 5

Distinctiveness Conflict Risk

Naming the three specific artifacts ('spec.md, plan.md, and tasks.md') carves a clear spec-kit niche with minimal overlap risk, fitting 'mostly distinct; minor overlap risk'. It falls short of anchor 5 only because the trigger phrasing is not distinctive enough to guarantee the right skill fires over related spec-review skills.

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.

Validation — 14 / 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.