CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

spec-updater

Apply feedback-driven changes to a UX spec and update it in Confluence

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/ux-spec-process/skills/spec-updater/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

62%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 delivers highly concrete, well-gated guidance with an exemplary safety workflow, but it pays for it in token cost: the write-safety rules are repeated many times over and the export contract and system prompt are inlined in an already-long single file. Consolidating the repetition and splitting the reference material into bundle files would improve both conciseness and progressive disclosure.

Suggestions

State the Write-Safety Gate once, authoritatively, at the top and reference it by name elsewhere ("per the Write-Safety Gate above") instead of restating the dry-run/confirm/draft/publish rules in How It Works, the system prompt, the Safety Gates section, Validation Rules, and every example.

Create references/ bundle files — e.g., references/confluence-export.md for the Markdown→Confluence conversion contract and element mapping, and references/system-prompt.md — and link to them from the body so SKILL.md stays a lean overview.

Specify the actual tool call for Step 5 (Publish), since it is the only step in the Execution Flow without a concrete Confluence MCP invocation.

DimensionReasoningScore

Conciseness

The write-safety policy is restated at least five times — the top-level Write-Safety Gate, How It Works Step 4, the system prompt's WRITE-SAFETY rule, the Safety Gates (Milestone A) section, Validation Rules 8–10, and again in every usage example — which is noticeable padding even granting the safety emphasis. This is several unnecessary repeated sections rather than the occasional tightening a 3 would allow.

2 / 5

Actionability

Guidance is mostly executable: concrete input/output JSON schemas, a complete copy-ready system prompt, exact MCP tool calls with parameters (getConfluencePage, updateConfluencePage), a deterministic markdown→storage-format element table, and worked examples. The minor gap is Step 5 (Publish), which names no actual tool call, keeping it just below copy-paste-ready throughout.

4 / 5

Workflow Clarity

The Execution Flow gives a clear six-step sequence with explicit validation checkpoints and feedback loops for a destructive operation: dry-run preview with named target page, hard stop for explicit confirmation, draft-only write, a second confirmation gate for publishing, a pre-export link preflight, and a ten-rule validation checklist including error-recovery rules (flag contradictions, never delete without deprecating).

5 / 5

Progressive Disclosure

There are no bundle files at all — references/, scripts/, and assets/ are absent — so the 336-line body is fully self-contained with good section headers but content that should be separate is inlined. The Markdown→Confluence export contract (~40 lines including the element-mapping table) and the full system prompt are prime candidates for one-level-deep reference files, matching the 'some structure but content that should be separate is inline' anchor.

3 / 5

Total

14

/

20

Passed

Description

61%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 concise, in third person, and clearly communicates the core function, but it lacks any 'Use when...' trigger guidance and only lists two concrete actions. Adding explicit trigger phrases and one or two more capabilities would lift it substantially.

Suggestions

Add an explicit trigger clause, e.g., "Use when a stakeholder says 'update the spec', leaves review comments, or asks to apply MUST-FIX items from a design review to an existing Confluence UX spec."

Expand capability coverage slightly: mention reading the current spec from Confluence, locating affected sections by heading, and updating the Revision History — actions the skill actually performs.

Include a few natural synonyms users would say ("spec update", "review feedback", "stakeholder comments") to improve trigger-term recall.

DimensionReasoningScore

Specificity

The description names the domain (UX spec, Confluence) and two concrete actions — "Apply feedback-driven changes" and "update it in Confluence" — but stops short of the several-action coverage of the level-4 anchor (e.g., reading the current spec, parsing feedback, adding revision-history entries are all absent).

3 / 5

Completeness

It has a clear "what" (apply feedback-driven changes to a UX spec and update it in Confluence) but no "Use when..." clause or equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 3.

3 / 5

Trigger Term Quality

"feedback", "UX spec", "Confluence", and "update" are natural terms a user would plausibly say, giving good keyword coverage, but common variations like "spec update", "review comments", or "stakeholder notes" are missing, so it falls short of the comprehensive synonym coverage of a 5.

4 / 5

Distinctiveness Conflict Risk

The combination of UX spec maintenance, feedback application, and Confluence writes carves a mostly distinct niche with clear triggers; the residual overlap risk is only with closely related sibling skills (e.g., a spec-writer or generic Confluence skill), matching the level-4 anchor rather than the minimal-conflict level-5 anchor.

4 / 5

Total

14

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

Repository

mattermost/mattermost-ai-marketplace

Path

plugins/ux-spec-process/skills/spec-updater/SKILL.md

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.