CtrlK
BlogDocsLog inGet started
Tessl Logo

speckit-updater

SpecKit Safe Update

44

Quality

46%

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/AI-Agents-Safe-Coding-Skills-claude/skills/speckit-updater/SKILL.md

The canonical home for this skill is speckit-updater in administrakt0r/AI-Agents-Safe-Coding-Skills

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 highly actionable and lays out a well-validated destructive-update workflow, but it is padded by a triple-stated approval flow and keeps reference-grade material inlined in one file rather than splitting it into linked references. Tightening the redundancy and extracting architecture/exit-code detail would lift it further.

Suggestions

Collapse the three repeated descriptions of the conversational approval/marker/-Proceed flow into a single authoritative section and cross-reference it from the others.

Move the Architecture/Modules, Exit Codes table, and full flag reference into separate reference files (e.g. ARCHITECTURE.md, EXIT_CODES.md) linked one level deep from the body.

Replace the hardcoded 'C:\Users\bobby\...' path with the {skill_path} placeholder everywhere, or add a note that the path must be resolved to the user's skill directory.

DimensionReasoningScore

Conciseness

The body avoids explaining concepts Claude already knows, but the conversational approval workflow, marker parsing, and -Proceed re-invocation are repeated across three separate sections ('What to do when invoked', 'Commands', and 'When you invoke this command, I will'), so it could be meaningfully tightened.

3 / 5

Actionability

It gives concrete, executable PowerShell commands with exact flags and explicit marker-parsing instructions, but the hardcoded 'C:\Users\bobby\.claude\...' path is not portable for other users — a minor gap partly mitigated by the {skill_path} form.

4 / 5

Workflow Clarity

A clearly sequenced multi-step process with validation checkpoints (prerequisite checks, fail-fast automatic rollback, one-at-a-time conflict resolution); validation is present so the destructive-operation cap does not apply, though the VSCode-only conflict path and duplicated step lists are minor gaps.

4 / 5

Progressive Disclosure

No bundle files exist and the single ~160-line file inlines reference-style content (architecture/modules, exit-code table, full flag reference) that would benefit from separate signaled files; section headers provide some structure but there are no one-level-deep references to navigate to.

3 / 5

Total

14

/

20

Passed

Description

28%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 essentially a product label ('SpecKit Safe Update') with no trigger guidance and only a vague notion of what it does. It is distinguishable only because SpecKit is a named product, not because the description itself earns it.

Suggestions

Add a 'Use when ...' clause with concrete triggers, e.g. 'Use when updating or installing GitHub SpecKit templates, or when the user mentions SpecKit updates, version bumps, or template conflicts.'

Enumerate concrete actions (e.g. 'detects customizations, creates timestamped backups, applies selective updates, resolves conflicts') instead of the single generic word 'update'.

Include natural synonyms and file/path cues (SpecKit, .specify/, template update, manifest) so users and Claude can match it to real requests.

DimensionReasoningScore

Specificity

The description 'SpecKit Safe Update' names the SpecKit domain but offers only the generic action 'update'; no concrete capabilities are enumerated, matching the 'names the domain but actions are minimal or generic' anchor.

2 / 5

Completeness

It provides a vague 'what' (safe update) and no 'when'/trigger clause whatsoever, matching the 'vague what and no when' anchor; the missing trigger guidance also caps completeness at 3 per the rubric.

2 / 5

Trigger Term Quality

Only 'SpecKit' and 'update' appear as keywords — one or two generic terms with none of the natural phrases a user would actually say, and no synonyms or extensions.

2 / 5

Distinctiveness Conflict Risk

Naming the specific product SpecKit gives it some distinctiveness, but the terse label with no trigger context leaves moderate overlap risk rather than a clear niche.

3 / 5

Total

9

/

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

description_field

'description' is very short (19 chars), consider making it more detailed

Warning

frontmatter_unknown_keys

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

Warning

Total

14

/

16

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
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.